# Welcome to i10X Your all-in-one AI workspace. Chat with the world's best models, create stunning visuals, run deep research, and automate your entire workflow - all from one place. Not sure where to start? This Knowledge Center will guide you through everything i10x.ai can do - step by step, no technical knowledge required. {% hint style="info" %} πŸ’‘ New here? Start with Chat & Research β†’ Chat. Leave the model on Auto, type your first question, and see what i10x.ai can do. {% endhint %} ### What do you want to do today?
Cover image
Chat & ResearchAsk questions, research topics, analyze documents, and compare AI models side by side./pages/LM9OvGZT05DAfIFE81Pv/files/VJRTPwgGvIgFQQ925A1q
CreateGenerate AI images and videos using the world's most powerful creative models./pages/0724KtugzuLtSjEShF8W/files/zUC2P1V8TQAmFpfTaJp8
DiscoverBrowse 500+ specialized AI agents built for specific tasks β€” find the one that fits your workflow./pages/20A398prLgApYaXjY2yt/files/Lu2vbTzTR1g4erI0ysDz
Agent BuilderBuild your own AI agents and chatbots. No coding required./pages/APPEhkFS5Fsakmx25wX7/files/vwgUkqtxHL0wr7JankHE
AutomationsConnect your apps and build no-code workflows that run on autopilot./pages/7RRG92GPGwHf6gvaA2eQ/files/swnXxG3m7CfsjfyYZy7F
{% hint style="info" %} βœ… Every section in this Knowledge Center follows the same structure: What it is β†’ Why it's useful β†’ How to use it. Start anywhere. {% endhint %} # Chat & Research Everything you need to ask questions, conduct research, analyze documents, and compare AI models - all in one place. Chat & Research is the command centre of i10x.ai. Whether you need a quick answer, a deep research report, or want to chat with your own documents - this is where it all happens. ### What's inside Chat & Research?
Cover image
ChatChat with 20+ AI models including GPT-5, Gemini, Claude and more. Connect your apps, upload files, and let AI work with your real data./pages/fX9PKvcPD0aIt1LyvzNL/files/fde8IIyHMdAm2SVBTBHn
Chat ArenaRun the same prompt through multiple AI models simultaneously and compare results side by side. Let the best answer win./pages/OgbqI3CAScA4ocFsBo7q/files/4sbZH3bdfDBXeZ03snS0
Deep ResearchGet structured, cited research reports on any topic. i10x searches the web autonomously and synthesizes multiple sources for you./pages/qrj4JHr7EqMHCUiITGoa/files/NB2JV21cgc6AzzDQxPq2
ChatPDFUpload any document and have a conversation with it. Ask questions, get summaries, and extract key insights instantly./pages/CDh8PgUsFQZQSJ3XQk0A/files/lycc6DsyzFotHDISG0uo
{% hint style="info" %} πŸ’‘ Not sure which tool to use? Start with Chat for quick questions, Deep Research for detailed reports, and ChatPDF when you have a specific document to analyze. {% endhint %} # Chat Chat with 20+ of the world's best AI models, connect your apps, upload files, search the web in real time, and let AI work with your actual data. Chat is the heart of i10x.ai. It looks like a simple chat window - but underneath it is one of the most powerful AI environments available. This page explains every feature so you can get the most out of every conversation. {% hint style="info" %} πŸ’‘ Just getting started? Leave everything on default settings and type your first question. The Auto model will handle the rest. {% endhint %} ### Choosing Your AI Model At the bottom left of the chat bar you will see the model selector. By default it is set to Auto. Auto means i10x.ai analyzes your prompt and automatically routes it to the best available model for that specific task. You do not need to know the difference between GPT-5 and Gemini to get great results. Want more control? Click the model selector to manually choose a model from the list below. | Model | Best For | Speed | | --------------------------------- | -------------------------------------------------- | ----------- | | **Auto** | Everything - let i10x decide | ⚑ Fast | | **GPT-5** | Complex reasoning, long documents, nuanced writing | 🐒 Thorough | | **GPT-5 Mini** | Quick everyday tasks, summaries, Q\&A | ⚑ Fast | | **GPT-5 Nano** | Ultra-fast simple tasks | ⚑⚑ Fastest | | G**PT-4.1** | Reliable all-rounder, writing and coding | ⚑ Fast | | **Gemini 2.5 Pro** | Massive documents, multi-modal reasoning | 🐒 Thorough | | **Gemini 2.5 Flash** | Fast and efficient everyday tasks | ⚑ Fast | | **Gemini 3.1 Pro Preview** | Advanced reasoning and research | 🐒 Thorough | | **Gemini 3.1 Flash Lite Preview** | Speed-optimised tasks | ⚑⚑ Fastest | | **Gemini 3 Pro Preview** | Balanced reasoning and speed | ⚑ Fast | | **Claude 4.6 Sonnet** | Writing, analysis, nuanced conversation | ⚑ Fast | | **Claude 4.6 Opus** | Deep reasoning and complex analysis | 🐒 Thorough | | **Claude Haiku 4.5** | Fast and lightweight tasks | ⚑⚑ Fastest | | **Grok 4** | Real-time web knowledge, current events | ⚑ Fast | | **Grok 4.1 Fast** | Speed-first tasks | ⚑⚑ Fastest | | **Grok Code Fast** | Code generation and debugging | ⚑ Fast | | **DeepSeek V3** | Technical reasoning and STEM tasks | ⚑ Fast | | **Meta LLaMA 4 Scout** | Lightweight open-source tasks | ⚑ Fast | | **Meta LLaMA 4 Maverick** | More powerful open-source tasks | 🐒 Thorough | | **Z.ai** | Experimental and creative tasks | ⚑ Fast | {% hint style="info" %} πŸ’‘ Not sure which model to pick? Here is the simple rule:\ Use Auto for everything. Switch to GPT-5 or Claude 4.6 Opus when you need deep analysis. Switch to GPT-5 Nano, Gemini Flash or Claude Haiku when you need speed. {% endhint %} ### Prompt Optimizer Not getting the result you expected? Click the wand icon (✨) next to the input bar before sending your message. i10x will automatically rewrite and improve your prompt to extract the best possible response from the AI - no prompt engineering experience needed. Think of it as having a professional prompt engineer on standby, for free. ### Voice Input Prefer to talk rather than type? Click the microphone icon in the chat bar to speak your prompt. i10x will transcribe your voice and send it to the AI instantly. {% hint style="info" %} ⚠️ Note: Voice input is supported. Voice playback (AI speaking back to you) is not available yet. {% endhint %} ### The "+" Menu - Supercharge Your Chat Click the blue + icon in the chat bar to unlock four powerful features that give the AI more context about you and your work.
🧠 Memory Memory is active by default. This means i10x remembers important context from your past conversations - your preferences, your projects, your name - so you never have to repeat yourself. You can toggle Memory OFF if you want a completely fresh, anonymous session.
πŸ“Ž Upload Files Attach documents directly to your chat for instant analysis. Supported formats include: PDF, Word (.docx), Excel (.xlsx), Google Docs exports, and more. Best for one-off tasks:\ β†’ "Summarize this contract."\ β†’ "Find the key numbers in this spreadsheet."\ β†’ "What are the action items in this meeting transcript?" Need the AI to remember a document permanently across multiple chats? Use Knowledge Base instead.
🌐 Web Search Enable Web Search to give the AI access to live, real-time information from the internet - including breaking news, current prices, recent research papers, and more. Turn this ON whenever your question involves anything time-sensitive or recent. Example:\ β†’ "What are the top AI funding deals this week?"\ β†’ "What is the current Bitcoin price?"\ β†’ "Summarize the latest research on GLP-1 drugs."
πŸ“š Knowledge Base Your Knowledge Base is a permanent document library connected to your i10x account. Create folders (e.g. "Client Contracts," "Research Papers," "Company SOPs") and the AI can reference them in any future chat. The difference between File Upload and Knowledge Base:\ β†’ File Upload = one session, one document, gone when the chat ends.\ β†’ Knowledge Base = permanent, always available, works across all chats. To set up your Knowledge Base, click "Knowledge Base" in the left sidebar of your i10x dashboard.
### Connect Your Apps Click the Connector icon (πŸ”Œ) in the chat bar to link your favourite apps directly to your chat. Once connected, you can talk to your real data - no copy-pasting, no switching tabs. | App | What You Can Ask | | ------------------- | ---------------------------------------------------------------- | | **Gmail** | "Summarize my last 5 unread emails and flag anything urgent." | | **Google Calendar** | "What does my Tuesday look like? Find me a free 30-minute slot." | | **Google Drive** | "Find the Q3 report I uploaded last week and summarize it." | | **Google Docs** | "Expand the introduction of my proposal document." | | **Google Sheets** | "Analyze the data in my sales tracker and identify trends." | | **Google Slides** | "Summarize the key points from my pitch deck." | | **Google Forms** | "What are the most common responses in my feedback form?" | | **Google Tasks** | "What tasks do I have due this week?" | | **Notion** | "Update my Q3 roadmap page with these meeting notes." | | **Firefly** | "Access and reference my creative assets." | {% hint style="info" %} βœ… Try This Now: 1. Click the Connector icon (πŸ”Œ) and connect Gmail. 2. Make sure Web Search is ON. 3. Type: "Summarize my last 5 unread emails and flag anything urgent." You just built your first AI email assistant. Welcome to i10x.ai. {% endhint %} # Chat Arena Run the same prompt through multiple AI models at the same time and compare results side by side. Stop guessing which AI is best - let them compete. Every AI model has different strengths. GPT-5 might write a better structure. Claude might nail the tone. Gemini might find better sources. Chat Arena lets you test them all at once - with a single prompt. {% hint style="info" %} πŸ’‘ Chat Arena is perfect when the quality of your output really matters - like a client proposal, an important email, or a critical piece of research. {% endhint %} ### When Should You Use Chat Arena? Use Chat Arena when you want the best possible answer and don't want to rely on a single model's perspective. | Situation | Why Chat Arena Helps | | --------------------------- | ----------------------------------------------------------- | | Writing an important email | Compare tone and structure across models | | Researching a complex topic | See which model gives the most accurate and complete answer | | Generating creative content | Get multiple creative variations in one shot | | Debugging code | Let multiple models attempt the fix simultaneously | | Making a business decision | Get different analytical perspectives at once | ### How to Use Chat Arena 1. Click "Chat Arena" in the left sidebar under Chat & Research. 2. Select 2 or more models from the model selector at the top. 3. Type your prompt once in the input bar at the bottom. 4. Hit Send β€” your prompt is sent to all selected models simultaneously. 5. Review the responses side by side. 6. Copy the best response or combine the strongest elements from each. {% hint style="info" %} πŸ’‘ Pro Tip: Try running the same prompt through Claude 4.6 Sonnet and GPT-5 when writing proposals or reports. Claude tends to excel at tone and flow, while GPT-5 tends to excel at structure and detail. Combine both for the strongest result. {% endhint %} ### Chat vs. Chat Arena - Which Should I Use? | | Chat | Chat Arena | | ------------ | ---------------------------------------- | ----------------------------------------- | | **Best For** | Quick tasks, back-and-forth conversation | High-stakes outputs where quality matters | | **Models** | One model at a time | Multiple models simultaneously | | **Output** | Single response | Multiple responses to compare | | **Speed** | Fastest | Slightly slower (running multiple models) | | **Use When** | You need a quick answer | You need the best possible answer | {% hint style="info" %} βœ… Try This Now: 1. Open Chat Arena. 2. Select Claude 4.6 Sonnet and GPT-5. 3. Type: "Write a 3-sentence intro for a proposal about improving team productivity using AI." 4. Compare both responses and pick your favourite. {% endhint %} # Deep Research Deep Research autonomously searches the web, synthesizes multiple sources, and delivers structured, cited reports on any topic - in minutes. There is a big difference between asking an AI a question and asking an AI to research a topic. Deep Research does the latter. Powered by the same technology behind Perplexity, Deep Research doesn't just answer your question - it goes out to the web, reads multiple sources, cross-references the information, and delivers a structured report with real citations you can verify. {% hint style="info" %} There is a big difference between asking an AI a question and asking an AI to research a topic. Deep Research does the latter. Powered by the same technology behind Perplexity, Deep Research doesn't just answer your question β€” it goes out to the web, reads multiple sources, cross-references the information, and delivers a structured report with real citations you can verify. {% endhint %} ### Chat vs. Deep Research - What's the Difference? Both Chat and Deep Research use AI - but they are built for very different jobs. | | Chat | Deep Research | | ------------- | -------------------------------------------- | --------------------------------------- | | **Best for** | Quick questions, back-and-forth conversation | In-depth reports on a specific topic | | **Sources** | Single AI model's knowledge | Multiple live web sources | | **Output** | Conversational answer | Structured report with citations | | **Time** | Seconds | 1-3 minutes | | **Citations** | Rarely included | Always included | | **Use when** | You want a quick answer | You need to trust and verify the output | ### How to Use Deep Research 1. Click "Deep Research" in the left sidebar under Chat & Research. 2. Type your research topic or question in the input bar. 3. Hit Send β€” Deep Research will begin autonomously searching the web. 4. Wait 1–3 minutes while it reads and synthesizes multiple sources. 5. Review your structured report with cited sources at the bottom. 6. Click any citation to verify the original source directly. {% hint style="info" %} πŸ’‘ The more specific your prompt, the better your report. Instead of: "Tell me about AI."\ Try: "What are the top 5 enterprise AI trends in 2025 and how are Fortune 500 companies adopting them?" {% endhint %} ### What Can You Research? Deep Research works best for topics where accuracy, sources, and up-to-date information matter. Here are some examples: | Use Case | Example Prompt | | ------------------------ | --------------------------------------------------------------------------- | | **Competitive Analysis** | "Compare the top 5 AI writing tools available in 2026." | | **Market Research** | "What is the current state of the B2B SaaS market in Southeast Asia?" | | **Investment Research** | "What are investors looking for in Series A AI startups right now?" | | **Academic Research** | "Summarize the latest clinical research on GLP-1 weight loss drugs." | | **Industry News** | "What are the biggest AI funding deals in the last 30 days?" | | **Legal & Regulatory** | "What are the latest EU AI Act compliance requirements for SaaS companies?" | | **Technology Trends** | "What are the most adopted no-code automation tools in 2026?" | ### Understanding Your Report Every Deep Research report follows the same structure: β†’ Summary - A concise overview of the key findings.\ β†’ Detailed Sections - The full breakdown of the topic, organized by theme.\ β†’ Citations - Every claim is linked to a real, verifiable web source. You can copy the full report, export it, or paste it directly into your workflow. {% hint style="info" %} βœ… Try This Now: Type this into Deep Research: "What are the top 5 AI productivity tools for founders in 2025 and what makes each one unique?" In under 3 minutes you will have a fully sourced competitive report - ready to share. {% endhint %} # ChatPDF Upload any PDF document and ask it questions. No more scrolling through 80-page reports - just ask and get instant, accurate answers. Reading long documents is slow, painful, and inefficient. ChatPDF changes that completely. Upload any PDF file - a contract, a research paper, a financial report, a pitch deck - and simply ask it questions in plain language. i10x reads the entire document and responds instantly, pulling the exact information you need. {% hint style="info" %} πŸ’‘ Think of ChatPDF as having a conversation with your document. Instead of reading it cover to cover, you ask it exactly what you need to know. {% endhint %} ### Supported File Types ChatPDF works with PDF files (.pdf). {% hint style="info" %} ⚠️ Only PDF files are supported. If your document is in Word or Excel format, export or save it as a PDF first before uploading. {% endhint %} ### How to Use ChatPDF 1. Click "ChatPDF" in the left sidebar under Chat & Research. 2. Click the upload area and select your document - or drag and drop it directly. 3. Wait a few seconds while i10x reads and processes the file. 4. Type your first question in the chat bar on the right. 5. Get instant, accurate answers pulled directly from your document. ### What Can You Ask? Here are some of the most powerful ways to use ChatPDF: | Task | Example Prompt | | ------------------------ | --------------------------------------------------------- | | **Summarize** | "Summarize this document in 5 bullet points." | | **Find key information** | "What are the key risks mentioned in this contract?" | | **Extract data** | "List every price and fee mentioned in this agreement." | | **Simplify language** | "Explain the executive summary in plain English." | | **Find action items** | "What are the action items and deadlines in this report?" | | **Compare sections** | "What is the difference between Section 3 and Section 7?" | | **Research papers** | "What methodology did the researchers use in this study?" | | **Financial reports** | "What was the revenue growth between Q1 and Q3?" | ### ChatPDF vs. Knowledge Base - Which Should I Use? Both features let you chat with documents - but they serve different purposes. | | ChatPDF | Knowledge Base | | ------------------- | --------------------------------------- | --------------------------------------------- | | **Best for** | Analyzing one document right now | Storing multiple documents for ongoing use | | **Persistence** | Session only - document is not saved | Permanent - always accessible in your account | | **Number of files** | One at a time | Multiple files across multiple folders | | **Use when** | You have a single file to analyze today | You want the AI to always know your documents | {% hint style="info" %} πŸ’‘ Working on an ongoing project with multiple documents?\ Upload them to your Knowledge Base instead. That way the AI can reference all of them across any chat - not just in a single session. {% endhint %} {% hint style="info" %} βœ… Try This Now: 1. Find any PDF on your computer - a contract, a report, an article. 2. Upload it to ChatPDF. 3. Type: "Summarize this document in 5 bullet points and list the 3 most important things I need to know." You just saved yourself 30 minutes of reading. {% endhint %} # AI Image Create professional-quality images from a simple text description. Access the world's most powerful image generation models - all in one place. With i10x.ai Image, you don't need a designer, a stock photo subscription, or any creative software. Just describe what you want to see - and watch it come to life in seconds. Whether you need a product mockup, a social media visual, a blog header, or a piece of concept art - i10x has the right model for the job. {% hint style="info" %} πŸ’‘ The quality of your image depends heavily on the quality of your prompt. The more descriptive you are - style, mood, colours, composition - the better the result. {% endhint %} ### How to Generate an Image 1. Click "Image" in the left sidebar of your i10x dashboard. 2. Select your preferred image model. 3. Type a detailed description of the image you want to create. 4. Choose your image dimensions and settings. 5. Click Generate and wait a few seconds. 6. Download your image or generate variations. ### Choosing Your Image Model Each image model has a distinct style, strength, and best use case. Here is a breakdown of every model available in i10x.ai so you can pick the right one for your project. | Model | Best For | Style | Speed | | -------------------------- | --------------------------------------------------------------------- | -------------------------- | ----------- | | **GPT-Image-1.5** | High-quality general purpose images, text in images | Photorealistic & versatile | ⚑ Fast | | **GPT-Image-1** | Reliable all-rounder for most tasks | Photorealistic & versatile | ⚑ Fast | | **DALL-E 3** | Creative and artistic concepts, strong prompt understanding | Illustrative & artistic | ⚑ Fast | | **DALL-E 2** | Simple quick generations, lower credit cost | Basic & illustrative | ⚑⚑ Fastest | | **Google Nano-Banana** | Image editing and transformation tasks | Photorealistic editing | ⚑ Fast | | **Google Nano-Banana Pro** | High-resolution editing, up to 2K, supports up to 10 reference images | Photorealistic editing | 🐒 Thorough | | **Google Imagen 4** | Photorealistic scenes, product photography | Ultra-realistic | 🐒 Thorough | | **xAI Imagine** | Creative and experimental visuals | Bold & stylized | ⚑ Fast | | **FLUX Pro 1.1 Ultra** | Ultra-detailed, highest quality outputs | Hyper-realistic & detailed | 🐒 Thorough | | **FLUX Pro 1.1** | High quality with a good speed/quality balance | Realistic & detailed | ⚑ Fast | {% hint style="info" %} πŸ’‘ Quick Guide: β†’ Need the best quality? Use FLUX Pro 1.1 Ultra or Google Imagen 4.\ β†’ Need to edit or transform an existing image? Use Google Nano-Banana or Google Nano-Banana Pro.\ β†’ Need speed and reliability? Use GPT-Image-1.5 or DALL-E 3.\ β†’ Want to experiment creatively? Try xAI Imagine or DALL-E 3.\ β†’ On a tight credit budget? Use DALL-E 2 for simple tasks. {% endhint %} ### Understanding the Settings Each model has its own settings panel. While the exact options vary slightly between models, here is what you will commonly find and what each setting means: | Settings | What it does | | ---------------------- | --------------------------------------------------------------------------------------------------------------------------- | | **Prompt** | Describe the image you want to create. The more detail the better. | | **Quality** | Controls the level of detail and rendering. Higher quality = sharper result, more credits. | | **Size / Resolution** | The dimensions of the output image. Choose based on where you will use it (e.g. square for social media, wide for banners). | | **Aspect Ratio** | The width-to-height ratio. Use 1:1 for social media, 16:9 for video thumbnails and presentations. | | **Background** | Set to transparent if you need a cutout for design work. | | **Reference Images** | Upload existing images to guide, transform, or edit. Depending on the model you can upload up to 3–10 reference images. | | **Input Fidelity** | How closely the output follows your reference image. Low = more creative freedom. High = stays closer to your reference. | | **Output Format** | The file format of the generated image. Use `webp` or `jpg` for web use. Use `png` for transparent backgrounds. | | **Output Compression** | Controls file size vs. quality. The default is the sweet spot for most use cases. | ### Pricing Each model has a different credit cost per generation depending on the quality and complexity of the output. You can see the exact credit cost and estimated number of runs at the bottom of each model's settings panel before you hit Generate. {% hint style="info" %} πŸ’‘ Credit Tip: Test your prompt with a faster, lower-cost model first to get the composition and style right. Once you are happy, switch to a premium model like FLUX Pro 1.1 Ultra or Google Imagen 4 for the final high-quality version. {% endhint %} ### Writing a Great Image Prompt The more detail you give, the better your result. A strong image prompt includes: β†’ Subject - What is the main focus of the image?\ β†’ Style - Is it photorealistic, illustrated, cinematic, minimalist?\ β†’ Mood - Is it bright and energetic, dark and moody, warm and inviting?\ β†’ Colours - Any specific colour palette?\ β†’ Composition - Close-up, wide shot, bird's eye view? | ❌ Weak Prompt | βœ… Strong Prompt | | ----------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------- | | **"A coffee shop"** | "A cozy independent coffee shop interior, warm golden lighting, exposed brick walls, steam rising from a coffee cup, photorealistic, wide shot" | | **"A business person"** | "A confident female founder presenting to investors in a modern glass boardroom, natural daylight, professional photography style" | | **"A logo"** | "A minimalist tech startup logo, geometric design, deep blue and white, clean lines, vector style, white background" | | **"A landscape"** | "A dramatic mountain sunrise, golden hour lighting, misty valleys, aerial perspective, hyper-realistic photography style" | ### Use Cases | Who | What They Create | | ------------------------ | ------------------------------------------------------ | | **Founders & Marketers** | Social media visuals, ad creatives, pitch deck imagery | | **Content Creators** | Blog headers, YouTube thumbnails, newsletter visuals | | **Freelancers** | Client mockups, brand concepts, presentation visuals | | **Students** | Project visuals, presentations, creative assignments | | **Developers** | App mockups, UI concepts, icon designs | {% hint style="info" %} βœ… Try This Now: Type this into the Image generator: "A sleek, modern AI dashboard interface on a MacBook screen, dark mode, glowing blue accents, minimal design, photorealistic, soft studio lighting." See what i10x.ai creates in seconds. {% endhint %} # AI Video Turn a text prompt or a single image into a high-quality video clip. Access the world's most powerful video generation models - all in one place. AI video generation has changed completely. What used to take a full production team can now be done in minutes with a single text prompt. Whether you need a product demo, a social media clip, a cinematic scene, or an animated concept - i10x.ai gives you access to the best video models available, all from one interface. {% hint style="info" %} πŸ’‘ Video generation takes longer than image generation - typically between 30 seconds and a few minutes depending on the model and settings. Be patient, the result is worth it. {% endhint %} ### How to Generate a Video 1. Click "Video" in the left sidebar of your i10x dashboard. 2. Select your preferred video model. 3. Write a detailed prompt describing the video you want to create. 4. Adjust the settings (aspect ratio, duration, reference images). 5. Click Generate Video and wait for your clip to render. 6. Preview, download, or regenerate with adjusted settings. ### Choosing Your Video Model Each video model has different strengths, styles, and credit costs. Here is a breakdown to help you pick the right one: | Model | Best For | Highlights | Speed | | ------------------------- | ------------------------------------------------ | ------------------------------------------------------------------------------------------- | ----------- | | **OpenAI Sora 2** | High-quality general purpose video, synced audio | OpenAI's flagship video model, strong prompt understanding | ⚑ Fast | | **Sora 2 Pro** | Premium cinematic quality, complex scenes | Highest quality Sora output, more detail and realism | 🐒 Thorough | | **Google Veo 3.1** | Cinematic video with context-aware audio | Higher fidelity, supports first frame + last frame interpolation and reference images (R2V) | 🐒 Thorough | | **Google Veo 3 Standard** | Balanced quality and cost | Great all-rounder for most video tasks | ⚑ Fast | | **Google Veo 3 Fast** | Speed-first generation | Quickest Veo output, ideal for drafts and iteration | ⚑⚑ Fastest | | **Google Veo 2** | Reliable, proven video generation | Solid quality for everyday video tasks | ⚑ Fast | | **Kling v1.6 Standard** | Creative and stylized video clips | Strong artistic control, great for social content | ⚑ Fast | | **Kling v1.6 Pro** | Higher quality Kling output | More detail and smoother motion than Standard | 🐒 Thorough | | **Kling v2.0** | Latest Kling generation, best quality | Most advanced Kling model, excellent motion realism | 🐒 Thorough | | **MiniMax Video-01** | Creative storytelling and animated content | Unique visual style, great for narrative-driven clips | ⚑ Fast | {% hint style="info" %} πŸ’‘ Quick Guide: β†’ Best overall quality? Use Sora 2 Pro or Google Veo 3.1.\ β†’ Need audio in your video? Use Google Veo 3.1 or OpenAI Sora 2 (synced audio).\ β†’ Want to animate an existing image? Use Google Veo 3.1 with a reference image.\ β†’ Creating social media content? Try Kling v1.6 Pro or MiniMax Video-01.\ β†’ Just testing or iterating? Use Google Veo 3 Fast to save credits. {% endhint %} ### Understanding the Settings Settings vary slightly between models but here is what you will commonly find across the video generator: | Settings | What it does | | -------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------- | | **Prompt** | Describe the video you want. Include subject, action, style, mood, camera movement and lighting for best results. | | **Duration** | The length of the video clip in seconds. Longer duration = more credits. | | **Aspect Ratio** | The shape of your video. Use 16:9 for landscape (YouTube, presentations), 9:16 for portrait (TikTok, Reels, Shorts), 1:1 for square (social media). | | **Input Image** | Upload a starting image for the AI to animate from. Ideal formats are 16:9 (1280Γ—720) or 9:16 (720Γ—1280) depending on your aspect ratio. | | **Last Frame** | Upload an ending image. The AI creates a smooth transition between your first and last frame. Available on select models. | | **Reference Images** | Upload 1–3 images for subject-consistent generation (also called R2V β€” Reference to Video). The AI keeps your subject consistent throughout the clip. | | **Input Reference** | An optional image or video to guide the overall style and direction of the generation. | {% hint style="info" %} ⚠️ Note: Reference Images only work with 16:9 aspect ratio and 8-second duration on some models. If Last Frame is provided alongside Reference Images, the Last Frame will be ignored. {% endhint %} ### Writing a Great Video Prompt Video prompts work best when you describe the scene like a film director. Think about: β†’ Subject - Who or what is in the video?\ β†’ Action - What is happening?\ β†’ Camera - Is the camera moving? Zooming in? Panning?\ β†’ Style - Cinematic, documentary, animated, lo-fi?\ β†’ Mood - Dramatic, calm, energetic, mysterious?\ β†’ Lighting - Golden hour, studio lighting, neon lights? | ❌ Weak Prompt | βœ… Strong Prompt | | ------------------ | ------------------------------------------------------------------------------------------------------------------------------------------------- | | "A person walking" | "A confident woman walking through a busy Tokyo street at night, neon reflections on wet pavement, cinematic slow motion, shallow depth of field" | | "A product video" | "A sleek black smartwatch rotating slowly on a white surface, soft studio lighting, close-up macro shot, premium product advertisement style" | | "A nature scene" | "A drone shot slowly rising above a misty mountain forest at sunrise, golden hour light breaking through the trees, cinematic 4K quality" | ### Pricing Each video model has a different credit cost depending on the model, duration, and quality settings you choose. You can see the exact credit cost and estimated number of runs at the bottom of each model's settings panel before you hit Generate Video. {% hint style="info" %} πŸ’‘ Credit Tip: Use Google Veo 3 Fast to test your prompt and get the motion and composition right first. Once you are happy with the direction, switch to Sora 2 Pro or Google Veo 3.1 for the final high-quality render. This saves significant credits during iteration. {% endhint %} {% hint style="info" %} βœ… Try This Now: Select Google Veo 3 Fast and type: "A slow motion close-up of coffee being poured into a white cup, steam rising, warm golden lighting, cinematic style." Hit Generate Video and see what i10x.ai creates in minutes. {% endhint %} # Discover Browse a curated library of specialized AI agents built for specific tasks. Find the right agent for your job and start using it instantly - no setup required. Not every task needs a blank chat window. Sometimes you need an AI that is already an expert in exactly what you are trying to do. Discover gives you access to 500+ specialized AI agents - each one purpose-built for a specific job. From writing SEO headlines to removing image backgrounds, from planning marketing campaigns to generating travel photos - there is an agent for almost everything. Just find it, click "Use AI Agent", and start working. {% hint style="info" %} πŸ’‘ Think of Discover as your AI app store. Instead of building the perfect prompt from scratch every time, just pick the agent that already knows how to do the job. {% endhint %} ### How to Use Discover 1. Click "Discover" in the left sidebar of your i10x dashboard. 2. Browse by category or use the search bar to find a specific agent. 3. Click on any agent card to read a description of what it does. 4. Click "Use AI Agent" or "Use Model" to open it. 5. Type your request in the chat bar - the agent already knows its job. 6. Get your result instantly. ### Agent Categories Agents are organized into categories so you can quickly find what you need: | Category | What You'll Find | | ------------------------------ | ------------------------------------------------------------------------------------------------------------------------- | | **LLMs** | Direct access to raw AI models like GPT-5, GPT-4o, Gemini, and more - use them without any preset instructions | | **Image Editing & Generation** | Agents for generating images, removing backgrounds, changing backgrounds, removing watermarks, and more | | **Marketing & SEO** | Headline generators, CTA writers, meta description crafters, content cluster planners, landing page copywriters, and more | | **Video** | Specialized agents for video-related tasks and generation | | **Business** | Agents for business strategy, planning, proposals, and operations | | **Documents** | Agents for summarizing, rewriting, editing, and analyzing documents | | **Wellness** | Agents focused on health, mindfulness, and personal wellbeing | | **Education** | Agents for learning, tutoring, research assistance, and academic tasks | | **Creativity & Fun** | Creative writing, storytelling, brainstorming, and entertainment agents | ### Finding the Right Agent With 500+ agents available, the fastest ways to find what you need are: * Use the Search Bar at the top - type what you want to do (e.g. "headline", "background remover", "SEO"). * Browse by Category - click any category tab at the top to filter agents by topic. * Sort by Relevance - use the sort dropdown to find the most popular or highest-rated agents. * Look at the ratings and usage count on each card to find the most trusted agents. ### Agent vs. Chat - What's the Difference? Both Chat and Discover agents use the same underlying AI models - but they work differently. | | Chat | Discover Agent | | ------------------- | --------------------------------------------- | ------------------------------------------------------- | | **Setup** | Blank canvas - you control everything | Pre-configured - the agent already has its instructions | | **Best for** | Open-ended tasks, back-and-forth conversation | Specific, repeatable tasks where you know what you need | | **Prompt required** | Yes - you write the full prompt | Minimal - just describe your specific request | | **Examples** | "Help me think through my business strategy" | "AI Marketing Strategy Designer", "Headline Generator" | ### Popular Agents to Try First Not sure where to start? Here are some of the most-used agents across different categories: | Agent | Category | What It Does | | ---------------------------------- | --------------- | ----------------------------------------------------------------- | | **AI Marketing Strategy Designer** | Marketing & SEO | Design full marketing strategies aligned to your goals and budget | | **Headline Generator** | Marketing & SEO | Generate 5 bold, click-worthy headlines for any topic | | **Meta Description Crafter** | Marketing & SEO | Create 3 concise, SEO-optimized meta descriptions instantly | | **Content Cluster Planner** | Marketing & SEO | Build a content strategy with 1 pillar article and 5 subtopics | | **AI Background Remover** | Image Editing | Remove the background from any photo instantly | | **AI Background Changer** | Image Editing | Replace the background of any photo with a new scene | | **AI Watermark Remover** | Image Editing | Clean up images by removing unwanted watermarks or logos | | **AI Travel Photo Generator** | Image Editing | Turn an ordinary photo into a stunning travel shot | | **Landing Page Copywriter** | Marketing & SEO | Write persuasive, conversion-focused landing page copy | | **AI Copy Editor** | Marketing & SEO | Polish and refine your marketing copy for SEO and readability | {% hint style="info" %} βœ… Try This Now: 1. Go to Discover and click the "Marketing & SEO" category. 2. Find the "Headline Generator" agent and click "Use AI Agent." 3. Type: "Generate 5 headlines for a blog post about AI productivity tools for founders." You just skipped writing a prompt from scratch - the agent already knows what to do. {% endhint %} # Agent Builder Build custom AI agents and embeddable chatbots tailored to your exact needs. No coding required. The Agent Builder is where i10x.ai goes from a tool you use to a tool that works for you. Build a private AI agent with a custom personality and instructions for your own daily workflow. Or create a chatbot powered by your own content and embed it directly on your website - in minutes. No coding. No technical setup. Just define what you want your AI to do, and it's ready. {% hint style="info" %} πŸ’‘ Not sure which one to build? β†’ Build an Agent if you want a private AI assistant for your own use inside i10x.\ β†’ Build a Chatbot if you want to embed an AI assistant on your website or share it with others. {% endhint %} ### Agent vs. Chatbot - What's the Difference? | | Create an Agent | Create a Chatbot | | -------------- | -------------------------------------------------------- | ------------------------------------------------------- | | **Purpose** | A private AI assistant for your own use | A public-facing AI assistant for your website or users | | **Access** | Only you - visible under "View Agents" in your dashboard | Anyone you share it with via link or embed | | **Deployment** | Stays inside i10x.ai | Embeds on any website via Script, iFrame, or Public URL | | **Best for** | Personal productivity, custom workflows | Customer support, lead generation, onboarding bots | {% hint style="info" %} βœ… Ready to build? β†’ Use the sidebar to go to "Create an Agent" or "Create a Chatbot" and follow the step-by-step guide. {% endhint %} # Create an Agent Build a custom AI agent powered by any of our models. Define its personality, give it instructions, and use it privately inside your i10x dashboard. An Agent is a personalised AI assistant that you build once and use whenever you need it. Give it a name, choose its model, write its instructions, and it is ready to go - available privately under your own account. Think of it as hiring a specialist that is always available, always consistent, and never forgets its instructions. {% hint style="info" %} πŸ’‘ Your agents are private by default. Only you can see and use them. They will appear under "View Agents" in your i10x dashboard. {% endhint %} ### How to Create an Agent 1. Click "Agent Builder" in the left sidebar of your i10x dashboard. 2. Click "Create Agent." 3. Fill in the agent details (see the settings guide below). 4. Click "Publish Agent" when you are ready. 5. Your agent is now available under "View Agents" in your dashboard. ### Agent Settings Explained | Settings | What It Does | Tipps | | --------------------- | ------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------- | | **LLM** | The AI model that powers your agent | Choose based on the agent's job. Use GPT-5 for complex reasoning, Claude 4.6 Sonnet for writing and tone, GPT-5 Mini for fast simple tasks. | | **Category** | The topic area your agent belongs to | Helps you organise your agents when you have multiple. | | **Agent Name** | The name of your agent | Be specific - e.g. "LinkedIn Post Writer" or "Research Summarizer" is better than "My Agent." | | **Short Description** | A brief explanation of what your agent does | Write this for yourself - it appears in your agent list so you can quickly identify it. | | **Custom Prompt** | The instructions that define your agent's behaviour, tone, and role | This is the most important field. See the guide below for how to write a great system prompt. | | **Agent Image** | A visual icon for your agent | Upload a JPG or PNG up to 5MB. | ### Writing a Great Custom Prompt The Custom Prompt is the brain of your agent. It defines how the agent behaves, what it focuses on, and how it responds. The better your prompt, the more useful your agent. A great custom prompt includes: β†’ Role - Tell the agent who it is.\ β†’ Task - Tell the agent what it does.\ β†’ Tone - Tell the agent how it communicates.\ β†’ Rules - Tell the agent what to always or never do.\ β†’ Format - Tell the agent how to structure its responses. | ❌ Weak Prompt | βœ… Strong Prompt | | ------------------------------ | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | "You are a helpful assistant." | "You are an expert LinkedIn content strategist. Your job is to help founders write engaging, professional LinkedIn posts. Always write in first person, keep posts under 200 words, use short paragraphs, and end with a thought-provoking question." | | "Help me with emails." | "You are an executive assistant specialising in professional email writing. When given a topic or situation, write a clear, concise, and polite email. Always include a subject line. Keep emails under 150 words unless asked otherwise." | | "You know about marketing." | "You are a performance marketing expert with deep knowledge of Meta Ads, Google Ads, and SEO. When asked a question, give a direct, actionable answer with specific recommendations. Always back your advice with reasoning." | {% hint style="info" %} πŸ’‘ Pro Tip: Start your custom prompt with "You are a \[role]..." and then describe the task, tone, and any rules. The more specific you are, the more consistent and useful your agent will be. {% endhint %} ### Agent Ideas to Get You Started | Agent Name | LLM | What It Does | | ------------------------------ | ----------------- | --------------------------------------------------------------- | | **LinkedIn Post Writer** | Claude 4.6 Sonnet | Writes engaging LinkedIn posts in your tone of voice | | **Research Summarizer** | GPT-5 | Summarizes long articles and reports into concise bullet points | | **Email Reply Assistant** | GPT-5 Mini | Drafts professional email replies in seconds | | **Meeting Notes Formatter** | Claude Haiku 4.5 | Turns raw meeting notes into structured action item lists | | **SEO Blog Outliner** | GPT-5 | Creates detailed blog post outlines optimized for SEO | | **Customer Objection Handler** | Claude 4.6 Sonnet | Generates persuasive responses to common sales objections | {% hint style="info" %} βœ… Try This Now: 1. Click "Create Agent." 2. Select GPT-5 Mini as the LLM. 3. Name it: "Email Reply Assistant." 4. In the Custom Prompt, type: "You are a professional email assistant. When given context about an email I received, write a clear, polite, and concise reply under 100 words. Always include a subject line." 5. Click "Publish Agent." You now have a personal email assistant available in your dashboard anytime. {% endhint %} # Create a Chatbot Build a custom AI chatbot powered by your own content and embed it anywhere on your website - in minutes, with no coding required. A Chatbot is an AI assistant you build inside i10x.ai and deploy anywhere - your website, your help centre, your landing page. Your visitors can ask it questions, get instant answers, and interact with your brand 24/7. You control what it knows, how it responds, and what it looks like. {% hint style="info" %} πŸ’‘ Unlike Agents (which are private), Chatbots are designed to be shared. Embed them on your website or share the public URL with anyone. {% endhint %} ### How to Create a Chatbot 1. Click "Agent Builder" in the left sidebar and select "Create Chatbot." 2. Fill in the chatbot details (see settings guide below). 3. Click "Save Chatbot." 4. Your chatbot appears in "My Chatbots" with a "Ready" status. 5. Click "Integrate" to get your embed code and deploy it. ### Chatbot Settings Explained | Settings | What It Does | Tips | | ---------------------- | --------------------------------------------------------------------------------------------- | ----------------------------------------------------------------------------------------------------------- | | **LLM** | The AI model that powers your chatbot | GPT-4o Mini is a great default - fast, reliable, and cost-efficient for conversational tasks. | | **Name** | The display name of your chatbot | Use something recognizable to your visitors - e.g. "Support Bot" or "Ask \[Your Brand]." | | **Description** | A brief explanation of what your chatbot does and who it's for | E.g. "Answers customer questions about products, orders, and support." | | **System Prompt** | The internal instructions that define your chatbot's role, tone, and behaviour | This is the most important field. It defines everything about how your bot responds. | | **Knowledge Base URL** | A public webpage (e.g. your help centre or docs) for the chatbot to use as a knowledge source | Add your website, docs, or FAQ page so the bot answers from your actual content. You can add multiple URLs. | | **Chatbot Image** | An icon or avatar for your chatbot | Upload a JPG or PNG up to 5MB. | ### Deploying Your Chatbot Once your chatbot is saved and showing "Ready" status, click "Integrate" to access three deployment options:
πŸ“œ Script (Floating Widget) Adds a floating chat bubble to your website β€” the most common way to deploy a chatbot. 1. Choose your widget position: Bottom Right, Bottom Left, Top Right, or Top Left. 2. Copy the script tag. 3. Paste it into the or before the tag of your website's HTML. 4. The chat widget will appear instantly on your site. Best for: Adding a support or sales chatbot to any website.
πŸ”— Public URL A direct link that opens your chatbot in a new browser tab. Copy the URL and share it anywhere - in an email, a social media post, a QR code, or a button on your website. Best for: Sharing your chatbot without embedding it, or testing it before deployment.
πŸ–ΌοΈ iFrame Code Embeds the chatbot directly inside a specific section of your webpage - not as a floating widget, but as a fixed element within your page layout. Copy the iFrame code and paste it into any HTML block on your website where you want the chatbot to appear. Best for: Embedding a chatbot inside a dedicated support page, a product page, or a landing page section.
### Chatbot Ideas to Get You Started | Chatbot Name | System Prompt Focus | Knowledge Base URL | | ------------------------ | ----------------------------------------------------------------------------------------- | -------------------------------------- | | **Customer Support Bot** | Answer questions about products, orders, delivery and returns politely and clearly | Your help centre or FAQ page | | **Lead Generation Bot** | Qualify website visitors by asking about their needs and collecting their contact details | Your product or services page | | **Onboarding Bot** | Guide new users through getting started with your product step by step | Your documentation or onboarding guide | | **Sales Assistant** | Answer questions about pricing, features and comparisons to help visitors make a decision | Your pricing and features page | | **Knowledge Base Bot** | Answer internal team questions based on company documentation | Your internal wiki or Notion page | {% hint style="info" %} βœ… Try This Now: 1. Click "Create Chatbot." 2. Select GPT-4o Mini as the LLM. 3. Name it: "Support Bot." 4. In the System Prompt, type: "You are a helpful and friendly customer support assistant. Answer questions clearly and politely. If you don't know the answer, say so and suggest the user contacts the support team." 5. Add your website URL as the Knowledge Base URL. 6. Click "Save Chatbot" β†’ then "Integrate" β†’ copy the Script and paste it on your website. Your AI-powered support chatbot is now live. {% endhint %} # Automations Connect your tools, automate repetitive tasks, and let AI do the heavy lifting - no coding required. Automations let you connect your favourite tools and build powerful\ workflows - without writing a single line of code. Set it up once, and it runs on autopilot: moving data, sending messages,\ generating content, and taking action across your apps - 24/7. ### What Makes i10x Automations Different? | Feature | What It Means | | ------------------------- | ----------------------------------------------------------------------------------------- | | **i10x AI Core built in** | All LLMs you already use on i10x are available inside every workflow - no API keys needed | | **Pre-built templates** | Activate powerful workflows in minutes - no building from scratch | | **100+ app integrations** | Connect Gmail, Slack, Notion, HubSpot, Google Sheets and more | | **We build it for you** | Request a custom workflow - free or paid depending on complexity | ### Three Ways to Get Started | Option | Best For | | ---------------------- | --------------------------------------------------- | | **Build your own** | You know what you want and want full control | | **Use a template** | You want to get started fast with a proven workflow | | **Request a workflow** | You want us to build it for you | # The Workflow Builder Learn how the drag-and-drop canvas works and how to build your first workflow from scratch - step by step. The workflow builder is a drag-and-drop canvas where you design automations\ by connecting components together. Each component does one job - trigger an\ event, take an action, process data, or make a decision. No code. No complexity. Just logic. ### The Canvas When you open a new workflow, you land on a blank canvas. The left sidebar\ shows all available components. The right panel (Inspector) lets you\ configure whichever component you have selected. Think of the canvas as your whiteboard - you drag components onto it and\ draw connections between them to define the flow of data. {% hint style="info" %} πŸ’‘ To start a new workflow, go to Automations β†’ click "New Flow" in the\ top right corner. {% endhint %} ### Your Building Blocks All components are organised into four categories in the left sidebar. ### AI | Component | What It Does | | ----------------------- | -------------------------------------------------------------- | | **i10x AI Core Module** | Access all i10x LLMs inside any workflow. No API key required. | | **Agent Tools** | Extend AI agents with tools like web search or data lookup. | ### MCP Servers Connect to MCP-compatible services like Google Maps, Perplexity, and\ custom HTTP endpoints for advanced integrations. ### Utilities | Component | What It Does | | -------------- | ---------------------------------------------- | | **Controls** | Add if/else logic, branching and loops | | **Filters** | Only pass data that meets your conditions | | **Converters** | Transform data between formats | | **HTTP** | Call any external API | | **Storage** | Store and retrieve values across workflow runs | | **Forms** | Trigger a workflow from a form submission | | **Email** | Send emails directly from a workflow | | **RSS** | Monitor any RSS feed for new content | | **Subflows** | Reuse workflows inside other workflows | ### Applications | Category | Apps | | -------------------- | ---------------------------------------------------------------------- | | **Productivity** | Notion, Airtable, Google Sheets, Google Docs, ClickUp, Asana, Evernote | | **Communication** | Slack, Discord, Gmail | | **CRM & Sales** | HubSpot, Salesforce | | **Social & Content** | Facebook, Facebook Business, Canva | | **Dev & Data** | GitHub, Amazon S3, Google BigQuery, HTTP | | **E-commerce** | BigCommerce, Stripe, Shopify | | **AI & Voice** | ElevenLabs, OpenAI, Google Gemini | | **Files & Storage** | Dropbox, Google Drive, Amazon S3 | | **Scheduling** | Calendly, Google Calendar | ### How to Build a Workflow - Step by Step Here's how to build a workflow from scratch. We'll use a real example:\ "Every morning, get today's top AI news and send a summary to Slack." #### Step 1 - Add a Trigger Every workflow starts with a trigger - the event that kicks everything off.\ Search for a trigger component in the left sidebar and drag it onto the canvas. Common triggers: β€’ Scheduler - runs the workflow at a set time or interval (e.g. every day at 8am)\ β€’ Webhook - fires when an external service sends data to a URL\ β€’ RSS - fires when a new item appears in an RSS feed\ β€’ App trigger - fires when something happens in a connected app\ (e.g. new row in Google Sheets, new email in Gmail) {% hint style="info" %} πŸ’‘ For our example: drag a Scheduler component onto the canvas.\ In the Inspector, set it to run every day at 08:00. {% endhint %} #### Step 2 - Add an Action Now drag the next component onto the canvas - the thing you want to happen\ after the trigger fires. Hover over the output port (the dot on the right side of a component)\ and drag a line to the input port of the next component to connect them. {% hint style="info" %} πŸ’‘ For our example: add an RSS component and connect it to the Scheduler. In the Inspector, paste the RSS feed URL for your news source. The RSS component will output the latest articles each time it runs. {% endhint %} #### Step 3 - Add AI Drop the i10x AI Core Module onto the canvas and connect it to the previous\ component. In the Inspector, write your prompt - and use variables from the\ previous step to pass real data into it. Variables let you reference the output of any earlier component.\ Click the variable picker inside any input field to browse available data. {% hint style="info" %} πŸ’‘ For our example: connect the RSS output to i10x AI Core. In the prompt field, type something like: "Summarise the following news articles in 5 bullet points.\ Focus on practical implications for AI professionals: {{rss.title}} – {{rss.description}}" {% endhint %} #### Step 4 - Deliver the Output Add your final action - where the result should go. Connect it to the AI\ component and map the AI's output into the message field. {% hint style="info" %} πŸ’‘ For our example: drag a Slack component onto the canvas. Connect it to the AI Core output. In the Inspector, select your Slack account, choose a channel, and in the Message field select the AI output variable. {% endhint %} #### Step 5 - Test and Start Before going live, test your workflow to make sure everything works correctly. 1. Click "View Logs" at the bottom of the canvas to monitor activity 2. Click "Start Flow" in the top right corner to activate it 3. Your workflow is now live and will run automatically {% hint style="info" %} βœ… Try This Now: 1. Go to Automations β†’ New Flow 2. Drag a Scheduler onto the canvas - set it to run daily at 09:00 3. Add the i10x AI Core Module - connect it to the Scheduler 4. In the prompt, type: "Write me a motivational one-liner to start my workday" 5. Add an Email component - connect it to the AI Core 6. Enter your email address in the To field and map the AI output as the body 7. Click "Start Flow" - your daily AI email starts tomorrow morning {% endhint %} ### Workflow Ideas to Inspire You | Workflow Name | Trigger | What It Does | | ---------------------- | ------------------------ | --------------------------------------------------------------------- | | **Daily News Digest** | Scheduler (8am) | Fetches RSS news, summarises with AI, sends to email or Slack | | **Lead Enrichment** | New row in Google Sheets | Takes a company name, researches it with AI, fills in the sheet | | **Ticket Analyser** | Scheduler (daily) | Pulls support tickets, classifies pain points with AI, logs to Sheets | | **Social Monitoring** | RSS / HTTP | Monitors brand mentions, analyses sentiment, alerts via Slack | | **Content Repurposer** | Form submission | Takes a blog URL, rewrites it as LinkedIn post + tweet thread | | **Meeting Prep Brief** | Scheduler (1h before) | Pulls calendar event, researches attendees with AI, sends a briefing | # Templates Skip the setup. Browse ready-made workflows, fill in a few details, and go live in minutes. Templates are pre-built workflows, ready to activate. Instead of building\ from scratch, you pick a template, fill in a few details, connect your apps,\ and you're live in minutes. ### How to Activate a Template 1. Go to Automations in the left sidebar 2. Click Templates 3. Browse by category or use the search bar 4. Click a template to preview what it does 5. Fill in the required fields (e.g. email address, keyword, time) 6. Connect any required apps 7. Click "Start Template" {% hint style="info" %} ⚠️ Each template clearly shows what inputs it needs and which apps it connects to - before you activate anything. {% endhint %} ### Template Spotlight: Brand Reputation Analysis AI-powered daily brand reputation reports delivered straight to your inbox. This workflow monitors any brand, company, or product name in Google search\ results every day - analyses everything with AI - and sends you a clean,\ professional report. #### The Report Includes: β€’ Executive Summary & Overall Sentiment\ β€’ Media Coverage & News Highlights\ β€’ Community Discussions & Reviews\ β€’ Search Intent Trends\ β€’ Risk Alerts\ β€’ Recommended Action Items #### What You Need to Fill In: | Field | Example | | ------------------------- | ----------------- | | **Brand Name to Monitor** | Tesla | | **Your Email Address** | | | **Delivery Time** | 09:00 | {% hint style="info" %} βœ… Try This Now: 1. Go to Automations β†’ Templates 2. Open "Brand Reputation Analysis" 3. Enter your company name in the Brand Name field 4. Add your email address 5. Set a delivery time (e.g. 09:00) 6. Click "Start Template" - your first report arrives tomorrow morning {% endhint %} # Request a Custom Workflow Tell us what you want to automate and we'll build it for you - free or paid depending on complexity. Don't have the time or confidence to build a workflow yourself?\ Just request it - and we'll build it for you. Whether it's a simple 3-step automation or a complex multi-app workflow\ powered by AI, we've got you covered. ### How to Submit a Request 1. Go to Automations in the left sidebar 2. Click "Request a Workflow" 3. Describe what you want to automate - the more detail, the better 4. Our team reviews your request 5. We build it and deliver it directly to your account ### Pricing | Complexity | Example | Price | | ----------- | --------------------------------- | ----- | | **Simple** | 3-5 steps, one app, basic logic | Free | | **Medium** | Multi-step, conditions, 2-3 apps | Paid | | **Complex** | AI + multiple apps + custom logic | Paid | {% hint style="info" %} πŸ’‘ Not sure which tier your request falls into? Submit it anyway - we'll let you know before we start. {% endhint %} ### Tips for a Great Request The more detail you give us, the faster we can build it. Here's what to include: * Trigger: What should start the workflow?\ (e.g. "every morning at 8am" or "when a new row is added to Google Sheets") * Outcome: What should happen at the end?\ (e.g. "send a summary to my Slack channel") * Apps: Which tools do you want to connect? * AI: Should AI summarise, classify, or generate content along the way? {% hint style="info" %} βœ… Example Request: "Every morning at 9am, pull the last 24 hours of mentions of my brand from Google, summarise them with AI, and send a bullet-point digest to my Slack channel #brand-alerts." {% endhint %} # Prompt Library A curated collection of ready-to-use prompts for i10X. Copy, paste, customize. ### Time Freeze Cinematic Street Snap A cinematic ultra-realistic live-action prompt for generating a 10-second time-freeze street scene where a character snaps to freeze a busy city around her, walks through the frozen crowd, smokes, and then restores time with a second shockwave.
``` Prompt: Use the provided image as the main character reference. Keep face, outfit, and body proportions identical in every shot. 15s cinematic time-freeze short film, ultra-realistic live-action. Shot on Arri Alexa Mini, 50mm, natural daylight, hard shadows, shallow DOF, subtle film grain. [0:00–0:03] Busy city sidewalk, time normal. Steadycam frontal medium shot tracking as the character walks confidently through a crowd. People walk, check phones, chat. Bright sunny sky; pigeons fly in the distance. He raises his right hand and snaps. [0:03–0:06] On the snap: a powerful white spherical shockwave bursts from his fingertips. Visible air distortion + light refraction, rapidly expanding. It sweeps the ground, lifting dust/leaves and freezing them mid-air. Pedestrians freeze mid-step. In the sky, pigeons freeze mid-flight in varied wing poses. The wave washes over distant buildings with rippling light distortions. After it dissipates: absolute silence. Time-frozen particles shimmer in sunlight. [0:06–0:09] Only his footsteps echo. Camera moves backward in front of him as he strolls through the frozen crowd, satisfied. He notices a pigeon suspended above, reaches up, gently touches its feathers. Pigeon stays perfectly still like a sculpture, yet emits a low coo that echoes. He keeps walking. [0:09–0:15] He stops, hands in pockets. Turns, pulls a cigarette from his jacket, puts it in his mouth. Flicks a lighter (click), lights it, takes a drag, slowly exhales. The smoke is the only moving thing in the frozen world. He faces camera with a confident smile and snaps again: stronger reverse shockwave (air distortion + refraction) restores motion instantlyβ€”people resume walking, pigeons scatter, city noise returns. He turns and walks away. Camera rises/pulls back to wide overhead as he blends into the city. Fade to black. Sound: city ambience β†’ snap + deep LF shockwave β†’ silence β†’ echoing footsteps β†’ pigeon coo β†’ lighter click β†’ inhale/exhale β†’ second snap + stronger reverse shockwave β†’ city ambience returns. ``` ### GPT Prompt Codes 100 Smart prompt codes to change the way AI responds to you. \ Download these codes to upgrade your ChatGPT prompts, prompt engineering, AI writing, and GPT productivity immediately.
{% file src="/files/VaEycmuUo02v5MYoh6rO" %}
### Photo Quality Enhancer This prompt turns any regular photo into a professional photographer's shot.\ Got a photo with a great expression, but the quality just isn't there? Flat lighting, weird-looking skin, a distracting background? This prompt fixes all of it, without changing your face.
How to do it: 1. Open GPT-Image-2 2. Upload your photo to the chat 3. Copy the full prompt below, paste it and send ``` ‏Ultra high-resolution 4K restoration of the original image, preserving exact composition and subject integrity. ‏Enhance fine details to maximum clarity: skin texture, fabric fibers, surface imperfections, micro-details, and environmental elements. ‏Apply advanced de-noising, remove compression artifacts, eliminate grain while retaining natural texture. Restore damaged or aged areas with realistic reconstruction (scratches, fading, blur, motion artifacts). ‏Improve sharpness with natural edge definition (no over-sharpening halos). Correct color fading with accurate color grading, restore true-to-life tones and dynamic range. ‏Enhance lighting realism: balanced highlights and shadows, improved contrast without crushing blacks or blowing highlights ‏Add subtle cinematic depth: natural depth of field, realistic focus falloff, no artificial blur ‏Preserve original framing, perspective, pose, and proportions EXACTLY - no changes to composition. ‏Output should look like it was captured on a modern high-end cinema camera (ARRI Alexa / RED), hyper-realistic, clean, crisp, and film-quality. ‏NO artifacts, NO AI distortion, NO plastic skin, NO oversmoothing, NO stylization, NO change in identity. ``` ### Cinematic Superhero Dog AI Video Trend We tested **Sora vs. Imagen** so you don't have to. Here's how to turn you and your pet into apocalyptic superheroes in under 5 minutes:
``` Step 1: Prep your images Take one photo of yourself. Take one photo of your dog. That's it. Step 2: Generate your character Paste this into Nano Banana Pro for better results. PROMPT 1: Person falling backwards shocked from the sky with Dog in their arm in apocalyptical city scenario with smoke and burning buildings beneath them. Step 3: Bring it to life Take your generated image and drop it into any video AI. We tested Sora and Imagenβ€”both delivered insane results. PROMPT 2: Person with dog falling from high above down spiraling and turning mid flight and dropping on the roof top rolling back then person with dog comes to a stop and camera zooms in then person getting mad then putting head together with dog transforming into black into armored beasts as the sky darkens The result? A full cinematic transformation sequence that looks like it cost $100k to produce. Except you made it in minutes with two prompts. ``` ### AI Product Catalog Shoot Curious how pro catalogs make models look so polished? Generate your own ultra-detailed beauty portraits for product catalogs with only a couple of quick prompts.
``` Part 1: Composition + framing A hyper-realistic, high-resolution beauty portrait captured in a tightly cropped close-up. The subject is posed in a subtle three-quarter angle, leaning slightly forward and resting her sharp chin gently on the back of her hand with her fingers delicately curled underneath. Though her face is angled slightly to the side to highlight her sharp jawline, she turns to look directly at the viewer with a calm, steady intensity. The image uses a very shallow depth of field: her eyes, textured skin, and lips are in razor-sharp focus, while her resting hand, ear, and the background softly blur away. The lighting is diffused and even, perfectly illuminating her features against a neutral, out-of-focus off-white background. Part 2: Facial features + skin + lighting detail The subject’s skin is the absolute focal point, with a warm, golden-tan complexion and an intensely detailed, dewy glass skin finish. Hyper-realistic textures are preserved, including visible pores, fine vellus hair, and a natural dusting of freckles across the nose, cheeks, and forehead. Soft glowing highlights accentuate her cheekbones, chin, and nose bridge, with a subtle warm rosy blush. Her eyes are slightly almond-shaped, a hazel-green blend of blue-green and warm brown, framed by natural lashes. Her eyebrows are thick, dark, and brushed up in a feathered style. Her lips are full and pouty, painted in a vibrant opaque ruby-red, slightly parted to reveal natural white upper teeth. Part 3: Hair, styling, and outfit Her hair blends dark roots into warm dirty-blonde tones and is styled tightly against the scalp in neat cornrows. The braids gather at the nape and transition into one thick braid falling over her left shoulder. She wears a large tiered gold hoop earring on her visible left ear, framing her jawline. A delicate gold chain necklace is faintly visible. Her outfit is layered: a crisp white crew-neck t-shirt under a rich chocolate-brown ribbed top. ``` ### Baseball Stadium Video Cam Wondering how everyone are creating the viral Korean baseball clip? Now you can make your own AI generated stadium video in just few easy steps.
``` Prompt 1: Take a photo of yourself and the reference image and paste this in Gemini: a hyper-realistic, high-resolution beauty portrait captured in a tightly cropped close-up. The subject is posed in a subtle three-quarter angle, leaning slightly forward and resting her sharp chin gently on the back of her hand with her fingers delicately curled underneath. Though her face is angled slightly to the side to highlight her sharp jawline, she turns to look directly at the viewer with a calm, steady intensity. The image utilizes a very shallow depth of field: her eyes, textured skin, and lips are in razor-sharp focus, while her resting hand, ear, and the background softly blur away. The lighting is diffused and even, perfectly illuminating her features against a neutral, out-of-focus off-white background. Facial Features and Skin: The subject’s skin is the absolute focal point, boasting a warm, golden-tan complexion with an intensely detailed, dewy "glass skin" finish. Hyper-realistic textures are celebrated rather than smoothed awayβ€”visible pores, fine vellus hair (peach fuzz), and a natural dusting of freckles are scattered across her nose, cheeks, and forehead. Soft, glowing highlights accentuate her prominent cheekbones, chin, and the bridge of her nose, complemented by a subtle, warm rosy blush. Her slightly almond-shaped eyes are a captivating, multifaceted hazel-greenβ€”a distinct blend of light blue-green and warm brownβ€”framed by natural lashes. Her eyebrows are thick, dark, and styled in a distinctly brushed-up, feathered manner. Her mouth is a striking focal point: notably full and pouty lips painted in a vibrant, opaque ruby-red. Her lips are slightly parted, revealing natural white upper teeth. Hair and Styling: Her hair features dynamic color, blending dark roots into warm, dirty-blonde mid-tones and ends. It is styled tightly against her scalp at the crown, sectioned straight back from her hairline in neat, intricate cornrows. These tightly woven braids gather at the nape of her neck and transition into one thick, substantial braid that falls casually over her left shoulder. Attire and Accessories: Adorning her visible left ear is a large, thick, tiered gold hoop earring that sits prominently framing her sharp jawline. A delicate gold chain necklace is faintly visible, blurring into the out-of-focus lower left corner. Her outfit consists of heavily textured, chic layers: a crisp, bright white crew-neck t-shirt peeking out from underneath a rich chocolate-brown ribbed top. Prompt 2: Add the new image to Kling Pro Convert this image to a video in the style of a Korean baseball live broadcast audience shot.The scene starts as a candid stadium crowd shot during an evening game. The woman is sitting naturally in the audience, watching the field, not posing at first. Surrounding crowd is slightly blurred and moving naturally, yellow cheering towels waving softly, beer cups on seats, realistic stadium LED lighting, telephoto sports broadcast lens, shallow depth of field, live TV compression artifacts, slight motion blur, authentic KBO broadcast atmosphere.The camera performs a slow, smooth broadcast-style zoom in toward the woman, like a live stadium "fan cam" moment shown on the big screen during a basketball or baseball game. Keep the zoom realistic, gradual, and centered on her face and upper body, with subtle handheld broadcast camera micro-shake.She has subtle blinking, natural breathing, slight hair movement from stadium breeze, and tiny natural head movements. At first she does not notice the camera. Near the end of the clip, she realizes she is on camera, looks directly toward the camera, reacts naturally, and gives a soft genuine smile. Documentary realism, candid live sports broadcast feeling, not overly cinematic, not Al-looking.Do not alter, remove, or change any text or graphics visible in the original image. All text overlays, scoreboards, and broadcast Ul must remain exactly as they appear in the source image ``` ### Editorial Skincare Photo A minimalist, editorial-style product shot using frosted glass and natural textures.
Use this prompt to generate a high-quality, editorial-style skincare product photo using an AI image generator. Simply copy the prompt below and paste it into your preferred tool on i10X (e.g., Midjourney, DALLΒ·E, GPT Image 2.0). ``` A minimalist skincare product photograph featuring a frosted glass pump bottle of cleanser. The bottle is cylindrical with a matte, translucent finish that reveals an off-white, creamy liquid filled to about halfway. A white plastic pump top with a gently curved spout sits on the bottle, giving a clean and modern silhouette. Product label and text Subtle, small-tone-on-tone text near the top reads β€œCleanser.” Very small text below that appears to say β€œe150ml” (suggesting volume). A faint vertical brand mark or partial word (looks like an β€œe” and part of another letter) runs along the lower side of the bottle in a soft, barely-contrasting white. Setting and props The bottle sits on a textured piece of tree bark or driftwood. Pale, intricate lichen and moss cluster around and behind the bottle, creating an organic, natural frame. The bark’s rough texture contrasts with the smooth, frosted glass. Colors and tone A neutral, muted palette dominated by soft grays, off-whites, and pale beige/green from the lichen. The overall color scheme is desaturated and serene, emphasizing simplicity and calm. Lighting and mood Soft, diffused lighting with minimal shadows β€” probably from a large softbox or window light. Even illumination highlights the frosted texture of the glass and the creaminess of the product inside. The image feels airy, clean, and intentionally minimalist β€” evoking purity, natural ingredients, and gentle skincare. Composition and focus Centered composition with the bottle as the focal point. Shallow depth of field: the bottle is sharp while elements farther back softly blur, keeping attention on the product. Negative space above and to the sides gives a high-end, editorial aesthetic suitable for a skincare brand. ``` {% hint style="info" %} You can customize the product type, label text, or setting to match your brand. {% endhint %} # Pricing Everything you need to know about i10x.ai plans, credits, and what's included - so you can choose the right plan with confidence. ### Plans & Pricing i10x.ai offers a range of plans designed for individuals, professionals, and teams. Whether you're just getting started or running a full-scale operation, there's a plan built for your needs. ### How Our Pricing Works All plans are built around two types of model access: Basic Models - available with unlimited or high-volume use depending on your plan. These cover the vast majority of everyday AI tasks. Advanced Models & Features - powered by i10X Credits. Credits are consumed when using high-compute models (like reasoning and frontier AI models), image & video generation, PDF & document tools, and specialist AI Agents. ### Everyday Plans Designed for individual users who want powerful AI access at an accessible price point. | Plan | Monthly Price | Annual Price | Basic Models | Advanced Model Uses | i10X Credits | | --------- | ------------- | ------------ | -------------- | ------------------- | ------------ | | Free | US$0/mo | US$0/mo | 3 uses per day | Not supported | | | Basic | US$10/mo | US$8/mo | 5,000 uses/mo | 200 uses/mo | 2,500/mo | | Unlimited | US$25/mo | US$17.50/mo | Unlimited | Unlimited\* | 7,500/mo | {% hint style="info" %} \* "Unlimited use of advanced models" refers to models such as ChatGPT 5.4/5.2/o3, Gemini 3.1/3/2.5, Grok 4.1 Fast/4/Vision, Claude 4.6 Sonnet, and Perplexity. These models draw from your monthly i10X Credits for high-compute tasks. See the section below for a full explanation. {% endhint %} ### Teams & Power User Plans Built for teams and power users who need higher credit volumes, shared workspaces, and access to all 500+ specialist AI Agents. All plans support multiple seats - simply select the number of seats your team needs at checkout. | Plan | Monthly Price | Annual Price | Seats | i10X Credits | | ----------- | ------------- | ------------ | ------ | ------------ | | Starter | US$40/mo | US$34/mo | From 2 | 15,000/mo | | Power Plus | US$80/mo | US$68/mo | From 2 | 40,000/mo | | Power Scale | US$100/mo | US$85/mo | From 2 | 60,000/mo | {% hint style="info" %} πŸ’‘ All Teams & Power User plans include unlimited use of both basic and advanced models, with i10X Credits allocated for high-compute features. The price shown is per billing cycle - additional seats can be added at checkout. {% endhint %} ### What Are i10X Credits? i10X Credits are used for features and models that require significantly more compute power. Rather than charging per use, we bundle a generous monthly credit allocation into every paid plan so you can plan and budget with confidence. ### How Far Do Credits Go? The number of credits consumed per run depends on the model or feature used. As a general benchmark, based on our Fair Use Policy: | Plan | Monthly Credits | | ----------- | --------------- | | Basic | 2,500 | | Unlimited | 7,500 | | Starter | 15,000 | | Power Plus | 40,000 | | Power Scale | 60,000 | {% hint style="info" %} πŸ’‘ For most everyday tasks, basic models are unlimited and require no credits at all. Credits are best reserved for complex reasoning, media generation, and document-heavy workflows. {% endhint %} ### What Happens If I Run Out of Credits? If you exhaust your monthly credits before your cycle resets, you will no longer be able to access credit-based models and features until your credits renew. Basic models remain fully accessible at all times. You have two options if you need more credits mid-cycle: 1. Purchase additional i10X Credits - top up your account without changing your plan. Contact our support team or visit your account settings for top-up options. 2. Upgrade your plan - move to a higher-tier plan to increase your monthly credit allocation going forward. ### Money-Back Guarantee We offer a 7-day money-back guarantee on all new subscriptions so you can try i10x.ai completely risk-free. #### Eligibility for a Full Refund To qualify for a full refund, both of the following must be true: 1. You request the refund in writing to within seven (7) calendar days of your initial purchase. 2. Your usage during these 7 days does not exceed the Normal 7-Day Usage Threshold (defined below). These thresholds are designed to allow genuine testing while preventing abuse. Exceeding them will disqualify you from a full refund. #### Normal 7-Day Usage Threshold The following limits apply during the 7-day window: | Limit | Basic Plan | Unlimited Plan | | ------------------- | ----------------------- | ---------------- | | i10X Credits used | Max 750 | Max 750 | | Basic Model uses | Max 1,000 (of 5,000/mo) | Reasonable use\* | | Advanced Model uses | Max 40 (of 200/mo) | Reasonable use\* | {% hint style="info" %} * For the Unlimited Plan, we review for extreme usage patterns that clearly indicate full-month consumption within the 7-day window. {% endhint %} If your usage exceeds these limits, we may - at our sole discretion - issue a partial refund pro-rated for time and usage consumed, or decline the refund entirely. #### Refund Process * Approved refunds are processed back to the original payment method within 10 business days. * After the 7-day period, all subscriptions are non-refundable. * You can cancel your subscription at any time from your account dashboard. Cancellation after 7 days does not entitle you to a refund for the current billing period. #### Anti-Abuse Policy Creating multiple accounts - using different emails, payment methods, IPs, or devices - to repeatedly subscribe, consume credits, and request refunds is strictly prohibited. We actively monitor for such patterns. Violations will result in: * Immediate denial of the refund request * Permanent suspension or termination of all related accounts * No future refunds or access to the platform {% hint style="info" %} ⚠️ This policy is in addition to any rights you may have under applicable consumer protection laws. {% endhint %} # Privacy & Data Security How i10x.ai protects your data, why we'll never use it to train AI models, and the independent certifications that back our commitment. Your data belongs to you - here's exactly how we protect it and what we'll never do with it. At i10x.ai, trust is the foundation of everything we build. When you use our platform, you're sharing your ideas, your work, and sometimes sensitive information with our AI models. We take that responsibility seriously - and we want to be completely transparent about how your data is handled. ### Your Data Is Not Used to Train AI Models i10x.ai operates a strict no-training policy. Your conversations, inputs, uploaded documents, and generated outputs are not used to train any large language model - ours or any third-party provider's. Your data exists solely to serve you in the moment it is needed. It is not stored for model improvement, not shared with AI providers for training purposes, and not leveraged in any way beyond delivering your requested results. This policy applies universally across every model available on i10x.ai - including ChatGPT, Gemini, Claude, Grok, Perplexity, and all others accessible through our platform. ### CASA Certification by Dekra Our commitment to security is independently verified. i10x.ai holds a CASA (Cloud Application Security Assessment) certification issued by Dekra - one of the world's most respected independent testing, inspection, and certification organisations operating across more than 60 countries. CASA certification confirms that our platform has been rigorously assessed against industry-recognised application security standards. It is not a self-assessment - it is third-party validation that our security controls meet the bar required to protect your data. ### SOC 2 Compliance - In Progress We are currently pursuing SOC 2 Type I and SOC 2 Type II certification - two of the most comprehensive and widely recognised security frameworks for cloud-based platforms. SOC 2 evaluates an organisation across five trust service criteria: Security, Availability, Processing Integrity, Confidentiality, and Privacy. Achieving both Type I and Type II demonstrates not only that our controls meet the required standard at a given point in time, but that they are consistently maintained and effective over the long term. We will update this page as each certification milestone is achieved. ### Have Questions About Your Data? We believe you should always feel confident about how your information is handled. If you have any questions regarding data storage, processing, retention, or security practices, our team is available to provide clarity. {% hint style="info" %} πŸ“© Contact us at - we are committed to responding to all data and privacy enquiries promptly and transparently. {% endhint %}