AI use cases

2915 ways people actually use AI, compiled from the videos in this library. Each names the job and why it is worth doing, and links to the moment in the source video.

Run several AI coding agents concurrently in one repository without letting them overwrite each other's files.

ManuAGI - AutoGPT Tutorials
Build AI-powered backends and agents that stream model output, call tools, and return structured results. — Create Go services with model integrations, approvals, retries, timeouts, logging, and metrics.

ManuAGI - AutoGPT Tutorials
Capture screenshots and hand ambiguous visual differences to a coding agent. — Help judge image or UI diffs during comparison workflows.

ManuAGI - AutoGPT Tutorials
Use a built-in MCP server to provide coding agents with framework context. — Help AI coding agents work with a Webiny project.

ManuAGI - AutoGPT Tutorials
Find, rank, validate, and review security issues in code. — Assess authorized repositories, diffs, or paths and trace potential attack paths.

ManuAGI - AutoGPT Tutorials
Study extracted and officially published system prompts. — Understand how AI chatbots, coding agents, browser assistants, and injected reminders are steered.

ManuAGI - AutoGPT Tutorials
Provide an AI companion with a model, avatar, voice chat, and external integrations. — Create a self-hosted digital character that can interact through voice, chat platforms, and games.

ManuAGI - AutoGPT Tutorials
Control coding agents from a mobile app, web app, or desktop app. — Remotely manage agents that continue running on the user's local hardware.

ManuAGI - AutoGPT Tutorials
Route reverse-engineering, penetration-testing, or CTF tasks to an appropriate method. — Guide coding agents toward the right security workflow before acting.

ManuAGI - AutoGPT Tutorials
Run agent sandboxes at scale — Operate parallel agents in Firecracker micro-VMs distributed across machines.

ManuAGI - AutoGPT Tutorials
Support scientific discovery — Let a local desktop agent read files, run code, search the web, call life-science data connectors, and produce reports, tables, and figures.

ManuAGI - AutoGPT Tutorials
Monitor AI agent activity — Normalize activity from desktop, CLI, IDE, and gateway agents and evaluate it for risky behavior.

ManuAGI - AutoGPT Tutorials
Localize React applications — Translate entire components through tagged wrappers and continuous-localization tooling.

ManuAGI - AutoGPT Tutorials
Run large language models locally — Run Gemma 426B A4B on Apple Silicon by streaming model experts from SSD.

ManuAGI - AutoGPT Tutorials
Conduct finance research — Turn natural-language finance questions into runnable analysis, backtests, reports, and multi-agent research across several asset classes.

ManuAGI - AutoGPT Tutorials
Build voice agents — Chain voice detection, speech-to-text, an LLM, and text-to-speech into a modular local or hosted voice system.

ManuAGI - AutoGPT Tutorials
Run multiple coding agents in parallel — Coordinate agents such as Claude Code, Codex, and Cursor in separate git work trees.

ManuAGI - AutoGPT Tutorials
Embed agentic workflows into applications — Let Copilot handle planning, tool calls, and file edits inside an application.

ManuAGI - AutoGPT Tutorials
Improving models from agent traces — Use routing policies, world model simulations, harness optimization, and distillation to continuously improve an endpoint.

ManuAGI - AutoGPT Tutorials
Selecting tools for an AI agent context window — Expose only the handful of registered or MCP-provided tools that matter for each turn.

ManuAGI - AutoGPT Tutorials
Fine-tuning and training large language models — Support full fine-tuning, LoRA, 4-bit, 8-bit, DPO, and GRPO across model families.

ManuAGI - AutoGPT Tutorials
Building AI agents and RAG applications — Provide ready-to-run, provider-agnostic templates for multi-agent teams, voice agents, MCP agents, and memory.

ManuAGI - AutoGPT Tutorials
Providing front-end design guidance — Improve AI coding agents' interface design using commands and deterministic rules.

ManuAGI - AutoGPT Tutorials
Turning books and document sets into agent skills — Let agents answer from locally extracted frameworks, patterns, and chapter content.

ManuAGI - AutoGPT Tutorials
Researching topics across online sources — Produce a grounded cited brief based on recent engagement.

ManuAGI - AutoGPT Tutorials
Sharing and reusing AI workflows, skills, MCPs, and connected services — Use the same workflows across agents, tools, teammates, and machines.

ManuAGI - AutoGPT Tutorials
Managing context across interactions and over time — Maintain relevant information, continuity, consistency, and awareness of context

IBM Technology
Structuring and optimizing information passed to an LLM or AI agent — Produce more accurate and relevant outputs

IBM Technology
Instruction-following video generation — Improve adherence to prompts and preserve fine details such as hair, text, and small textures.

ManuAGI - AutoGPT Tutorials
Native audio generation — Generate dialogue, footsteps, and ambiance in the same pass as the video.

ManuAGI - AutoGPT Tutorials
Region-level video editing — Change one object, character detail, or frame region without affecting the rest of the video.

ManuAGI - AutoGPT Tutorials
Multi-reference scene generation — Use up to 50 images, clips, audio inputs, style boards, and prompts to keep story and brand elements consistent.

ManuAGI - AutoGPT Tutorials
Continuous AI video generation — Create up to 30-second unbroken shots while maintaining character, camera, lighting, and scene structure.

ManuAGI - AutoGPT Tutorials
Synchronized audio generation — Generate dialogue, footsteps, and ambience in the same pass as the video.

ManuAGI - AutoGPT Tutorials
Region-level video editing — Change one object, character detail, or frame region without regenerating the full video.

ManuAGI - AutoGPT Tutorials
Reference-guided video generation — Map up to 50 images, video clips, audio files, style boards, and text prompts into a scene.

ManuAGI - AutoGPT Tutorials
Continuous video generation — Create one unbroken shot lasting up to 30 seconds.

ManuAGI - AutoGPT Tutorials
Analyze Chainlink economics and CCIP — Examine the economics of Chainlink's cross-chain infrastructure and its role in bridging equities.

Ivan on Tech
Check whether new tokenized stocks launched on Hyperliquid — Verify the timing and details of a new tokenized-equities deployment.

Ivan on Tech
Analyze crypto and US stock market events from the previous 24 hours — Generate a market report covering Trump Media, Nvidia, financing partnerships, Hormuz-related concerns and Intel.

Ivan on Tech
Summarize bullish and bearish assets and current market news — Use AI to review real-time trends, market queries and macroeconomic developments.

Ivan on Tech
Assess which coins are strongest against quantum risks — Correct an earlier AI query and obtain a more relevant ranking with explanations.

Ivan on Tech
Coordinate multimodal creative workflows — Maintain consistent subjects, products, characters, and creative direction across images, video, and audio.

ManuAGI - AutoGPT Tutorials
Generate audio — Produce voiceovers, dialogue, sound effects, music direction, or audio layers for scenes.

ManuAGI - AutoGPT Tutorials
Generate and revise images — Create product images and supporting visual assets in different styles and formats.

ManuAGI - AutoGPT Tutorials
Generate cinematic video — Create clips from descriptions involving subjects, actions, camera movement, lighting, environments, and sound.

ManuAGI - AutoGPT Tutorials
Interpret creative requests and route them to generation tools — Claude interprets the request, Higgsfield runs the generation, and the result returns to the conversation.

ManuAGI - AutoGPT Tutorials
Select only the best trades for an automated trading system — The speakers suggest AI might make it possible to define and identify better trades, which is difficult with conventional MQL languages.

xChief Global
Data portal development — Advise on portal architecture and scaffold editable Next.js code for catalogs, datasets, charts, maps, schemas, and deployment.

ManuAGI - AutoGPT Tutorials
Multimodal agent development — Compose agents, tools, multi-agent teams, knowledge graphs, prompt pipelines, and image, audio, and video generation.

ManuAGI - AutoGPT Tutorials
Procedural 3D reconstruction — Rebuild objects from reference images as TypeScript procedural models using primitives, shaders, generated geometry, and staged visual checks.

ManuAGI - AutoGPT Tutorials
Web data extraction — Search, scrape, crawl, interact with, and convert websites into formats suitable for AI agents and applications.

ManuAGI - AutoGPT Tutorials
Penetration testing — Autonomously conduct reconnaissance, exploitation, and post-exploitation while validating vulnerabilities with proof-of-concept exploits.

ManuAGI - AutoGPT Tutorials
Personalized tutoring — Generate quizzes, conduct research, solve problems with multiple agents, create math animations, and produce interactive visuals from study materials.

ManuAGI - AutoGPT Tutorials
Codebase context reduction — Use structural graphs and dependency relationships to show AI assistants only the files relevant to a task or review.

ManuAGI - AutoGPT Tutorials
Coding assistance — Read and edit code, run commands, search files, fetch web pages, and choose next steps from feedback.

ManuAGI - AutoGPT Tutorials
Computer and browser use — Expand agents' ability to test software and operate in a more complete quality-assurance environment.

Y Combinator
Stress testing and code review with sub-agents — Break projects into features, test or review each feature, and direct later testing based on findings from other sessions.

Y Combinator
Building and demonstrating feature ideas — Allow agents to implement ideas and create screenshots or playable prototypes so weak ideas can be discarded before consuming human attention.

Y Combinator
Reviewing and testing pull requests — Reduce Peter's context switching by presenting fully reviewed and tested work instead of raw issues or feature ideas.

Y Combinator