AI use cases
551 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.
-
Business-context retrieval
— AWS's context ontology accelerator converts databases and files into validated ontology and knowledge-graph context for agents.
-
Coding assistance
— Soul advisor, DSCode, Scopey, and related projects coordinate coding agents, isolate work, checkpoint changes, or detect scope drift.
-
Research and CRM maintenance
— CRM uses a durable research agent to process queued database rows while preventing unsupported personal inferences.
-
Code-change review
— Ratchet checks agent-produced edits for unnecessary dependencies, duplicate helpers, thin wrappers, and other patterns.
-
Procedure recording
— Skill recorder reconstructs the intent and ordered steps of a real work session for reuse as an agent skill or scheduled automation.
-
Workplace coordination and campaign production
— QM and the marketing team Eve template isolate agents, route work among specialists, and preserve shared context.
-
Generating interactive video worlds
— Lingbot World V2 generates long interactive video with causal frame generation, KV caching, and planning agents.
-
Reviewing and improving user interfaces
— The skills collection gives coding agents structured checks for visual design, accessibility, layout, details, and product writing.
-
Monitor and control coding agents
— Numbat applies local CEL rules to agent events for live alerts, forensic timelines, and supported pre-action blocking.
-
Reduce coding-agent tool context
— Ratel searches tool schemas and skill metadata and injects only the capabilities relevant to the current turn.
-
Agent framework execution
— labs-OO-Agents hands methods with ellipsis bodies to a model while retaining deterministic Python implementations for methods with real bodies.
-
Agent-session accounting
— agentacct joins Claude Code and Codex logs with tasks and test evidence to estimate tokens and cost and distinguish verified from agent-reported work.
-
Agentic reinforcement-learning environments
— AgentENV provides sandboxed, forkable environments for Kimi K3's agentic RL training.
-
Coding-agent game generation
— Claude-of-Duty uses a fleet of coding agents to generate a browser FPS and evaluates the result with screenshot tests and profiling.
-
Home automation and personal information assistance
— Renfield's agent works across Home Assistant, calendars, email, media, and documents using local context from a RAG knowledge base and long-term memory.
-
Coding-agent control and session management
— Fact adds prompt-cache stability, session compaction, crash recovery, and explicit policies around tool calls without replacing the existing coding agent or model.
-
Financial statement import and transaction analysis
— Expense Budget Tracker exposes a SQL API that an agent can use to import statements or analyze transactions.
-
Coding-agent operations
— Fractera provides browser-based coding tools, shared RAG memory, and an MCP-based design for coordinating coding agents.
-
Drafting email replies
— Agentic Inbox uses a Workers AI agent to draft replies for confirmation before sending.
-
Modifying data and model-training pipelines
— Agents increasingly improve the systems used to train future models.
-
Evaluating model-run results
— Agents assess experiment outputs and help determine subsequent changes.
-
Launching training jobs
— Agents automate the execution of model experiments.
-
Writing training and research code
— Agents increasingly implement researchers' ideas inside Poolside's Model Factory.
-
Write software end-to-end
— Have agents implement work while humans revisit and review the results.
-
Personalized agents and assistants
— Zuckerberg's proposal for a personal AI agent for everyone is discussed alongside Grokbot and other personalized AI systems.
-
Coding, research and tool calling
— Muse Glimmer is designed to support agentic workloads on a laptop.
-
Search and retrieve video content
— Use an agentic RAG pipeline to identify relevant videos and return exact moments from their timestamped transcripts.
-
Operating company functions through specialized agents
— Provide marketing, executive assistance, sales, support, scheduling, research, analytics, and other operational leverage.
-
Route users around standalone software
— Agents selected direct AI functionality instead of Canva and other standalone tools.
-
Generate advertising creative and collateral
— An agent-based internal system generated creative and served it to the SaaS community without suggesting Canva.
-
Replacing repetitive work
— AI agents are presented as a way for companies to reduce mundane repetitive work and enable humans to perform higher-value activities.
-
Video editing
— OpenEdit lets coding agents transcribe videos, design caption styles, render subtitles, and revise edits through natural-language instructions.
-
Software development workflow enforcement
— Agent Skills and Superpowers guide coding agents through specifications, planning, implementation, testing, review, and debugging.
-
Autonomous coding and research
— Prime Agent runs long, multi-step work through a persistent coding and research session with tools and child agents.
-
Software development
— Shorten the time from identifying an opportunity or problem to shipping code to users through agentic development and AI-assisted product work.
-
Build memory, retrieval, and context systems for agents.
— Help an agent determine which information to retain for a given task.
-
Implement the task list
— Use an AI coding agent to build the podcast website and update task status as work progresses.
-
Search and process web data
— Search, scrape, crawl, interact with live websites, parse PDFs and DOCX files, and return agent-ready content.
-
Automate software delivery
— Create self-healing tests, monitor logs and user feedback, coordinate coding agents, and prepare pull requests.
-
Coordinate creative production
— Plan, execute, revise, and deliver film, games, music, and social work through specialized agents.
-
Maintain semantic, episodic, and procedural memory for a local assistant
— Provide readable, local-first agent operation with controlled retrieval.
-
Maintain CRM records and schedule follow-ups
— Let an agent continue work on its schedule while limiting claims to observed evidence.
-
Run agent workloads at high density on Kubernetes
— Multiplex suspended and resumed workloads while preserving state.
-
Convert documents into Markdown
— Create consistent, clean input for developers and agents without ML models or external services.
-
Read, edit, render, and automate office documents
— Let agents work with Word, Excel, and PowerPoint files.
-
-
Share conversations, documents, code, skills, wikis, and code graphs with agents
— Provide reusable team memory while controlling ownership, versions, and visibility.
-
Run continuous workflow agents
— Automate workflows and respond to outside events.
-
Simulate thousands of agents with personalities and memory
— Rehearse possible futures and produce prediction reports.
-
Build auditable knowledge graphs and trace agent decisions
— Give agents grounded, provenance-backed, queryable context.
-
Agent safety
— Agent Safe Pipeline separates agent intent submission from policy decisions and credential use.
-
Human-agent collaboration
— Human Review packages edits and comments into a batch for an agent to process.
-
Agent execution
— DeepSeek Harness provides a plug-in-based agent harness with a local web UI.
-
Generating agent skills
— Book to Skill converts technical books and documentation into compact skills, chapter notes, glossaries, patterns, and reference rules.
-
Edit office documents and files
— GenOffice provides a shared AI panel and tool-calling agent for documents, spreadsheets, slides, and PDFs.
-
Coordinate multiple AI agents
— Omnigent lets agents collaborate, review one another, switch harnesses, and share or fork sessions.
-
Generate coding-agent plans and execute terminal coding workflows
— DeepSeek-Reasonix is a terminal coding agent, while Embabel uses dynamic planning to mix LLM calls with code.
-
Provide agents with an executable computer environment
— Cloudflare Computer lets agents access a virtual file system and run code through configurable backends.
-
Parallel coding
— Coordinate several coding agents in one repository while preventing file conflicts.
-
Break the implementation plan into ordered tasks
— Give the coding agent small, concrete units of work that can be reviewed individually.