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.
-
Generate and implement application code from structured project documentation
— Use the constitution, feature specification, implementation plan, and task list to guide the coding agent and reduce guesswork.
-
Expanding services for postcard advertisers
— AI tools and AI agents were mentioned as possible services to offer alongside websites and marketing.
-
Add safety checks to automated workflows.
— Provide guardrails for AI-agent actions.
-
Retrieving documents, refining search queries, and synthesizing results
— Support a research assistant system through specialized coordinator and sub-agent responsibilities
-
Planning, executing, remembering, and reflecting across multi-step tasks
— Enable agents to complete meaningful tasks end to end by using tools, storing relevant context, and evaluating results
-
Local personal-computer assistance
— Run agents locally to search files and emails, manage storage, and support personal productivity.
-
Agent orchestration
— Coordinate multiple intelligent components, models, and agents working with humans or each other.
-
-
Agent monitoring
— Agents can be used to observe and evaluate other agents, although deterministic controls are still needed for critical decisions.
-
Agent execution and optimization
— AI agents can execute LLM and tool calls, undergo evaluation, and use observed data to improve or bug-fix their behavior.
-
-
Specialized workflow automation
— Smaller models can handle repeated, focused tasks and support agents that make a few tool calls in a workflow.
-
Suggest search terms and agentic use cases
— Identify potential article topics and ways to apply AI agents to daily activities, work, hobbies, or business.
-
Automated spam defense
— An AI agent replies to unsolicited outreach, asks questions, schedules calls, requests follow-ups and contracts, and wastes the sender's time in return.
-
-
Read websites and deliver useful answers without requiring a site visit.
— Compress the human research and purchasing process into an agent-generated answer.
-
Self-improvement
— Use feedback and evaluation tests to identify errors, improve accuracy, and adjust the agent's personality and verbosity.
-
Sub-agent orchestration
— Use low-cost models for deterministic subtasks while an orchestrator model handles broader, less predictable work.
-
Agent evaluation and improvement
— Evals connect agent behavior to business outcomes and provide feedback for training and iteration.
-
Vehicle inspection and repair support
— The El Mike agent acts as a mechanic's sidekick by providing inspection guidance and tips.
-
Financial services
— Agents support car-loan approval, underwriting, pricing, servicing, and personalized loan offers.
-
Customer relationship management and sales
— Agents remember customer history, develop strategies, pursue long-term goals, and sell cars and related products.
-
Execute routine steps and scripts
— The agent handles routine work while deterministic scripts perform fragile logic that should not be improvised.
-
Select whether to run a skill
— The agent uses each skill's name and description at startup to decide which skill to trigger.
-
Perform a specific job using procedural instructions
— An agent skill supplies the particular process and expertise that the model does not already know.
-
Formulate and send messages
— Allow an AI agent to communicate autonomously, including potentially sending email without human verification
-
Execute and write code
— Allow an AI agent to perform work autonomously
-
Call other services using an API
— Allow an AI agent to take autonomous actions toward a user's goal
-
Read and write to databases
— Achieve a user's goal autonomously through an AI agent
-
Agent orchestration
— Plan tasks, delegate them to parallel sub-agents and reduce latency for agent workloads.
-
Fine-tuning and customization
— Adapt an open-weight model to specific needs through parameter-efficient fine-tuning, RAG, behavioral control and agent customization.
-
Orchestrate agents for complex multi-stage work
— Dynamic workflows fan agents out across initial work, verification, summarization, and later stages to increase productive test-time compute.
-
Replacing manual data collection
— AI agents were described as collecting large amounts of data, placing it in dashboards, and preparing drafts and follow-up actions.
-
Operate a voice agent for a roofing business
— Answer customer questions, provide information about hail damage, and schedule a free roof inspection.
-
Generate large-scale outbound content
— The discussion uses AI agents producing large volumes of emails and user-generated-content videos as an example of future internet noise.
-
Manage approval workflow
— The agent sends sufficiently attractive bakery deals to William for a thumbs-up or thumbs-down before continuing negotiations.
-
Source bakeries and negotiate supplier terms
— The agent checks email, finds bakeries in specified locations, evaluates them, sends outreach, and negotiates discounts for cake orders.
-
Deploy specialized agents and personas
— Operate on behalf of users like employees through a marketplace of creator-built AI agents.
-
Build the app back end, front end, and landing page
— Create a government-contract search application with multiple agents working in parallel.
-
Generate and adapt conversational-agent instructions
— Create industry-specific prompts that make the SMS agent sound human, ask relevant questions, answer customers, and book appointments.
-
Operate as a persistent agent
— Search the web, create files, maintain conversation context, and interact with users through Telegram, Discord, or its built-in interface.
-
Create marketing copy and videos
— Explain the AI agent community and attract pre-orders through social media.
-
Analyze TikTok videos and comments
— Find repeated audience requests and identify demand for personal AI agents.
-
Manage communications
— Have a Codex-powered management agent review email, Slack, sponsorship communications and text messages and produce prioritized actions.
-
Draft and review a legal contract
— Have multiple agents inspect clauses, consult prior contracts and settle on a final agreement.
-
Create agents and channels
— Use an agent inside Buzz to configure new agents, assign models and create workspaces.
-
Coordinate multiple agents in shared channels
— Allow agents using different harnesses and models to collaborate, delegate work and exchange feedback.
-
-
Generate a knowledge base for an inbound tree-trimming business voice agent.
— Provide answers to common questions about scheduling on-site quotes for trimming or removal jobs.
-
Critique designs
— Agents can produce coherent lists of design strengths and weaknesses, although they do not reliably apply that judgment to their own code.
-
Improve code quality
— Agents can measure function complexity and test coverage, then add tests or split functions to meet quality constraints.
-
Run system simulations
— Agents can make it cheaper to explore design alternatives and what-if scenarios before committing to a system design.
-
Implement system changes
— A human can describe a desired change in the context of available system primitives, and an agent can implement it.
-
Inspect system structure
— Agents can expose module hierarchies, dependencies, allocation, and data flow so humans can review and change the system at a higher level.
-
Supervised parallel development
— Nizar describes supervising about four agents at once while reading and understanding their changes.
-
Generating code changes under validation
— Agent behavior is checked for TDD compliance, including whether proposed changes are unnecessary or over-implemented.
-
Running tests and interpreting test results
— The agent runs npm test, identifies a failed test, and proceeds from red toward green.
-
Writing and modifying software for the RPG combat code kata
— The coding agent creates tests and implementation code while following the TDD cycle.
-
Create website code from Paper designs
— Allow a brand designer to design in Paper and use agents to add animations and turn the designs into a shipped Next.js website.
-
Role-playing and text adventure simulation
— AI agents interact with other AI agents and tools inside a fictional scenario.