AI use cases
2983 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.
-
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.
-
Iteratively refining existing code
— AI can polish or improve code, but repeated autonomous refinement can increase critical vulnerabilities without human expertise.
-
Producing plausible code quickly
— AI coding assistants can accelerate code production for appropriate tasks.
-
Auditing and improving AI-generated code
— To make applications created with AI more secure and reduce problems such as exposing backend data or unauthenticated APIs.
-
Assessing quantum resistance across major crypto protocols
— To compare Bitcoin, Ethereum, and Solana across technical simplicity, governance, upgrade friction, and responsiveness to new threats.
-
Finding lesser-known AI infrastructure companies and market opportunities
— To surface companies such as SiTime and Aeva and provide narrative context alongside chart-based trend analysis.
-
Summarizing recent AI-stock and AI-industry developments
— To identify top stories involving models, hyperscalers, newcomers, supply chains, and market trends.
-
Perform translation and resizing
— Automate repetitive design tasks and save human work.
-
Review pull requests
— Catch bugs through automated review, despite the review being described as overly pedantic.
-
Assist with software development
— Accelerate coding while retaining human review of every line for a precise, reliable design product.
-
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.
-
Convert designs into code
— Build a selected Paper design into a component in an existing codebase while following its coding styles and conventions.
-
Modify selected design frames
— Apply comments, improve alignment and contrast, reduce font sizes and weights, and fix text overflow.
-
Generate design variations
— Explore alternative layouts and visual directions quickly, then let a human curate and combine the best ideas.
-
Code generation and drafting
— AI-generated responses can provide inspiration or draft code that developers later modify.
-
AI-generated content detection
— Tools attempt to determine whether text, audio, images, or video were created or assisted by AI.
-
Cybersecurity evaluation
— Models are instructed to remove guardrails and attempt attacks so evaluators can assess their worst-case behavior.
-
Role-playing and text adventure simulation
— AI agents interact with other AI agents and tools inside a fictional scenario.
-
Generate bulk directory content
— Accelerate content production while leaving human curation, organization, validation, and quality control to the operator.
-
Natural-language reporting
— An LLM can turn calculated results and identified trends into a clean natural-language report.
-
Multi-step workflows
— Agents can support flexible multi-step workflows.
-
Code generation
— Generative AI can generate code from complex inputs.
-
Large document summarization
— Generative AI can transform and summarize unstructured documents.
-
Question answering over document sets
— Generative AI can support retrieval-augmented generation over unstructured documents.
-
Customer support
— An AI agent can understand intent, retrieve relevant knowledge, and generate a unique reply.
-
Reinforcement fine-tuning
— Train a model to make high-scoring answers more likely using candidate sampling and a grader.
-
Model compression through distillation
— Use outputs and reasoning traces from a large teacher model to fine-tune a smaller model.
-
Procedural task execution
— Agent skills package instructions and tools so a general-purpose model can perform specialized procedures.
-
Retrieval-augmented generation
— Retrieve relevant documents at query time and provide them to the model in the prompt.
-
Legal document and legal task performance
— Fine-tuning can specialize a general-purpose model for legal work.
-
Compress the boring parts of learning and debugging
— Leave human mentors more time for guidance that requires human judgment.
-
-
Critique designs and identify edge cases
— Improve planning without delegating architectural decisions to AI.
-
Brainstorm multiple design approaches
— Explore alternatives before implementation.
-
-
Handling ambiguity and conflicting evidence
— The AI should preserve multiple possible answers when the underlying documents support them instead of forcing a single answer.
-
Question clarification
— A clarification loop identifies ridiculous, malformed, or underspecified questions and prompts the user to rephrase or add details.
-
Answering questions with retrieved document information
— A RAG system uses vector database search results and the original user question to provide an answer through an LLM.
-
Triage patients
— Represents a high-risk clinical use case requiring traceable explanations, provenance, testing, and reliability.
-
Recommend a television show
— Provides an example of baseline and enhanced explainability based on prior viewing history and viewing patterns.
-
Guess a person's job from a bookshelf image
— Demonstrates pattern recognition without sufficient context or relationships; the AI guessed NSA employment from cryptography books.
-
Build an AI system
— Illustrates that AI can be used to build AI systems easily, though not necessarily in a risk-appropriate way.
-
Generate boilerplate and assist with syntax
— Reduce time spent on repetitive parsers, regular expressions, and unfamiliar configuration syntax.
-
Repair broken code
— Produce a corrected version of broken code such as Python.
-
-
Explain existing code
— Help developers understand legacy or unfamiliar code more quickly.
-
Generate code from natural-language requests
— Translate requirements such as returning a filtered, sorted, paginated list of users into working code.
-
Automate cyberattacks
— AI agents may increase attack volume and velocity and lower the barrier of entry for less-skilled attackers.
-
Drive ransomware operations
— JADEPUFFER was described as an LLM-driven operation that gained access, encrypted data and generated a ransom note.
-
Identify software vulnerabilities
— AI models can help defenders find zero-day vulnerabilities proactively, but attackers can also use the capability to discover and exploit vulnerabilities.
-
Analyze user interactions and model outputs in real time
— Classifiers are used to detect and block potentially harmful requests and outputs.
-
Adversary simulation workflow automation
— Perform routine steps so human teams can focus on novel attack chains and higher-value work
-
Incident-response automation
— Handle low-hanging tasks, perform data gathering, provide direction, and assist with decoding or decryption