Topic
Agents use cases: 442 examples
Source-linked agent workflows tagged Agents.
Separate CRM facts from channel conversation when answering a deal-status question
Claude Tag answers account questions in the shared channel and identifies which facts came from the connected CRM and which came from the conversation.
Build a store-shift handoff from verified product, policy, and display notes
Microsoft's store-associate example uses Copilot for product and policy lookup, planogram guidance, and an end-of-shift summary for colleagues.
Codex overnight debug loop against a reproducing unit test
A developer leaves Codex CLI running for hours to add debug prints and test hypotheses against a deterministic front-door unit test until it can explain the bug with evidence.
Require Cursor to inspect reference files before cloning a module pattern
Agent Use Cases records a failed Cursor attempt to scaffold a second module because it missed the four or five reference files. The useful lesson is to make reference-context inspection explicit before generation.
Amplitude ships 3x production commits with Cursor cloud agents
Amplitude runs 1,000+ unprompted Cursor agent runs a week: Slack bugs become tickets and fixes, Bugbot merges 60–70% of low-risk PRs, and weekly production commits tripled with Cursor among top-3 committers.
Give a document agent a PDF table-extraction and OCR playbook
Anthropic's published PDF skill supplies tool recipes for reading tables, OCR of scanned pages, combining outputs, and producing files, giving an agent concrete operations for document work.
Send deduplicated sports-score summaries to a private Signal group
A public repository documents an agent that polled ESPN, used Claude Haiku for short commentary, checked scores deterministically, and sent confirmed results to Signal. Its 2026 World Cup deployment is retired.
Generate a landing-page draft from an idea and an authorized template library
The CrewAI project expands a brief, selects from supplied templates, and adapts the chosen page; its README requires users to provide appropriately licensed template files.
Generate an Instagram draft with a local-model CrewAI workflow
CrewAI's Instagram example uses specialist agents to turn an idea into a post and documents a local Ollama/OpenHermes setup alongside browser and search tool configuration.
Have an agent explain Markdown lint errors and proposed document changes
CrewAI's Markdown reviewer gives an assistant a deterministic linting tool, then asks it to turn the tool's errors into readable change recommendations rather than relying on model-only syntax judgment.
Adapt your own conversation into a screenplay with specialist agents
CrewAI's screenwriting example analyzes a discussion, creates dialogue, and formats a screenplay; the README includes sample input and output and supports several model endpoints.
Research a topic into a user-defined JSON extraction schema
LangChain's enrichment template searches and reads the web, extracts facts into a supplied schema, and checks completeness, with configurable models and tools in LangGraph Studio.
Run a configurable deep-research agent and inspect its report traces
Open Deep Research provides a public LangGraph implementation with separate research, summarization, compression, and report roles, configurable search providers, MCP support, and an evaluation workflow.
Pause a LangGraph trip planner to collect traveler preferences
A LangChain sample demonstrates parallel trip-input preparation, a join barrier, weather research, a human interrupt for preferences, and itinerary assembly using the same graph locally and when deployed.
Branch a data investigation visually with Microsoft Data Formulator
Microsoft's Data Formulator combines AI data transformation with visual chart editing and Data Threads, letting analysts compare alternative questions without losing the path through their analysis.
Convert image-rich PDFs to Markdown with an optional model-powered OCR plugin
MarkItDown documents an OCR plugin that accepts the same model-client configuration used for image descriptions and adds OCR during file conversion.
Route multi-knowledge-base support answers and escalate uncertain cases
An n8n template combines an Ollama agent, three Supabase vector knowledge bases, Postgres memory, request validation, deduplication, and confidence-based escalation across Slack, Gmail, and callbacks.
Detect duplicate invoices and pause risky approvals in n8n
This n8n template extracts invoice PDFs with GPT-4o, checks invoice numbers and totals, assesses category and risk, and uses a wait-and-resume approval path before recording the final status.
Claude Code skills plus scheduled GitHub agents automate review and triage
An HN commenter described a Claude Code setup with reusable skills for a UI library/Storybooks/APIs, a post-change review agent, PR checklist reviews, scheduled docs/coverage agents, and ticket triage that leaves a halfway-done plan on each issue.
Split Cursor for focus and Claude Code for parallel CI agents
A developer using both daily reports code quality converging once plans are clear, but keeps Cursor for slow focused diffs/sense-making and Claude Code for parallel/async agents plus well-scoped CI/CD tests and refactors.