Build a working coding agent in R from three tools
Author builds a functional coding agent in R starting from three tools, then adds tools to make it safer and more efficient.
Shipping code, reviewing PRs, running infra, and fixing things at 3am.
198 use cases
Author builds a functional coding agent in R starting from three tools, then adds tools to make it safer and more efficient.
Author's custom-built agent made its first code change to its own repository.
Simon Willison had the Fable model more or less one-shot a CLI coding agent built on his LLM Python library.
The author built a Canvas LMS tool with Claude Code that lets educators list courses, find missing submissions, monitor forums, schedule announcements and export the gradebook.
A reviewer had Manus build a currency converter, fix a find_max bug and make a landing page, with mostly strong results.
Users had Hermes Agent set up a local AI stack (liteLLM, Postgres, Prometheus, Grafana) and install Gbrain as an MCP server to build a personal knowledge graph.
A team used Devin for a month on small fixes like chart formatting and API edge cases, with tests and PRs; a complex full-stack task went poorly.
Devin opened a PR with the endpoint and backend wiring that was merged, but missed API key logic, code style and abstraction, needing review fixes.
A reviewer had Devin set up a project, write code, install dependencies, test endpoints and add error handling in about 4 minutes on a simple task.
Answer.AI testers found Devin completed only 3 of 20 tasks, succeeding at moving Notion data to Google Sheets and building a planet tracker.
Cognition staff assign Devin work in Slack or Linear; it posts PRs, fixes bugs flagged by review bots and works CI and lint failures until checks pass.
A review lists Devin building a full-stack to-do app, debugging a public repo with a PR, and doing Docker setup, deployment and CI/CD.
A software engineer had Replit Agent build a searchable map of Wefunder brick-and-mortar companies in about 3 hours for about $22.
The author used Replit Agent to build a Postgres-backed web app with image storage, analytics and a landing page; an S3 switch failed and was reverted.
Replit Agent generated a scraper, database models, API endpoints and front end that stores and shows Hacker News items, then deployed it.
Cursor's background agent built a pricing landing page from a short spec in about 5 minutes on a new branch and opened a PR.
A founder used Cursor agents to find prototype gaps, draw ASCII wireframes, and plan and implement a feature with parallel agents in worktrees.
A developer used Cursor and Warp agents to analyze NestJS database queries and recommend indexes for a production performance problem.