--- title: "AI agents for coding: 68 real examples" canonical: "https://agenticfeats.com/categories/coding/2/" receipts: 68 shown: 42 page: 2 pages: 2 --- > From Agentic Feats: sourced examples of AI agents at work. Map of the site for agents: https://agenticfeats.com/llms.txt # AI agents for coding: 68 real examples Agentic Feats lists 68 sourced examples of AI agents doing coding work; 42 link the artifact; most common agent: Claude Code (26). Newest first. ## Feats, newest first - [OpenAI build-fix agent on OpenClaw](https://agenticfeats.com/c/openai-build-fix-agent-on-openclaw.md) (OpenClaw; Claim; 2026-10-13): An OpenAI engineer reports an internal OpenClaw agent, Androidclaw, working across Git, GitHub and logs to trace broken builds back to their causes. Result: Androidclaw traces broken builds to the relevant pull request and incident, and sometimes prepares and merges fixes itself. - [Marketing site from Figma](https://agenticfeats.com/c/marketing-site-from-figma-devin.md) (Devin; Numbers; 2026-10-13): Devin AI connected to a Figma file through MCP and built a WordPress marketing site with easy content management overnight. Result: The unfinished output is work the author would have quoted at about €2.5k, built in one overnight run. - [Rule-citing AI dungeon master game](https://agenticfeats.com/c/rule-citing-ai-dungeon-master-game-custom-agent.md) (Custom agent; Shown; 2026-10-13): The author built a browser D&D 5e dungeon crawl whose AI Dungeon Master answers rules questions by looking up and citing rules stored in Sanity. Result: A live game with 87 rules, 33 conditions, 14 spells and 15 monsters in two editions, answering rules questions in about 1.3 to 2.2 seconds. - [Docs crawler MCP server](https://agenticfeats.com/c/docs-crawler-mcp-server-claude-code.md) (Claude Code; Shown; 2026-10-13): Claude used the author's pulpie-mcp server to crawl a documentation site and save every page locally as clean Markdown files. Result: Claude pulled 60 documentation pages into local Markdown files in about 49 seconds, including roughly 10 seconds of backend cold start. - [Password reset migration experiment](https://agenticfeats.com/c/password-reset-migration-experiment-claude-code.md) (Claude Code; Numbers; 2026-10-13): Claude Code with Opus migrated a password reset flow in a legacy web app, with the author closely supervising under a pre-made plan. Result: It cost about two months of Pro subscription over half a working day, and ended up slightly slower than doing the migration by hand. - [Game engine from one prompt](https://agenticfeats.com/c/game-engine-from-one-prompt-grok-bot.md) (Grok Bot; Claim; 2026-10-13): Grok Bot ran four bots with one coordinator and built a Unity-style game engine from a single prompt, in minutes. Result: The author got a working Rust editor, .NET 10 scripting, multi-threaded runtime, culling, weather, lighting, water simulation and hot reloading within minutes. - [Hospital-style agent pipeline ships Db2 support](https://agenticfeats.com/c/hospital-style-agent-pipeline-ships-db2-support-custom-agent.md) (Custom agent; Shown; 2026-10-13): Cockroach Labs ran a multi-role coding agent pipeline modeled on a teaching hospital to add Db2 support to its MOLT migration tool. Result: Db2 support shipped in under two days for a $4172 token bill, versus 9 months and about $160K for Oracle; 27 PRs merged. - [Three agents build multiplayer Counter Strike](https://agenticfeats.com/c/three-agents-build-multiplayer-counter-strike-codex.md) (Claude Code, Codex, Gemini agent; Shown; 2026-10-13): The Instant team gave Codex, Claude Opus 4.5 and Gemini 3 Pro the same prompts to build a 3D multiplayer Counter Strike clone. Result: All three produced a playable multiplayer game with a map list and saved rooms; Opus won on visuals, Gemini on backend, Codex landed in between. - [Claude Code plays RollerCoaster Tycoon](https://agenticfeats.com/c/claude-code-plays-rollercoaster-tycoon.md) (Claude Code, Codex; Shown; 2026-10-13): Ramp Labs forked OpenRCT2, built a kubectl-style CLI, and let Claude Code manage a theme park through it. Result: Claude handled analytics, pricing, staffing and simple stall placement well, but failed at pathways, large coasters, and vertical terrain. The mod took about 40 hours. - [SQLite-like engine in Rust](https://agenticfeats.com/c/sqlite-like-engine-in-rust-claude-code.md) (Claude Code, Codex, Other; Shown; 2026-10-13): Claude, Codex, and Gemini workers, two of each, built a SQLite-style database engine in Rust by claiming tasks through git lock files. Result: About 19k lines of Rust across 154 commits in three days. The engine passes 64 SQLLogicTest queries and 282 AI-written unit tests. - [Coding agent built on LLM](https://agenticfeats.com/c/coding-agent-built-on-llm-claude-code.md) (Claude Code; Shown; 2026-10-13): Claude Code on the web wrote a spec, then built and tested a coding agent library on LLM using red/green TDD. Result: Shipped llm-coding-agent 0.1a0 to PyPI with six file and shell tools, a CLI and a Python API; it built a working ASCII-art clock app. - [Month of Devin tasks](https://agenticfeats.com/c/month-of-devin-tasks.md) (Devin; Numbers; 2026-10-13): Devin was given more than 20 real coding, research, and code-modification tasks over a month by an Answer.AI team to test its autonomy. Result: Out of 20 tasks, Devin had 14 failures, 3 successes, and 3 inconclusive results, with no pattern predicting which would work. - [Month-long Devin trial](https://agenticfeats.com/c/month-long-devin-trial.md) (Devin; Numbers; 2026-10-13): Devin was tested by the Answer.AI team on 20+ real coding, research, and code-modification tasks over a month through Slack. Result: Out of 20 tasks, Devin had 14 failures, 3 successes, and 3 inconclusive results, with no predictable pattern for which would work. - [Dependency and framework upgrade](https://agenticfeats.com/c/dependency-and-framework-upgrade-cursor.md) (Cursor; Shown; 2026-10-13): Cursor listed outdated packages by upgrade difficulty, then upgraded them in stages, including Remix v2 to React Router v7 on a 42k-line site. Result: The author upgraded kentcdodds.com across all dependency tiers, finishing a Remix v2 to React Router v7 migration with routing matching the original structure. - [Vue 2 to Vue 3 migration](https://agenticfeats.com/c/vue-2-to-vue-3-migration-devin.md) (Devin; Claim; 2026-10-13): Devin was asked to migrate a production Electron app from Vue 2 to Vue 3 with Composition API, script setup, and Pinia. Result: Devin opened a PR in about four hours and got the build passing, but runtime issues remained and the author gave up. - [Personal site redesign with Codex](https://agenticfeats.com/c/personal-site-redesign-with-codex.md) (Codex; Shown; 2026-10-13): Codex CLI redesigned the author's personal site after reading a design prompt copied from Anthropic's frontend-design plugin into a local markdown file. Result: The author shipped a redesigned personal site, nearly right in one shot, after a few more iterations. - [Cursor for data science scorecard](https://agenticfeats.com/c/cursor-for-data-science-scorecard.md) (Cursor; Claim; 2026-10-13): The author used Cursor on a real data science project in Python and graded it across general coding and data tasks. Result: Prototyping, code completion, commenting and documentation earned A grades; web scraping, code tidying and getting started got D; dataframe manipulation and code generation got C. - [AI chat app on Nokia 110](https://agenticfeats.com/c/ai-chat-app-on-nokia-110-codex.md) (Codex, Custom agent; Shown; 2026-10-13): Codex helped the author reverse-engineer a Nokia 110 4G's firmware and build a native AI chat app with a custom agent. Result: A working prototype runs on the handset over mobile data: typed chat via DeepSeek, battery check, torch, calls and alarms, tested on the phone. Page 2 of 2. Newer feats: https://agenticfeats.com/categories/coding.md