Claude Code
Best for: Serious work on real repos
Anthropic's agent for your terminal, IDE and desktop. Reads the whole repo, runs commands and tests, and handles large multi-file changes well.
Visit Claude Code ↗Home / Use case
Make slow code faster
“Part of my program is too slow and I don't know where to start.”
Agents can profile, try optimizations and benchmark them in a loop. Watch for cheating: an agent may 'win' by skipping work or changing the benchmark.
Fix it yourself in 3 steps
- Write a benchmark and a correctness test so 'faster' and 'still right' are both measured.
- Ask the agent to profile first and list the top hotspots before changing anything.
- Let it try one change at a time; check the diff to make sure tests and benchmark weren't edited.
Copy this prompt
Make [function/module] faster without changing its results. First run the benchmark and profiler and report the top 3 hotspots. Then try one optimization at a time, rerunning the correctness tests and benchmark after each. Never edit the tests or benchmark. Stop after 5 attempts and summarize what helped.
Fill in the [brackets]. Each prompt says when the AI should stop, so it doesn't wander off.
Agents people used for this: Custom agent.
Inspired by real examples collected at agentusecases.ai.
📚 3 real stories of people doing this with AI agents
- Audit a codebase for redundant dependencies and polyfills · custom-built or unnamed agent
- Optimize CUDA kernels with agents that benchmark and profile · custom-built or unnamed agent
- Speed up Rust code by having agents iteratively optimize it · custom-built or unnamed agent
Collected at AgentUseCases.ai.
Tools for this
Cursor
Best for: Editor-first developers
A VS Code-style editor built around AI, with background agents. The comfortable choice if you live in an editor.
Visit Cursor ↗OpenAI Codex
Best for: Delegating tasks as PRs
OpenAI's coding agent, in the CLI and in the cloud. Good at handing off well-scoped tasks that come back as pull requests.
Visit OpenAI Codex ↗