Have coding agents test your onboarding flow
Run coding agents through your product’s onboarding and get a scorecard, fix list, and session traces.
- What they did
- A product owner used AX Check to see how well coding agents could learn a product from its public material. They entered the site, which first evaluated the product page itself, then launched three coding agents in sandboxes to complete onboarding from start to finish. Afterward, the service collected the sessions and turned them into concrete feedback.
- How it went
- The report showed a score out of 100, a letter grade, and a leaderboard. Examples included oleander at 100, Moderne at 65 because it lacked llms.txt, and Strapi at 65 because agents had to guess at pricing.
- Tips
- Use the output to tighten docs, the marketing site, CLI guidance, MCP details, or Skills content. If you want a realistic test, ask the agent to rely only on public docs and to stop before anything involving credentials or submission.
Try it yourself with Claude Code
Act as a new developer trying to get set up with [product name] using only the public docs at [docs URL] and the product site. Work in a fresh temporary folder and try to finish the quickstart end to end. Keep a step-by-step log of what you do, every error you hit, and where you get stuck. After that, give me a scorecard out of 10, the five most important fixes for docs or setup, and a full record of your session. Before you enter any credentials, submit anything, delete anything, or make any payment, stop and ask for my approval first.
Fill in the [brackets]. Agents can make mistakes, so review anything before it is sent, paid or deleted.
Get 3 agent uses like this every morning
With the day's top AI news. Free, and one click to unsubscribe.
Related agent uses
Run coding agents in parallel with tmux and Markdown specs
Manuel Schipper uses separate tmux panes and numbered Markdown specs to keep several coding agents moving at once.
Use parallel agents to build a database engine
They split a SQLite implementation across several coding agents working in separate branches, then merged the pieces after repeated test-and-fix loops.
Track agent memory in git for coding work
Store project context in git so a coding agent can reuse decisions and notes across sessions.
Build a terminal calling tool with human backup
They wired a CLI agent to place calls and loop in a person only when it needed an answer.
Run bug fixes through a staged agent team
Use separate agent roles to reproduce, diagnose, review, and audit bugs before any irreversible step.
Create a CLI coding agent from a Python LLM base
Claude Code turned Simon Willison’s Python LLM template into a working CLI coding agent from two prompts.