EXP-001AI Travel Planner
Three coding agents, one 1,245-line product spec, eight hours each. Build a real AI travel SaaS and deploy it.
- CCClaude Code
- CXOpenAI Codex
- CUCursor CLI

An experiment in public
Same challenge. Different agents. A fixed time budget. Each coding agent gets the same versioned spec and builds on its own. Then the results get tested, compared and shown with the evidence.
01 The format
Not "can AI write code?" but what an agent can deliver with a serious product spec, limited time and a fair chance to work on its own.
An ambitious app, game or tool, fully specified before any agent starts: behavior, constraints, deliverables and acceptance criteria. Versioned and published.
Claude Code, Codex and Cursor CLI each get the same spec, environment and time budget. They build independently in separate repos while the session is recorded.
Every build gets hands-on testing: real user journeys, edge cases, deployment, security and code. A polished screenshot doesn't count as proof.
A transparent rubric, side-by-side results and the raw artifacts (specs, repos, build reports) so you can judge for yourself.
02 Featured experiment
EXP-001Three coding agents, one 1,245-line product spec, eight hours each. Build a real AI travel SaaS and deploy it.
Self-reported elapsed time from each agent's BUILD_RESULTS.json. Each hour mark is one-eighth of the budget.
All three agent runs finished in under two hours, despite the eight-hour allowance.
03 The contenders
Anthropic's agentic coding tool. It works in the terminal, reads the codebase, runs commands and makes changes on its own.
In EXP-001 Observed: Observed by The Build Hypothesis during the recorded run.
Claude Code ran through without asking for further input during the run.
OpenAI's coding agent. It plans, edits and runs code from the command line, inside a sandbox with configurable approval policies.
In EXP-001 Observed: Observed by The Build Hypothesis during the recorded run.
Codex asked for approval whenever it needed to run a new command. Commands it had already been allowed could be allowed again.
The command-line agent from the makers of the Cursor editor. It runs the Cursor agent headless in any terminal.
In EXP-001 Observed: Observed by The Build Hypothesis during the recorded run.
Cursor CLI asked for approval once and offered a "run everything" option, which was selected.
04 House rule
Coding agents write confident reports. Every fact on this site is labeled with where it came from, so "the agent says it works" never gets mistaken for "we tested it and it works".
Read the methodology05 Up next
A real browser video editor with a multitrack timeline, AI captions, plain-English edits and a genuine MP4 export.
Five-on-five basketball in the browser, with real ball physics, keyboard control and an AI opponent.
A stationary 3D lane shooter where you steer an auto-firing squad, recruit soldiers and survive ten levels.
06 From the channel
No episodes published yet
The first experiment has been recorded. New uploads from @TheBuildHypothesisappear here automatically.
Subscribe for the first episode (opens in a new tab)
Every experiment becomes an episode: the spec, the runs, the failures and the hands-on evaluation. Subscribe to see the results first.