Free Agent Evaluation Harness Prompt
Compare coding agents on the same task, evidence standard, and definition of done—not vibes.
OUTPUTReusable task spec, acceptance rubric, evidence log, verification record, retry/cost ledger, and comparative scorecard.
REPLACESModel rankings based on impressions, cherry-picked demos, and unrepeatable tests.
RUNS INChatGPT · Claude · Codex
HOW TO USE IT
Give the prompt real context. Get a usable artifact.
Share your product, buyer, motion, constraints, and the decision you need to make. The workflow separates facts from assumptions, compares viable paths, and produces the promised artifact instead of generic advice.
Outputs vary by AI and context. Treat this prompt as a launch point and adapt it to fit your needs. Attribution isn’t required, but appreciated; backlinks are preferred.
FULL PROMPT · FREE FOREVER
Copy the full GTM workflow.
No account or email required. Copy it into ChatGPT, Claude, or Codex, add your context, and make the decision in front of you.
Loading the full prompt…
Free forever. No email gate.