Startup idea roast
Kill it, fix it, or ship it: pressure-test an idea in one call.
Six questions every investor asks: is the problem real and already paid for, is there a specific customer, is it different, can you reach the first hundred customers, can you build it in weeks, and is it a thin wrapper a model provider will ship next month.
Try it live
Real calls to Jev. Pick an example or paste your own.
Pick an example or paste your own input, then run it.
Under the hood
Every question and rule, in the open. Fork it to change any of them.
What it asks
Reads idea, then asks 6 questions in one call.
- Q1Real, paid-for problemYes / no
Does the
ideatarget a problem people clearly already spend money or time on? - Q2Specific customerYes / no
Does the
ideaname a specific customer who has the problem? - Q3DifferentiatedYes / no
Is the
ideameaningfully different from obvious existing solutions? - Q4Reachable customersYes / no
Is there an obvious way to reach the first 100 customers?
- Q5BuildableYes / no
Could a small team build a first version in weeks, not years?
- Q6Thin wrapperYes / no
Is the
ideaa thin wrapper around a general AI model that the model's maker could add as a feature?
How it decides
Rules run in code, top to bottom. The first one that matches gives the verdict.
- 1If Thin wrapper ≥ 0.75 and Differentiated < 0.4Kill it
- 2If Idea score ≥ 62Ship it
- 3If Idea score ≥ 40Fix it
- ·DefaultKill it
A 0-100 score weighted from Real, paid-for problem ×3, Specific customer ×2, Differentiated ×2, Reachable customers ×1.5, Buildable ×1, Thin wrapper (inverted) ×1.5.
Call it from your code
Every template runs as-is with an API key, no setup: POST /api/v1/judges/idea-roast/run.
curl -X POST https://tryevally.com/api/v1/judges/idea-roast/run \ -H "Authorization: Bearer $EVALLY_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "input": { "idea": "ChatGPT but for writing emails." }}'Seen in the wild
Community builds on Jev that use this pattern. Not affiliated with Evally.
More in Product
- Product
User intent classifier
What does the user want, and are they telling the app to do something right now?
Ask to clarifyAsk a questionReport a problem+72 questions - Product
Product feedback triage
Sort feedback into bugs, requests, confusion and praise, and surface what's critical.
Critical bugUser at riskBug+64 questions - Product
Landing page clarity audit
Would a first-time visitor get what you sell, who it's for and why it's better?
ClearFixableConfusing7 questions - Product
Dark pattern detector
Flag manipulative UX copy and flows: confirmshaming, hidden costs, roach motels.
FairQuestionableManipulative6 questions