Kill My Idea
Turn a startup pitch into a compact set of scores and a blunt Kill, Fix, or Ship verdict.
What Jev decides
Dimension scores, idea category, whether the pitch is understandable, and supporting diagnostic signals.
The app runs eight Jev Score judgments plus category and readability checks, computes a weighted total in code, and maps the result to Kill, Fix, or Ship thresholds.
- Jev role
- Produce bounded evaluations of a startup pitch across predefined dimensions.
- Input
- A short startup idea supplied by the user.
- Output
- Eight Score distributions, a category Choice, and Noul checks; application code derives the final verdict.
- Decision frequency
- Once per submitted idea.
- Fallback
- Weighted scoring and Kill/Fix/Ship thresholds are deterministic; real validation still requires customers and market evidence.
How it works
Overview
Kill My Idea packages Jev judgments into a consumer-facing startup critique. It scores dimensions such as demand, pain, differentiation, monetization, and founder fit on a 0–4 scale, classifies the idea, checks whether the input is understandable, and calculates the final verdict locally.
The output is a provocative heuristic, not market validation, investment advice, or evidence of demand. The repository says successful evaluations are archived by default unless the user opts out, so submitters should review that behavior before entering confidential ideas.
- Language
- TypeScript
- License
- Not declared
- Author
- Stefano Monte
Sources
Related projects
HA-Jev
Turn Jev answers into Home Assistant sensors and automation results.
What Jev decides
A yes/no probability, one option, or a score for a supplied question.
Jev Chat Assistant
An Android conversation copilot that uses Jev to interpret chats and rank reply candidates without sending for the user.
What Jev decides
The likely intent, conversation risk, reply need, best next action, unresolved tension, and which of three candidate replies fits best.
Distill
Route coding-agent work, reasoning effort, and context retention through bounded Jev decisions.
What Jev decides
Which configured model and effort should handle a call, what evidence deserves attention, whether another attempt is useful, and what context should be retained.