Be brutally honest. Act as a skeptical senior engineer who's seen too many reinvented wheels. 1. **Does this already exist?** - Name specific existing tools, libraries, or services that solve this - What would I lose by just using those? 2. **Is this actually a problem?** - Who has this problem badly enough to use a new tool? - What are they doing today without this? - Is "doing nothing" or "manual process" actually fine? 3. **Am I overcomplicating something simple?** - Could this be a bash script? - Could this be a GitHub Action someone already wrote? - Could this be solved with existing tools + documentation? 4. **What's the simplest version that validates the idea?** - Not MVP. Simpler. What's the one-hour version? - What's the version that uses only tools that already exist? 5. **Why would this fail?** - What's the most likely reason nobody uses this? - What's the hidden complexity I'm not seeing? Don't be encouraging. Don't soften it. If this is a bad idea or already solved, say so directly.
Reality Check
Brutally honest assessment. Does this already exist? Is this actually a problem? Am I overcomplicating something simple?
Product Updated Jan 17, 2026 ~264 tokens
0.1% of 200k
How to use this prompt
- Copy the prompt using the button above
- Paste it into your preferred AI coding assistant
- Adjust any placeholders or context as needed
- Let the agent implement the changes
Related prompts
- Grill Me Strategy
If the idea survives, question it branch by branch until the design is clear.
- Avoid Feature Creep Product
Keep a real idea small, so the honest version stays the shipped version.
- Repo Shape Operating Docs
Turn what survives into a falsifiable claim and a notebook of experiments.
- Effect PRD Architect Ralph Loop
Write the surviving idea as a PRD with failure modes and gates.
- Product Building Guidelines Product
Check the idea against twenty principles for building products.