A framework for working with AI agents.
One question at a time until the problem is sharp.
Brief, design, specs — everything inspectable before work begins.
Each task completes and verifies before the next one starts.
Blind review: did the output match the intent?
npm install -g reespec
Your AI delivered something — just not what you meant. The gap appears somewhere, but you can't pinpoint where.
Every conversation resets. Decisions made yesterday aren't remembered. Context dissolves between sessions.
Complex tasks drift. The AI loses the thread halfway through, confidently producing something that missed the point.
You can't inspect the work in progress. By the time you see the output, it's too late to course-correct.
Each phase directly addresses one of the ways AI work goes wrong. Use all four, or start with just discover and plan.
Form the intent before the work starts.
Your AI asks you one question at a time, drawing out what you actually want — not what you think you want. Every branch of the decision tree gets resolved. You decide when there's enough clarity to move forward.
Turn intent into a verifiable contract.
A structured set of artifacts — brief, design, specs — is produced before any work begins. Every task has a clear before and after state that anyone can inspect. Nothing is left to interpretation. You review and approve before execution starts.
One verifiable step at a time.
Work proceeds one task at a time. Each step has a clear starting condition and a clear completion check. The AI pauses and reports on blockers rather than guessing. Progress is always visible.
Did the output match the intent?
An adversarial review reads only the original contract and the actual outputs — never the implementation notes. It surfaces gaps between what was asked and what was delivered, giving you a structured verdict per capability.
Most frameworks assume you're building software. reespec works for any complex task where intent needs to be expressed, work needs to be structured, and outcomes need to be verified.
| reespec | BMad Method | superpowers | |
|---|---|---|---|
| Audience | Anyone using AI agents | Software developers | Software developers |
| Weight | Lightweight | Heavy | Medium |
| Non-code tasks | ✓ First-class | ✗ Dev-only | ~ Partial |
| Structured discovery | ✓ | ✓ | ~ Partial |
| Verifiable outputs | ✓ All tasks | ✓ Code only | ~ Partial |
Install reespec globally, initialise it in your project, and ask your AI agent to use the reespec skills. Three commands and you're in.
npm install -g reespec reespec init reespec new request "my-first-request"