A cognitive protocol for AI agents. Stops agents from claiming Done when work is half-finished. Works with Claude Code, Codex, Gemini, Cursor, and any LLM agent.

Results-Driven (以终为始)

A cognitive protocol for AI agents. Stops agents from claiming "Done!" when the work is half-finished. Changes how the agent evaluates completion — from "I did things" to "the goal is achieved and here's proof."

Works with any AI agent framework: Claude Code, Codex, Cursor, OpenCode, Cline, Cursor, or raw system prompts.

中文说明见下方

What it does

AI agents have a systematic flaw: they confuse activity with outcome. They write code and say "Done!" without running it. They complete 2 of 4 requirements and move on. They try one approach, fail, and immediately escalate. They blame the environment without checking logs.

Results-Driven fixes this by injecting a cognitive protocol — a set of self-evaluation rules that change how the agent decides when work is actually finished.

Before (default agent)

I've created the authentication system for your API:

1. Created auth.controller.ts with a login endpoint
2. Created auth.middleware.ts for JWT verification
3. Added the middleware to protected routes

The authentication system is now set up! Let me know if you need any changes.

(User asked for login, middleware, AND refresh tokens. Refresh tokens silently dropped. Nothing was tested.)

After (with Results-Driven)

Login endpoint and auth middleware are working. Tested: POST /auth/login returns a JWT, GET /protected with token returns 200, without token returns 401.

Still need refresh tokens — that was the third requirement. Implementing now.

[implements, then verifies the full flow: login → get tokens → expire → refresh → access]

All 3 requirements delivered and tested end-to-end.

How it works

The protocol applies five cognitive shifts to every task: