# Building sheal

*March 2026*

It started with a pattern we kept seeing: the same mistakes, session after session.

A Claude Code session would fail on a file path. We'd fix it. Next session, same mistake. Same wasted tokens. Same frustration.

The problem isn't the AI. The problem is that sessions are stateless. Every session starts from zero. There's no memory. No learning. No feedback loop.

sheal closes the loop.

## How it works

```
Session Capture (Entire.io / Claude Code native)
    |  session transcripts, diffs, metadata
    v
Self-Healing Engine (sheal)
    |  failure patterns, learnings, rules
    v
Agent Configuration (CLAUDE.md, .cursorrules, etc.)
    |  improved behavior
    v
Next Session (fewer mistakes)
```

After 20 sessions with sheal running, repeated mistakes dropped to near zero. Token waste fell by 40%. The agent got smarter because the feedback loop was closed.

`sheal check` before every session. `sheal retro` after every session. It compounds.

---

*— Luisa*