Explain it like I know nothing about AI

AndyAI Stack is a safety system around very fast AI workers.

Think of an AI agent as a fast worker. AndyAI Stack is the supervisor, checklist, gatekeeper, evidence recorder, and recovery plan around that worker.

The simplest picture

Human

Decides intent, approves risk, keeps authority.

AndyAI Stack

Plans, scopes, checks policy, records evidence, routes recovery.

Agent

Does bounded work only after the Stack defines the safe path.

Evidence

Turns action into something reviewable and trustworthy.

Why this matters

Without Stack

Fast, but foggy

The agent may edit files, run commands, and produce output before the human clearly sees the plan, risk, proof, or recovery path.

With AndyAI Stack

Slower than chaos, faster than panic

The same work passes through plan, scope, dry-run, approval, verification, evidence, and recovery.

What happens step by step?

1
Human

You ask

Update my website, prepare release notes, or fix a repo problem.

Proof
The request is visible.
2
AndyAI Stack

The Stack plans

The request becomes a controlled plan with allowed files and boundaries.

Proof
A run contract exists.
3
AndyAI Stack

Dry-run first

The Stack previews what would happen before real files are changed.

Proof
Dry-run output exists.
4
Human

Human approves

Risky work waits for explicit human approval.

Proof
Approval record exists.
5
Agent

Agent acts

Only then does the AI agent perform the bounded work.

Proof
Changed files are known.
6
AndyAI Stack

Stack verifies

The result is checked through build, tests, rules, or review.

Proof
Verification result exists.
7
Evidence layer

Evidence remains

The work leaves a report so trust is reviewable later.

Proof
Evidence file exists.
You do not trust the agent blindly. You trust the path the work must pass through.