# Multi-agent error cascade audit

## Description
Audits error compounding probability across sequential multi-agent tool execution pipelines.

## Category
`evaluation`

## Tags
`evaluation`, `multi-agent`, `error-cascade`, `reliability`, `workflow`

## When to Use
Audit multi-step autonomous agent workflows to evaluate compounding error failure rates.

## Operational Limitations
Computes joint failure probability based on observed step error rates; does not execute agent tool steps.

## Verification Script
Run the deterministic verification checker:
```bash
python3 scripts/check.py examples/synthetic.json
```
Exit codes:
- `0`: Check passed and thresholds satisfied.
- `1`: Threshold breach or operational violation detected.
- `2`: Schema error or invalid usage.
