---
title: Audit Log
description: How agent writes and human approve/reject decisions are recorded for review in Log.
canonical: https://bennybooks.com/developers/guides/audit-log
markdown: https://bennybooks.com/developers/guides/audit-log.md
---
# Audit Log

How agent writes and human approve/reject decisions are recorded for review in Log.

> **Documentation index.** Fetch [https://bennybooks.com/developers/llms.txt](https://bennybooks.com/developers/llms.txt) before browsing further. Prefer markdown (this file or `Accept: text/markdown`). Site-wide map: [https://bennybooks.com/llms.txt](https://bennybooks.com/llms.txt).

BennyBooks treats explainability as a product surface. Every propose-write and every human approve/reject is written to audit_log and shown in-app at Log (https://bennybooks.com/log). Agents do not get a REST or MCP tool to read that trail in v1 — write as if a human will read your reason tomorrow.

> **Two human surfaces.** Ledger → Approvals is the decision queue for pending proposals. Log (https://bennybooks.com/log) is the durable history of agent actions and review outcomes. Tell users about both after you propose.

## What is logged

| Event | Typical tool / actor |
| --- | --- |
| Propose categorization | propose_categorization · mcp:<tokenId> |
| Propose journal entry | propose_journal_entry · mcp:<tokenId> |
| Propose receipt link | propose_receipt_link · mcp:<tokenId> |
| Propose / create note | attach_note or create_note · mcp:<tokenId> |
| Approve proposal | approve_proposal · user:<clerkUserId> |
| Reject proposal | reject_proposal · user:<clerkUserId> |

Reads (list_transactions, get_dashboard_summary, …) are not logged. Proposal rows also stay queryable via GET /proposals while pending.

## Write for humans

- reason — short, specific (e.g. “Description matches counterparty AWS”), not “looks like software”
- confidence — honest 0–1; low confidence should say why
- evidence[] — structured types when you have them (counterparty_match, keyword, rule, historical, receipt)
- categoryCode — stable codes so Log and Approvals show the same chart slot

> **No agent read API (v1).** Do not scrape https://bennybooks.com/log or invent a list_audit tool. Use list_pending_proposals for queue state. Humans own the historical Log UI.

## Related

- Agent skill: https://bennybooks.com/skill.md (Audit trail section)
- Categorize guide: https://bennybooks.com/developers/guides/categorize
- Proposals API: https://bennybooks.com/developers/api/proposals
- MCP design: https://bennybooks.com/developers/guides/mcp-design

---

## Machine-readable

- HTML: https://bennybooks.com/developers/guides/audit-log
- Markdown: https://bennybooks.com/developers/guides/audit-log.md
- Docs index: https://bennybooks.com/developers/llms.txt
- OpenAPI: https://bennybooks.com/openapi.json
- Skill: https://bennybooks.com/skill.md
- Auth: https://bennybooks.com/auth.md

```json
{
  "@context": "https://schema.org",
  "@type": "TechArticle",
  "headline": "Audit Log",
  "description": "How agent writes and human approve/reject decisions are recorded for review in Log.",
  "url": "https://bennybooks.com/developers/guides/audit-log",
  "inLanguage": "en",
  "encodingFormat": [
    "text/html",
    "text/markdown"
  ],
  "isAccessibleForFree": true,
  "publisher": {
    "@type": "Organization",
    "name": "BennyBooks",
    "url": "https://bennybooks.com",
    "logo": {
      "@type": "ImageObject",
      "url": "https://bennybooks.com/apple-icon.png"
    }
  },
  "mainEntityOfPage": "https://bennybooks.com/developers/guides/audit-log",
  "image": "https://bennybooks.com/opengraph-image",
  "workExample": {
    "@type": "CreativeWork",
    "url": "https://bennybooks.com/developers/guides/audit-log.md",
    "encodingFormat": "text/markdown",
    "name": "Audit Log (Markdown)"
  },
  "about": {
    "@type": "WebAPI",
    "name": "BennyBooks Agent API",
    "url": "https://bennybooks.com/api/v1",
    "documentation": "https://bennybooks.com/developers"
  }
}
```
