Continuous Audit Agent

An agent monitoring entries and contracts continuously.

Industry	Level	Difficulty	Recommended mode
Fiscal auditing	4 of 5	Expert	flat

Coming soon

A complete, runnable Continuous Audit Agent reference implementation is in progress. The architecture and core code below already work with SrvDB 0.3.

The problem

• Audits are periodic.
• Anomalies surface late.
• Teams are small.

How SrvDB powers Continuous Audit Agent

1. Journal entries, contracts and findings in separate databases.
2. The agent flags unusual entries and deviations.
3. Engagement memory persists.
4. Per-entity isolation.

What changes

Today	With Continuous Audit Agent on SrvDB
Annual checks	Continuous checks
Late anomalies	Early flags
Small teams	Agent assistance

How it works

1. Connect data.
2. Index continuously.
3. Flag anomalies.
4. Review.
5. Report.

SrvDB features it uses

• Several databases: each database is a directory, so different data types or tenants stay separate.
• upsert: inserts new items and replaces changed ones, so the knowledge base stays current.
• Crash-safe persist(): after it returns, data survives a crash or power loss and reopens exactly as committed.
• search_batch: runs many queries at once, in parallel inside Rust.

Use cases

• Journal entry testing
• Contract deviations
• Expense anomalies
• Procurement signals
• Public budgets
• Grant audits

Core code

embed() is your embedding model (for example sentence-transformers, or a function that turns your records into feature vectors).

import json
import srvdb

db = srvdb.Database("./continuous-audit-agent-db", dimension=384)

def ingest(items):
    """items: list of (id, text, metadata dict)"""
    db.upsert(
        ids=[i for i, _, _ in items],
        embeddings=[embed(t) for _, t, _ in items],
        metadatas=[json.dumps(m) for _, _, m in items],
    )
    db.persist()                      # crash-safe checkpoint

def unusual_entries(entry_description, k=5):
    hits = db.search(embed(entry_description), k)
    return [(json.loads(db.get(i)), round(score, 3)) for i, score in hits]

Limits and honest notes

• Auditors review every flag.

Build roadmap

1. Prototype: load a sample of real data with flat mode and check that searches return what an expert expects.
2. Measure: if you move to an approximate mode, compare its results with flat on the same queries (recall).
3. Pipeline: add continuous upsert and decide when to call persist().
4. Harden: test restarts and crashes, add logging, review every output path with domain experts.
5. Deploy: ship the database directory with the application or service.

All Fiscal auditing projects

Level	Project	What it does
1 · Beginner	Working-paper Search	Search prior working papers and findings by meaning.
2 · Intermediate	Finding Drafter	Drafts audit findings and management letters from similar past findings.
3 · Advanced	Duplicate Invoice Detector	Finds duplicate and near-duplicate invoices and vendors.
4 · Expert	Continuous Audit Agent (this page)	An agent monitoring entries and contracts continuously.
5 · Frontier	Public Funds Analytics	Cross-entity pattern discovery for public-sector auditors.

See also: Use cases · Live examples (coming soon)