Finding Drafter

Drafts audit findings and management letters from similar past findings.

Industry	Level	Difficulty	Recommended mode
Fiscal auditing	2 of 5	Intermediate	flat

Coming soon

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

The problem

• Writing findings is slow.
• Quality varies.
• Standards wording matters.

How SrvDB powers Finding Drafter

1. Past findings and standards passages are embedded.
2. A new issue retrieves similar findings.
3. A local LLM drafts with citations.
4. Reviewers edit.

What changes

Today	With Finding Drafter on SrvDB
Slow drafting	Drafted findings
Inconsistent wording	Consistent style
Standards lookups	Retrieved passages

How it works

1. Embed findings.
2. Describe the issue.
3. Draft.
4. Review.
5. Save final.

SrvDB features it uses

• Exact search (flat): every query compares against every stored vector, so results are exact and explainable.
• 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.
• Fully offline: SrvDB runs in-process and never opens a network connection.

Use cases

• Internal control findings
• Compliance findings
• Management letters
• Public-sector reports
• Follow-ups
• Board summaries

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("./finding-drafter-db", dimension=768)

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

Limits and honest notes

• Auditors own every finding.

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 (this page)	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	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)