AML Investigation Agent

An investigator agent with memory across cases, typologies and media.

Industry	Level	Difficulty	Recommended mode
Anti-money laundering	4 of 5	Expert	flat

Coming soon

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

The problem

• Investigations span many systems.
• Narratives take hours.
• Context is lost between investigators.

How SrvDB powers AML Investigation Agent

1. Databases for cases, typologies and adverse media.
2. The agent gathers evidence per case.
3. Drafts narratives with citations.
4. Case memory persists.

What changes

Today	With AML Investigation Agent on SrvDB
Manual evidence gathering	Automatic context
Hours of writing	Drafted narratives
Lost context	Persistent memory

How it works

1. Populate databases.
2. Agent gathers evidence.
3. Draft narrative.
4. Investigator reviews.
5. Store memory.

SrvDB features it uses

• Several databases: each database is a directory, so different data types or tenants stay separate.
• search_batch: runs many queries at once, in parallel inside Rust.
• Crash-safe persist(): after it returns, data survives a crash or power loss and reopens exactly as committed.
• Thread-safe handles: one database object can be shared between threads; searches run in parallel.

Use cases

• Case investigations
• Report drafting
• Quality assurance
• Look-backs
• Regulator requests
• Training

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("./aml-investigation-agent-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 case_context(case_summary, k=5):
    hits = db.search(embed(case_summary), k)
    return [(json.loads(db.get(i)), round(score, 3)) for i, score in hits]

Limits and honest notes

• Investigators sign off every report.

Caution

Decision support only: SrvDB does not replace regulated screening systems or investigator judgement.

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 Anti-money laundering projects

Level	Project	What it does
1 · Beginner	Typology Library	Search money-laundering typologies and red flags by description.
2 · Intermediate	Alert Prioritizer	Ranks AML alerts by similarity to past true and false positives.
3 · Advanced	Adverse Media Matcher	Deduplicates and matches adverse media to customers.
4 · Expert	AML Investigation Agent (this page)	An investigator agent with memory across cases, typologies and media.
5 · Frontier	Emerging Typology Radar	Detects clusters of cases far from every known typology.

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