Investigator Agent

An agent that gathers context across cases, policies and customer history.

Industry	Level	Difficulty	Recommended mode
Finance & banking	4 of 5	Expert	flat

Coming soon

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

The problem

• Investigators pivot across many systems.
• Notes are lost between shifts.
• Reports take hours.

How SrvDB powers Investigator Agent

1. Separate SrvDB databases for cases, policies and customer notes.
2. The agent searches all of them per case.
3. Case memory is stored and recalled.
4. Reports are drafted from retrieved evidence.

What changes

Today	With Investigator Agent on SrvDB
Manual pivots	One agent gathers context
Lost notes	Persistent case memory
Slow reports	Drafted from evidence

How it works

1. Populate databases.
2. Agent receives a case.
3. Search all databases.
4. Draft summary with links.
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.
• Thread-safe handles: one database object can be shared between threads; searches run in parallel.
• Crash-safe persist(): after it returns, data survives a crash or power loss and reopens exactly as committed.

Use cases

• Fraud investigations
• Customer complaints escalations
• Credit reviews
• Sanctions alert context
• Internal audits
• Regulatory responses

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("./investigator-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_description, k=5):
    hits = db.search(embed(case_description), k)
    return [(json.loads(db.get(i)), round(score, 3)) for i, score in hits]

Limits and honest notes

• Humans approve every conclusion.

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 Finance & banking projects

Level	Project	What it does
1 · Beginner	Policy Assistant	Answers staff questions from internal policies and product terms.
2 · Intermediate	Complaint Analyzer	Clusters and deduplicates customer complaints to find root causes.
3 · Advanced	Fraud Pattern Matcher	Compares new cases with confirmed fraud cases and ranks them for investigators.
4 · Expert	Investigator Agent (this page)	An agent that gathers context across cases, policies and customer history.
5 · Frontier	On-prem Risk AI Platform	A data-resident AI retrieval platform for risk and compliance teams.

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