Policy Assistant

Answers staff questions from internal policies and product terms.

Industry	Level	Difficulty	Recommended mode
Finance & banking	1 of 5	Beginner	flat

Coming soon

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

The problem

• Policies are long and change often.
• Front-line staff need quick, correct answers.
• Customer data must stay internal.

How SrvDB powers Policy Assistant

1. Policies and product terms are embedded in SrvDB.
2. Questions retrieve passages; a local LLM answers with citations.
3. Updates via upsert.
4. Runs inside the bank’s network.

What changes

Today	With Policy Assistant on SrvDB
Email the compliance team	Instant answers with sources
Outdated PDFs	Current passages only
Cloud AI blocked	Local stack

How it works

1. Collect policies.
2. Embed.
3. Answer with citations.
4. Review usage.
5. Refresh on change.

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

• Lending policy questions
• Fee and product terms
• KYC procedure questions
• Complaint handling steps
• Data-handling rules
• Branch procedures

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("./policy-assistant-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 policy_answer(question, k=5):
    hits = db.search(embed(question), k)
    return [(json.loads(db.get(i)), round(score, 3)) for i, score in hits]

Limits and honest notes

• Answers must show the source policy.

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 (this page)	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	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)