Citizen Service Bot

Answers citizens’ questions from official public guidance.

Industry	Level	Difficulty	Recommended mode
Government & defence	2 of 5	Intermediate	flat

Coming soon

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

The problem

• Contact centres are overloaded.
• Guidance is spread across sites.
• Answers must be accurate and sourced.

How SrvDB powers Citizen Service Bot

1. Public guidance pages are embedded.
2. Answers cite the official page.
3. Updates replace old guidance.
4. Runs on government infrastructure.

What changes

Today	With Citizen Service Bot on SrvDB
Long phone queues	Instant sourced answers
Outdated answers	Current guidance only
Scattered sites	One search

How it works

1. Crawl approved guidance.
2. Embed.
3. Answer with links.
4. Escalate unclear questions.
5. Refresh nightly.

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.
• Thread-safe handles: one database object can be shared between threads; searches run in parallel.

Use cases

• Benefits questions
• Licensing
• Tax deadlines
• Permits
• Public health guidance
• Local services

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("./citizen-service-bot-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 guidance_for(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

• Escalate anything personal or ambiguous to staff.

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 Government & defence projects

Level	Project	What it does
1 · Beginner	Doctrine Assistant	Air-gapped question answering over manuals and doctrine.
2 · Intermediate	Citizen Service Bot (this page)	Answers citizens’ questions from official public guidance.
3 · Advanced	Report Linker	Links related reports and requests across departments.
4 · Expert	Field Intelligence Agent	An offline agent on rugged laptops combining text and imagery.
5 · Frontier	Sovereign AI Stack	A fully reviewed, air-gapped AI stack with a published SBOM.

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