Questionnaire Autopilot

Answers security and vendor questionnaires from past approved answers.

Industry	Level	Difficulty	Recommended mode
Governance, risk & compliance	2 of 5	Intermediate	flat

Coming soon

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

The problem

• Questionnaires repeat the same questions.
• Answers are scattered.
• Responses take weeks.

How SrvDB powers Questionnaire Autopilot

1. Approved answers are embedded.
2. Each question retrieves the closest answers.
3. A local LLM drafts responses with sources.
4. Approved responses fed back.

What changes

Today	With Questionnaire Autopilot on SrvDB
Weeks of manual work	Drafts in minutes
Inconsistent answers	Approved answers reused
Lost knowledge	Growing library

How it works

1. Embed approved answers.
2. Import questionnaire.
3. Draft answers.
4. Review.
5. Save approved.

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.
• 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.

Use cases

• Security questionnaires
• Vendor due diligence
• RFP responses
• Customer audits
• Privacy assessments
• Insurance forms

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("./questionnaire-autopilot-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 best_answers(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

• Owners approve every answer.

Caution

SrvDB supports compliance work; it does not certify compliance with any framework.

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 Governance, risk & compliance projects

Level	Project	What it does
1 · Beginner	Policy Search	Find the right policy passage from a plain question.
2 · Intermediate	Questionnaire Autopilot (this page)	Answers security and vendor questionnaires from past approved answers.
3 · Advanced	Control Mapper	Suggests mappings between controls across frameworks.
4 · Expert	Regulatory Change Agent	Assesses which policies and controls a new regulation affects.
5 · Frontier	Continuous Compliance Platform	On-prem AI retrieval for evidence, controls and audits with an audit trail.

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