Field Intelligence Agent

An offline agent on rugged laptops combining text and imagery.

Industry	Level	Difficulty	Recommended mode
Government & defence	4 of 5	Expert	sq8

Coming soon

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

The problem

• Field teams lack connectivity.
• Information spans text and images.
• Power is unreliable.

How SrvDB powers Field Intelligence Agent

1. Multimodal embeddings put text and images in SrvDB.
2. The agent answers and recalls field notes offline.
3. Crash-safe persist() survives power loss.
4. One database per classification level.

What changes

Today	With Field Intelligence Agent on SrvDB
Paper notes	Searchable field memory
No connectivity	Fully offline
Data loss on power cuts	Crash-safe storage

How it works

1. Preload reference data.
2. Capture notes and images.
3. Embed locally.
4. Query and recall.
5. Sync when back at base.

SrvDB features it uses

• Fully offline: SrvDB runs in-process and never opens a network connection.
• Crash-safe persist(): after it returns, data survives a crash or power loss and reopens exactly as committed.
• Several databases: each database is a directory, so different data types or tenants stay separate.
• SQ8 compression (sq8): stores each value in one byte, 4× smaller than full precision.

Use cases

• Field reports
• Equipment identification by photo
• Translation memory
• Mission notes
• Logistics lookups
• After-action reviews

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("./field-intelligence-agent-db", dimension=512, mode="sq8")

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 field_recall(note, k=5):
    hits = db.search(embed(note), k)
    return [(json.loads(db.get(i)), round(score, 3)) for i, score in hits]

Limits and honest notes

• Handle data per classification rules.

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	Answers citizens’ questions from official public guidance.
3 · Advanced	Report Linker	Links related reports and requests across departments.
4 · Expert	Field Intelligence Agent (this page)	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)