Investigation Workbench

Isolated, multimodal workspace per investigation.

Industry	Level	Difficulty	Recommended mode
Media & journalism	4 of 5	Expert	flat

Coming soon

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

The problem

• Investigations mix documents, images and transcripts.
• Sources need protection.
• Teams collaborate under pressure.

How SrvDB powers Investigation Workbench

1. One SrvDB database per investigation.
2. Text and images embedded together.
3. Runs on the newsroom’s own hardware.
4. Delete the folder to remove everything.

What changes

Today	With Investigation Workbench on SrvDB
Scattered materials	One searchable workspace
Source exposure risk	Local only
Messy cleanup	Delete one folder

How it works

1. Create a workspace.
2. Ingest materials.
3. Search and annotate.
4. Draft.
5. Archive or delete.

SrvDB features it uses

• Several databases: each database is a directory, so different data types or tenants stay separate.
• delete and compact(): remove items immediately from search, then reclaim disk space.
• 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

• Document leaks
• Court records
• Interview transcripts
• Photo verification
• Timeline building
• Podcast research

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("./investigation-workbench-db", dimension=512)

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

Limits and honest notes

• Follow source-protection procedures.

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 Media & journalism projects

Level	Project	What it does
1 · Beginner	Archive Search	Search decades of articles by meaning.
2 · Intermediate	Fact-check Assistant	Matches claims against previously fact-checked claims and sources.
3 · Advanced	Narrative Tracker	Clusters stories and posts into narratives.
4 · Expert	Investigation Workbench (this page)	Isolated, multimodal workspace per investigation.
5 · Frontier	Secure Leak Analysis	Air-gapped analysis of large leaked datasets.

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