HOME

GAIN 2026

Northwestern Agentic AI Investigative Journalism Challenge — Buried Signals' submission.

A note before the work

Thank you to Northwestern's Knight Lab and the GAIN organisers for hosting this challenge. Building agentic skills that hold power accountable is exactly the kind of work the next decade of journalism needs. We're grateful to be part of it.

The submission

An agentic skill that reads a million lobbying records and finds the story.

We built data-detective — a ten-skill orchestrator for structured-records investigations — and ran it against U.S. federal lobbying disclosures. Nine verified findings. Every numeric claim cites a SQL query by SHA hash; every record has an evidence card; every external source is archived.

Deliverables

  1. A

    Findings report

    Public-facing journalism artifact. Per-finding replication paths, archived primary sources, phase-by-phase methodology walkthrough.

  2. B

    data-detective Agent Skill

    Orchestrator + nine sub-skills. All ten validate against the agentskills.io spec. Portable across structured-records corpora.

  3. C

    Audit trail

    Every detector output, every evidence card, every adversarial fact-check verdict, every Spotlight OSINT investigation output. The full audit chain for replication.

  4. D

    Interaction traces

    Session structure and human-judgment moments. Brief approval, methodology approval, Gate 1 review, finishing-path choice, OSINT lead curation.

Method

Deterministic where possible. LLM only over already-filtered candidates.

Full corpus ingest
~4 min
pyarrow bulk insert · 60× speedup
Entity resolution
99.9%
deterministic bridge keys
LLM tokens on raw documents
0
exploration is SQL-only
SQL-only detectors
12
SHA-tagged per query
Agent Skills
10
orchestrator + 9 sub-skills
Findings verified · OSINT promoted
9 / 6
spotlight-handoff cycles

Submission details

Submitter
Tom Vaillant · Buried Signals · tom@buriedsignals.com
Repository
github.com/buriedsignals/gain-2026 · will be tagged final-submission at the submission deadline
License
MIT (skills) · CC-BY-4.0 (findings + report)
Conflicts of interest
None. Tom Vaillant has no relationship to any registrant, client, member, or lobbyist named in the findings.
Future development
This repository is the frozen prize submission. Productized data-detective evolves at github.com/buriedsignals/skills.

DOC-REF · BS-GAIN-2026 · SUBMITTED 2026-05-23