AI investigation methodology 2026

Agents that argue their way to a defensible answer

A multi-agent investigation practice built on competing personas, adversarial debate, and an LLM judge. It turns ad-hoc fraud questions into auditable runs, and once caught an agent fabricating a reconciliation.

Business Analyst, AWS Payments & Fraud Prevention

Impact

Turned ad-hoc fraud questions into dozens of auditable, leadership-ready reports backed by 800+ scripts and 900+ outputs, reconciled to the cent, and the adversarial loop caught an LLM fabricating a reconciliation before it shipped.

Leadership-ready reports
Dozens
Near-daily cadence over a month-plus.
Query scripts · outputs
800+ scripts
Backed by 900+ saved outputs, every claim traceable to its query.
Fabricated reconciliation
Caught
The debate loop overturned an agent's invented headline before it shipped.
Context

LLM agents are fast and confident, which in fraud work is dangerous: a fluent, wrong reconciliation that lands in a stand-up is worse than no answer. I wanted the speed without trusting any single model's say-so.

What I did

I built a methodology, not just prompts. An 'arena' runs competing personas at a question and has a judge synthesize consensus, disagreements, and the best-supported answer. A 'debate' mode has two agents argue across rounds to a converged verdict, and an 'investigation' mode runs params-driven ring deep-dives. Every run is a self-contained folder with numbered scripts, raw outputs, and a graded report, so any number traces back to the query that produced it. Headline figures get reconciled to the cent across independent reproductions, and a second agent re-checks the first.

Outcome

A near-daily cadence over a month-plus produced dozens of leadership-ready reports backed by 800+ query scripts and 900+ outputs, the majority reconciled to the cent. The adversarial structure earned its keep: in one debate, an agent invented an impossible reconciliation and a wrong headline. The loop caught it and drove the agents to a corrected, converged answer instead of shipping the fabrication.

Without this work

A single confident agent ships the fabricated reconciliation and its wrong headline straight into a stand-up, and the month's investigation throughput collapses back to one slow manual case at a time.

The failure mode of an LLM in fraud analysis isn’t being slow. It’s being fluently wrong in a stand-up. So I built the speed in but never let a single model’s confidence be the evidence.

The methodology has three shapes. An arena runs competing personas at the same question and has a judge synthesize where they agree, where they don’t, and which answer is best-supported. A debate puts two agents in an argument across rounds until they converge on a verdict. An investigation mode runs structured, params-driven ring deep-dives. The common thread is that every run is a self-contained folder of numbered scripts, raw CSVs, and a graded report, so any figure can be clicked back to the exact query behind it.

Discipline lives on top of that: headline numbers reconciled to the cent across independent reproductions, and a second agent re-checking the first before anything is called done. Over a month-plus this sustained a near-daily cadence, with dozens of leadership reports backed by 800+ scripts and 900+ outputs.

The clearest proof it was worth the overhead came in one debate, where an agent invented a reconciliation that couldn’t be true and attached a wrong headline to it. A single-agent pipeline would have shipped it. The adversarial loop caught the fabrication and drove both agents to a corrected, converged answer. That’s the whole reason the structure exists.

  • Multi-agent
  • LLM judge
  • Adversarial debate
  • Reproducibility
  • MCP