AI Research

Advancing AI for
financial operations.

The research behind more capable, reliable AI for financial institutions. Built around the real work of onboarding, investigations, disputes, and money movement, and the teams who run it.

Explore our research
Sphinx / Applied intelligence

Interpretable Agentic Framework / IAF

Three agents. Every angle.

A case for. A case against. A judgment grounded in your policy. See how Sphinx makes the reasoning visible.

One case. The same facts.

The Prosecutor and Defender receive the same case evidence, with separate instructions and tools. Each builds an independent argument; neither can rewrite the other’s work.

Make both sides of the case.

The Prosecutor builds the risk case. The Defender looks for weak matches, missing context, and mitigating evidence. The disagreement becomes part of the record.

Apply the policy, not an average.

The Judge weighs both arguments against a signed, versioned rubric. It returns a recommendation, flags ambiguity, or escalates the case when the evidence is incomplete.

A recommendation you can inspect.

Your team reviews the evidence, both arguments, and the rubric behind the recommendation. Inputs, outcomes, and any human overrides stay in the case record.

Read the framework
Inside a screening reviewIllustrative case
Shared case fileA name-screening alert

Customer record · Watchlist · Identity documents

Prosecutor

Build the risk case

  • Strong name similarity
  • Country appears in both records
Watchlist + customer record

Defender

Challenge the match

  • Date of birth does not match
  • Source profile is incomplete
Identity document + source profile

Judge

Weigh both arguments against policy

Versioned rubric

Identity conflictIncomplete evidenceEscalate

Ready for human review

Evidence, both arguments, and rubric preserved.

The research agenda

From models to measurable outcomes.

Benchmarks, technical releases, and the methods behind them.

4 research areas

Benchmarks

Coming soon

Measuring AI on the work that matters.

Financial operations tasks, reference datasets, and results with the methodology behind them.

Models

Coming soon

Intelligence built for how financial institutions operate.

Models and agent systems for onboarding customers, investigating cases, and reviewing documents.

Evaluations

Coming soon

Beyond the right answer.

Evaluating the evidence, reasoning, and adherence to procedures behind every decision.

Papers

Coming soon

A closer look at how it works.

Technical whitepapers, experiments, and lessons from deploying AI in financial operations.

Upcoming research releases will include supporting papers, repositories, and evaluation results.

Our point of view

A score is only useful if you
know what it measures.

Financial operations are full of edge cases. The way we evaluate AI should reflect that.

01

Start with the actual work.

Onboarding a business. Clearing an alert. Resolving a dispute. Measure the task, not just the response.

02

Make the criteria explicit.

Correctness, supporting evidence, and procedure adherence belong alongside speed and cost.

03

Put results in context.

A useful result comes with its dataset, model version, evaluation method, and limitations.

Continue exploring

The thinking behind the work.

Explore Sphinx’s published guides and perspectives on AI for financial operations.

Explore the library