Skip to content
ClaudeClaude

Fighting financial crime with Claude Cowork

Leveraging Claude Cowork to optimize high-stakes workflows and fight financial crime. In-house MCPs, MCP gateways, evals, deploying critical workflows in production for analyst teams.

May 22, 202627mWatch on YouTube ↗

At a glance

WHAT IT’S REALLY ABOUT

Qonto’s secure, auditable agentic AI for financial crime investigations

  1. Qonto targets the slow, manual “second line of defense” in financial-crime investigations by using agentic AI to gather scattered data, synthesize findings, and assist investigator judgment.
  2. They chose Claude Opus 4.7 for long-context, cross-document reasoning (citing GraphWalks as a relevant benchmark for finding facts distributed across large contexts).
  3. To address security and compliance concerns with MCP, they built a centralized MCP gateway providing SSO/OAuth authentication, RBAC, short-lived PASETO tokens, and an append-only audit trail.
  4. Investigators interact through a Claude Cowork plugin that encapsulates domain workflows into modular “skills,” calls specific tools/data sources, and renders interactive widgets/dashboards in one interface.
  5. They emphasize evals as essential for critical workflows—testing tool-choice/ordering, grounding (hallucination avoidance), and quality of reasoning—both to prevent regressions and to satisfy compliance and user trust.

IDEAS WORTH REMEMBERING

5 ideas

Agentic AI is most impactful where humans currently “tab-hop” across tools.

Qonto focuses on the investigation step after alerts, where analysts compile data from many sources and manually reason about it; an agent that fetches, organizes, and summarizes can compress hours of work into a single guided workflow.

Long-context, cross-document reasoning should drive model choice.

Their selection of Opus 4.7 is justified by the need to connect facts scattered across many documents and data sources; benchmarks like GraphWalks better reflect this investigative reality than generic QA scores.

MCP becomes enterprise-ready when wrapped in a security/compliance “harness.”

Instead of exposing many tools directly, they centralize authentication, authorization, and logging in an MCP gateway so risk/compliance concerns (who accessed what, and why) are addressed systematically.

Use short-lived, scoped tokens to reduce blast radius and avoid token reuse.

They avoid passing SSO tokens downstream and mint short-lived PASETO bearer tokens for MCP servers, limiting damage from leakage and simplifying downstream verification via signed public tokens.

RBAC should be infrastructure-as-code to stay auditable and reviewable.

Defining access in versioned Terraform enables change history, approvals, and reproducibility—key for regulated environments where “who can access what” must be provable over time.

WORDS WORTH SAVING

5 quotes

Just to give you an idea, between two and five trillion US dollars are laundered every year in the world.

Stefano Amorelli

We ask a lot from them. So what's the role of AI? How we can apply AI to make this process better?

Stefano Amorelli

When you mention MCP to risk and compliance, when you mention it to security, you can raise some eyebrows, to put it mildly.

Stefano Amorelli

For compliance reasons, we do not want to fully automate the process just yet. So we want to keep human judgment, at least on the critical decisions, because these actions, these financial crime investigations, have consequences, have legal consequences as well.

Stefano Amorelli

Evals, start with evals. I like to compare, uh, evals to TDD.

Stefano Amorelli

Financial crime investigation lifecycle (alerts → manual casework)Agentic AI for second-line investigationsModel selection for long-context reasoning (Opus 4.7, GraphWalks)MCP security posture and governanceCentralized MCP gateway architectureSSO/OAuth, RBAC, PASETO short-lived tokensAuditability (append-only logs, OTEL, Grafana/ClickHouse)Cowork plugin design (orchestrator, sub-skills, meta-skill, XML prompts)Evals for grounding, tool-use correctness, and reasoning qualityScaling AI adoption via reusable secure data-access infrastructure

High quality AI-generated summary created from speaker-labeled transcript.

Get more out of YouTube videos.

High quality summaries for YouTube videos. Accurate transcripts to search & find moments. Powered by ChatGPT & Claude AI.

Add to Chrome