AI observability as the engine of production-ready AI

Samuel Jaja, Generative AI Engineer at Capgemini UK, brings a talk grounded in a real multi-agent financial compliance system to Leeds Sharp on Thursday 21 May 2026. The case study is a five-agent pipeline handling OFAC sanctions screening, AML detection and regulatory rules enforcement — every agent decision captured in an immutable Langfuse audit trail showing token usage, latency, cost and data lineage in real time.

The talk walks through three architecturally distinct ways to build the same system: raw SDK with custom parallel orchestration via asyncio; the OpenAI Agents SDK for rapid prototyping; and MCP (Model Context Protocol) for exposing tools across team and organisational boundaries. Each approach trades differently, and the talk is explicit about when to reach for which. Attendees will leave with a working mental model for when multi-agent architecture is genuinely necessary, why observability is the feedback loop that compresses build-debug-ship cycles, and how Azure OpenAI changes the calculus when data sovereignty and auditability matter in regulated industries.

The format is a single talk with a 6pm arrival for pizza and drinks, talk starting at 7pm, wrapping by 8pm. Some attendees head to the Editor's Draft pub afterwards — venue vote taken on the night.

Leeds Sharp is a .NET user group that has been running in Leeds for several years. It draws engineers working across the Microsoft stack, though talks like this one pull in a wider audience interested in AI architecture and production systems. Sponsors include Fruition Group, JetBrains and tronik ecommerce consultants.

Why attend

The case study here is not a toy. It is a production-grade, multi-agent compliance pipeline in a regulated industry, with real observability tooling (Langfuse) and real architectural trade-offs laid out in the open. If you are building or evaluating AI systems at work, this is the kind of talk that gives you something concrete to take back.

Samuel Jaja founded PyData Hull, spoke at DDD North 2026 and holds an MSc in AI and Data Science with Distinction from the University of Hull. He builds across finance, energy and construction. The crowd at Leeds Sharp tends to be working engineers rather than spectators, so the post-talk conversation is usually worth staying for.

Agenda

• 18:00 — Doors open, pizza and drinks at Enablis
• 19:00 — Talk: From Black Box to Glass Box: Systems Thinking & Observability as the Engine of Production-Ready AI — Samuel Jaja
• 20:00 — Close; optional drinks at the Editor's Draft pub (vote taken on the night)

Speakers

• Samuel Jaja — Generative AI Engineer at Capgemini UK; founder of PyData Hull (youngest NumFOCUS chapter in Yorkshire) and Atlasync AI Ltd; MSc AI and Data Science with Distinction, University of Hull; speaker at DDD North 2026.