Cohort 3

Consultant

Hendrik Reh

Build LLM-powered software reliably & from first principles. Learn the GenAI software development lifecycle: agents, evals, iteration & more

Hugo Bowne-Anderson

Host of Vanishing Gradients podcast; ex-Outerbounds; expert in DS/ML.

Stefan Krawczyk

Agentforce; Ex-Stitch Fix; 13+ Years building / productionizing data, ML, Agents

Building LLM Applications for Data Scientists and Software Engineers

Hugo & Stefan

<h3>Why I enrolled</h3>
1. Challenge My Current ApproachI’ve built a multi-agent RFQ system using Pydantic-AI and DeepEval. Now, I want to pressure-test those concepts to see what holds up and what needs rethinking.2. Re-educate and RefactorI’ve taken my first steps in architecting LLM-powered systems. Now I’m here to:<ul class="list-disc ml-8"><li>compare notes with experienced practitioners</li><li>adopt reusable design scaffolds for conversation state, tool routing, fallback handling, and evaluation</li><li>evolve from smart PoCs to robust, production-grade agents for real-world B2B use cases like quoting, pricing, and support automation</li></ul>3. Contribute, Collaborate, and Level UpI’m not just here to learn. I’m here to build with others.I want to collaborate with fellow AI engineers (not just prompt tinkerers), exchange code-level feedback, and find strategic sparring partners to help push agentic systems into production.



<h3>What I’ll apply</h3>
I’ll definitely start treating evals as part of the actual SDLC - not some afterthought once the app is “done.” I’ve already started wiring up basic test sets, trace logging, and cost tracking into my GenAI projects so I’m not flying blind. Also, I’ll skip the temptation to reach for fancy agent frameworks unless there’s a clear need.

Hendrik Reh

Has completed Building LLM Applications for Data Scientists and Software Engineers with Hugo Bowne-Anderson, Stefan Krawczyk

Certificate

Course Info