Advanced AI Engineering Workshop Series

Build agentic systems that hold up in production.

For experienced developers and engineering leaders. Three live engineering deep-dives: harnesses, agentic search and real-time voice. Each session covers design, trade-offs and performance, tested in production. You learn the engineering decisions, not the features of a tool. 3 hours, online, max 15 people.

Accuracy, evals, latency, infra

Agentic Search Engineering

Build agentic search with a coding agent. Set up the data and the evals first. Compare grep ranking, BM25 and vector search on e-commerce and finance datasets, and find where each one fails. Then scale to multi-hop queries across thousands of documents and long entity chains.

Live workshop
3 hours: engineering deep-dive + 30-minute open discussion on your systems · code-first · live online · max 15 people
November, date to be confirmed
Join the waitlist
Course
Coming later.

Rethink search

  • Why does search fail? Build the first-principles mental model that answers it, and use it on any search stack.
  • What if search is a set of agent actions, not a chunk-retrieve-rerank pipeline? Learn to design search as actions an agent can choose: list, search, inspect, localize.

What you will do

  • Compare static RAG with dynamic agentic search, and find when each one is the better choice
  • Configure the bridges as agent tools: grep, keyword (BM25), semantic and multi-vector search
  • Use Jev decision models to cut the agent's latency, for example as a fast reranker
  • Work with e-commerce and finance datasets
  • Set up evals and learn from failure traces