A one-page role system map
Map three AI components, shared memory, routines, contracts and autonomy boundaries for your role.
Applied Agentic AI Systems
Orchestrate agents. Prove they work. Run your role on them. Build multi-agent patterns, engineer their workflow graphs, measure their performance and operate them within explicit budgets, permissions and human gates.
Experienced GenAI usersIntermediate18.5 hours3 days · In person
01 / What you’ll build
Three running agent patterns
Build a pipeline, parallel fan-out and orchestrator–workers system on real work inputs.
Evaluation and operations evidence
Ship a golden set, regression result, permissions, approval gate, runbook and autonomy decision.
02 / Curriculum
- Map recurring responsibilities across memory, routines, reactive agents, an on-demand harness and governance.
- Choose three components and give each a contract covering its goal, inputs, output, constraints and definition of done.
- Build one component twice: first as a single agent, then as an orchestrator with two specialist agents.
- Compare quality, time and token use to decide whether the multi-agent design earns its complexity.
03 / Your instructor
Vincent Leow
Tech Lead, Neutral Trade. As a current tech lead and former DeFi protocol co-founder, he brings hands-on experience architecting, testing and operating production software systems.