Advanced · 6 weeks
Advanced — Agents & Evals
A deep, 6-week program on building production-grade agentic systems with rigorous eval pipelines. Prerequisite: Practitioner level or equivalent.
฿58,000 Enroll now
Who it’s for
You build for a living and you’ve shipped at least one AI feature to production. You want to go deep on the two hardest problems: agentic loops and evaluation at scale.
Format
- 6 weeks, ~8 hours per week
- Twice-weekly live sessions
- Mandatory shipping by week 4 — the second half of the cohort is hardening the system you built
- Pair you with a lab mentor for the duration
Curriculum
- Week 1 — Agent loops: planning, tool use, recovery
- Week 2 — Memory and context window discipline
- Week 3 — Multi-agent: when it helps, when it hurts
- Week 4 — Eval pipelines: building a harness that catches regressions
- Week 5 — Observability: tracing, drift detection, alerting
- Week 6 — Productionization: cost, latency, safety, rollout