Agent Engineering

9 interactive modules. Production-ready agent engineering — picks up where AI Agents Foundations ends. Free, browser-based.

HA
Module 1
Production Harness Architecture

Idempotency, checkpoints, retry policy, durable execution platforms — surviving crashes, deploys, and network failures.

Start module →
OB
Module 2
Observability for Agents

Span-per-tick traces, what to log, replay, golden metrics vs vanity, alerting on stochastic systems.

Start module →
GR
Module 3
Layered Guardrails

Defense-in-depth: input filters, output filters, policy enforcement, fail-safe vs fail-open.

Start module →
CL
Module 4
Cost & Latency Engineering

Where the tokens go, prompt caching, result caching, parallel tool calls, batching at the agent layer.

Start module →
PE
Module 5
Production Evals & Shadow Mode

Online vs offline evals, shadow traffic, A/B harness, drift detection, eval-driven rollout.

Start module →
DR
Module 6
Deployment & Rollout

Prompts as code, canary rollouts, rolling releases, version pinning, rollback discipline.

Start module →
IH
Module 7
Incident Handling

The first 15 minutes, trace replay in anger, root-cause discipline, postmortems, drills.

Start module →
AT
Module 8
Agent Teams

Multi-agent orchestration — when teams beat a single agent, supervisor/worker, voting, handoffs, coordination cost.

Start module →
RO
Module 9
Capstone — Reliability Operations

SLOs, error budgets, on-call rotations, runbooks. From Foundations to running an agent fleet.

Start module →