Section guide
Hands-On Labs
Practical implementation paths and vertical slices.
Use when you want implementation practice and vertical slices.
Leave with runnable examples and a production gap list for each pattern you try.
A runnable slice with test evidence and a missing-production-controls list.
Reading order
18 chapters- 01 Lab Guide Lab · Hands-on 45-90 min lab Builder · Student
The lab guide explains how to use runnable examples to connect patterns to code, tests, traces, and production gaps.
- 02 Framework and Language Matrix Lab · Hands-on 45-90 min lab Builder · Student
The framework and language matrix maps each lab to its language, framework style, runtime concern, and expected evidence.
- 03 Lab Production Readiness Checklist Lab · Hands-on 45-90 min lab Builder · Student
The lab checklist helps turn working demos into production candidates by naming the missing controls, evals, traces, and runbooks.
- 04 01 - Tool-Using Agent Lab · Hands-on 45-90 min lab Builder · Student
Lab 01 builds the smallest useful tool boundary: validate a proposed call, execute through code, label trust, and return structured results.
- 05 02 - Agent Loop and Planning Lab · Hands-on 45-90 min lab Builder · Student
Lab 02 separates planning from execution so the planner proposes steps while bounded code runs operations and records results.
- 06 03 - Agentic RAG Lab · Hands-on 45-90 min lab Builder · Student
Lab 03 builds an Agentic RAG boundary with scoped retrieval, grounded answers, and refusal or escalation when evidence is weak.
- 07 04 - A2A Communication Lab · Hands-on 45-90 min lab Builder · Student
Lab 04 builds typed agent-to-agent messages with correlation IDs, acceptance, refusal, errors, and cancellation states.
- 08 05 - Multi-Agent Supervisor Lab · Hands-on 45-90 min lab Builder · Student
Lab 05 builds a supervisor shape where one coordinator owns the goal, delegates bounded work, merges outputs, and produces the final answer.
- 09 06 - Observability and Evals Lab · Hands-on 45-90 min lab Builder · Student
Lab 06 adds trace data, regression tasks, expected outcomes, and trajectory checks to evaluate behavior beyond final answers.
- 10 07 - Mastra Runtime Packaging Lab · Hands-on 45-90 min lab Builder · Student · Operator
Lab 07 packages agents, tools, workflows, memory, trace events, and evals in a Mastra-style TypeScript runtime shape.
- 11 08 - CrewAI Flows and Crews Lab · Hands-on 45-90 min lab Builder · Student
Lab 08 uses a CrewAI-style Python shape to separate flow ownership from specialist crew collaboration.
- 12 From-Scratch Mini-Framework Track Lab · Hands-on 45-90 min lab Builder · Student
The from-scratch track builds a minimal agent runtime so engineers can see the framework ideas without framework magic.
- 13 09 - Minimal Agent Loop Lab · Hands-on 45-90 min lab Builder · Student
Lab 09 builds a minimal loop that receives a goal, asks for a typed decision, updates state, and stops for an explicit reason.
- 14 10 - Tool Registry and Policy Gate Lab · Hands-on 45-90 min lab Builder · Student · Security
Lab 10 extends the mini-runtime with a tool registry and policy gate so software decides whether a proposed tool call may run.
- 15 11 - Context, Memory, Trace, and Evals Lab · Hands-on 45-90 min lab Builder · Student
Lab 11 makes the mini-runtime inspectable with context packets, scoped memory reads, trace events, and trajectory evals.
- 16 12 - LangGraph State Graph Lab · Hands-on 45-90 min lab Builder · Student
Lab 12 models LangGraph-style state graphs with explicit state, nodes, edges, checkpoints, interrupts, and resume behavior.
- 17 13 - AutoGen Transcript Evals Lab · Hands-on 45-90 min lab Builder · Student
Lab 13 evaluates AutoGen-style team transcripts so multi-agent collaboration has reviewable messages, turn order, and stop reasons.
- 18 Vertical Slice Examples Lab · Hands-on 45-90 min lab Builder · Student
Vertical Slice Examples show how to combine patterns into small product workflows with clear runtime and evidence boundaries.