Agentic Architecture & Orchestration
7 build exercises to practise the concepts in this domain.
1.1 — Build a Multi-Tool Agent Loop
Intermediate
45 minutes
- How the agentic loop lifecycle works with the Messages API
- Why stop_reason is the authoritative signal for loop control
- How to handle tool_use and end_turn stop_reason values correctly
- How to append tool results to conversation history for multi-turn execution
- When safety iteration caps are appropriate versus inappropriate as stopping mechanisms
1.2 — Build a Hub-and-Spoke Research Coordinator
Intermediate
60 minutes
- How hub-and-spoke architecture centralises all communication through a coordinator
- Why subagent isolation means every piece of context must be explicitly passed
- How to implement broad task decomposition that avoids the narrow decomposition failure
- How iterative refinement loops detect and fill coverage gaps
- Why tracing failures to the coordinator decomposition is the correct diagnostic approach
1.3 — Implement Context Passing with Structured Metadata
Intermediate
50 minutes
- Why the coordinator allowedTools must include Task to spawn subagents
- How to design structured metadata that separates content from source attribution
- Why context passing failures cause attribution errors in downstream agents
- How to spawn independent subagents in parallel for reduced latency
- The difference between fork_session and parallel Task invocation
1.4 — Build a Prerequisite Gate for Financial Operations
Advanced
60 minutes
- Why programmatic enforcement is required for financial operations instead of prompt-based guidance
- How prerequisite gates physically block tool execution until preconditions are met
- The difference between the 8% prompt failure rate and 0% gate failure rate
- How to implement structured handoff protocols with all required fields
- How multi-concern requests should be decomposed and handled in parallel
1.5 — Implement Agent SDK Hooks for Normalisation and Policy Enforcement
Advanced
60 minutes
- The distinction between PostToolUse hooks (after execution, data normalisation) and tool call interception (before execution, policy enforcement)
- Why hooks provide deterministic guarantees that prompts cannot match
- How to normalise heterogeneous data formats from multiple MCP tools into a consistent schema
- How to implement threshold-based and prerequisite-based policy enforcement using pre-execution hooks
- The decision framework: hooks for 100% requirements, prompts for preferences
1.6 — Build a Multi-Pass Code Review Pipeline
Advanced
60 minutes
- Why attention dilution produces inconsistent analysis depth across files in single-pass reviews
- How multi-pass architecture (per-item + cross-item) solves the structural attention allocation problem
- The difference between fixed sequential pipelines and dynamic adaptive decomposition
- Why batching without a cross-file integration pass still misses cross-cutting issues
- How to identify attention dilution artefacts: same pattern flagged in one file, approved in another
1.7 — Implement Session Management Strategies
Intermediate
45 minutes
- The three session management options: resume, fork_session, and fresh start with summary injection
- Why resuming after file changes leads to the stale context problem
- How structured summary injection preserves knowledge without stale tool results
- When targeted re-analysis is more efficient than full re-exploration
- The difference between fork_session (divergent exploration) and resume (continuation)