Build a Research Agent with Tool Delegation
Orchestrator, supervisor, and swarm patterns for multi-agent systems with real trade-offs and failure modes.
Build: Build a Research Agent with Tool Delegation
A guided implementation with code you can run and adapt for production.
Reading Multi-Agent Architecture is free. Pro unlocks the other four modes on all AI Engineering topics, so you can go from understanding it to building it.
Helps to know first
- SeeThe architecture as diagrams, so you can hold the whole system in your head.
- AnimateStep through the flow one stage at a time and watch the data move.
- TestScenario questions with explanations that show exactly where your model of it breaks.
- BuildA guided implementation with code you can run and adapt for production.
Continue reading
All Agentic Systems articles →Agent Skills: Knowledge That Loads on Demand
Stop growing your system prompt. How SKILL.md folders and progressive disclosure work, how to write a description that fires, and when a skill beats a tool or an MCP server.
Durable Agents and Sandboxing: Surviving the Crash
Checkpoints do not make a side effect safe. Idempotency keys, the interrupt replay trap, choosing a runtime, and the isolation and egress rules that contain generated code.
Harness Engineering: Everything Around the Model
Long-running agents fail in the code around the model. Clean sessions, progress on disk, a task list that starts failing, and checks the agent cannot talk its way past.
Discussion
Sign in to share your feedback and join the discussion.