Build a Multi-Agent Research Team · 35 min · Python · LangGraph · asyncio

Market Analyst + Parallel Execution

Three agents defined but wired sequentially still take 3x as long as they need to -- the graph edges, not the agent code, are what decide whether parallelism actually happens.

Hiring signal: Getting real, verified concurrency out of a multi-agent graph -- not just assuming it happens because you used LangGraph -- is exactly the kind of detail that separates a system that's actually fast from one that only looks parallel in the architecture diagram.

What you will learn

Build the Market Analyst specialist (trends, adoption, competition)
Wire all 3 specialists as parallel fan-out edges from the Planner
Rate-limit concurrent API calls with asyncio.Semaphore and verify real parallelism with timing

Introduction

Third specialist, then the moment this course has been building toward: all 3 running at once, not one after another. Today you build the Market Analyst and wire the actual fan-out.

The Market Analyst: same mechanics, market-focused prompt

Reuses Lesson 4's _run_specialist helper with a focus instruction on trends, adoption data, and competitive landscape — no new mechanics, just the third application of a pattern you've now built twice.

Unlock the full lesson

You've read the first 2 sections. The rest of this lesson covers Wiring real fan-out, Verify it's actually parallel — don't just assume, Rate limiting: 3 simultaneous calls hit the same API limit, What You're Building — plus a hands-on lab, quiz, and project artifact.

Create a free account to unlock Phase 0 and Phase 1 of every course — no credit card.