Member-only story
Building Dynamic Workflows: A New Agentic System
A lead model writes the plan as a short checked program, and plain Python runs it with parallel workers
34 min readOct 19, 2026
Read this story for free: link
Most multi-agent systems work in one of two ways. A lead agent calls helpers one at a time and waits on every report, or an engineer hard-codes a pipeline that runs the same steps for every job. A newer approach, dynamic workflow introduced by Anthropic, lets the lead write the whole plan once as a short program, and plain code runs it with many workers in parallel.
Here is the architecture we are going to build, one component at a time:
- A benchmark: 72 planted bugs and a scorer that checks findings against a hidden key.
- An answer ledger: caching, replay and crash recovery.
- A runtime: workers that run in parallel phases under one budget.
- An audit kit: scan workers, and skeptics that vote on what they find.
- A plan language: restricted Python, checked before it can spend.
- The lead: it reads a 500-token fact sheet instead of the code.
- An evaluation: five designs and an ablation.
