Building an internal agent: Code-driven vs LLM-driven workflows

This article explores the distinction between LLM-driven and code-driven agent workflows, using the example of a Slack bot that sometimes mislabelled merged pull requests due to LLM non-determinism. The author describes how they added a "coordinator" configuration option that allows workflows to be run either by an LLM or by a deterministic Python script that has access to the same tools and virtual files.

Visit Original Article →