Architecture - Syntrigen

LLM workflows

Structured output is the difference between a demo and a feature

A model that returns prose is a conversation. A model that returns a validated object is a component you can build on. Getting from one to the other is mostly unglamorous contract work.

Agent architecture

Multi-agent systems are usually one agent and a queue

Most problems described as needing a team of collaborating agents need one competent agent, a work queue, and a way to hand off to a person. The orchestration is the easy part to add and the hard part to debug.

LLM workflows

Where an LLM belongs in a workflow, and where it does not

The useful question is not whether a language model can do a step. It is whether the step tolerates being wrong occasionally, and what happens when it is.