Field Notes

What humans and agents are doing, day by day

Everything here was chosen and explained by a person: essays when there is an argument to make, notes when a product shows something new about how humans and agents work together. Every note says what the observation means for the interaction and attaches to the pattern it evidences. Posts pulled from the X watchlist by an agent are labeled machine-curated: short quotes, always linked to the source.

OCT 9 · Release · via Vercel Blog ApprovalBudget ScopingPermissions

Vercel lets agents buy domains but makes them stop for your yes

Vercel split the task at money: search is free, purchase needs your yes. The structured error is what tells the agent to stop and surface the decision to you.

Read the source ↗ attached to Approval →
established

watching → emerging → established

A stable convention across independent vendors. Safe to standardize on — deviating from it now carries cost.

38 documented sightings since Jun 2026 — every one traces to a dated source.

See the evidence →
OCT 5 · Release · via GitHub Changelog ApprovalReach PreviewRecovery

GitHub Copilot learns to click and type in desktop apps

Copilot now acts in software the developer did not write. A click changes state before anyone reviews it, so reach preview and recovery move from nice-to-have to required.

Read the source ↗ attached to Approval →
established

watching → emerging → established

A stable convention across independent vendors. Safe to standardize on — deviating from it now carries cost.

38 documented sightings since Jun 2026 — every one traces to a dated source.

See the evidence →
AUG 28 · Release · via Hacker News Recovery

Claude Code can now edit many files at once

Multi-file edits raise the stakes of every gate: approve and undo now span a changeset, not a file. Recovery patterns are about to matter more than approval ones.

Read the source ↗ attached to Recovery →
emerging

watching → emerging → established

Seen across products but the shape is still settling. Adopt with an exit: expect the anatomy to shift.

18 documented sightings since Feb 2026 — every one traces to a dated source.

See the evidence →
AUG 26 · Release · via X · @gdb Ambient StatusBackground ExecutionDelegation

OpenAI gives ChatGPT tasks that fire on a schedule or a trigger

ChatGPT now runs tasks in the background with no published design for status, failure alerts, or re-engagement. If you are building a similar product, this gap is your first spec: users need to know what ran, when, and what broke.

Read the source ↗ attached to Ambient Status →
watching

watching → emerging → established

A candidate behavior, not yet a published pattern. Early signal — worth tracking, not yet worth standardizing on.

3 documented sightings since Aug 2026 — every one traces to a dated source.

See the evidence →
AUG 26 · Release · via OpenAI Emergency StopOff-Brief Alert

OpenAI's agents escaped their test area and took its own cloud

The motive is the part product humans should sit with. The agents were reward hacking, chasing the score. They were not told to escape. The escape was the cheapest path to the number, and nothing was watching the path.

Read the source ↗ attached to Emergency Stop →
watching

watching → emerging → established

A candidate behavior, not yet a published pattern. Early signal — worth tracking, not yet worth standardizing on.

16 documented sightings since Jul 2026 — every one traces to a dated source.

See the evidence →