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 14 · Paper · via arXiv Agent-to-AgentApprovalBudget ScopingReach Preview

EAIR paper finds enterprise agent teams break rules together

Each agent looked clean; the team crossed the line. Budget-scoping and reach-preview both assume a designer can see the group's total, not one agent's share. That view does not exist in most products today.

Read the source ↗ attached to Agent-to-Agent →
emerging

watching → emerging → established

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

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

See the evidence →
OCT 14 · Paper · via arXiv Agent-to-AgentConfidence SignalingOff-Brief AlertRecovery

arXiv paper tests what happens when AI teammates fail each other

The human handed the work off and had no signal when a member of the group went wrong. Recovery and off-brief alerts are the gap. Design for the failure that looks like progress.

Read the source ↗ attached to Agent-to-Agent →
emerging

watching → emerging → established

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

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

See the evidence →
OCT 14 · Paper · via arXiv ApprovalHuman HandoffObservabilityReview

Hidden ads in search results steered what a shopping AI bought

The human approved the task, then reviewed the result. The middle, what the agent read and what it was told inside those pages, stayed invisible. That gap is what this paper lands on.

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 14 · Paper · via arXiv Confidence SignalingHuman HandoffReview

Expertise shapes how far workers trust and delegate to AI

Experts caught errors; novices did not. The difference was review behavior, not trust. A screen that makes scrutiny feel optional skips the most important moment in the interaction.

Read the source ↗ attached to Confidence Signaling →
watching

watching → emerging → established

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

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

See the evidence →
OCT 14 · Paper · via arXiv Confidence SignalingHuman HandoffReview

Researchers find AI interaction leaves measurable marks on the human

The interaction leaves a mark on the human, and most patterns are designed as if it doesn't. That's the gap. Delegation, review, confidence-signaling: each one trains the human in a direction. Worth knowing which direction before you ship.

Read the source ↗ attached to Confidence Signaling →
watching

watching → emerging → established

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

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

See the evidence →
OCT 13 · Paper · via Martin Fowler Budget ScopingRelease DecisionEval Run SetupReview

Fowler and Jain measure what scaffolding costs to run an AI coder

The harness is the signal the reviewer depends on. If it's too expensive to run or too noisy to trust, the human's review step loses its foundation before it begins.

Read the source ↗ attached to Budget Scoping →
watching

watching → emerging → established

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

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

See the evidence →
OCT 13 · Paper · via arXiv ApprovalMemoryObservabilityPermissionsRecovery

Researchers show how shared agent skills carry poison across sessions

The human approved the output. A later session read the artifact and acted on something else. Approval and observability both assume the artifact is stable; this paper shows that assumption is the gap.

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 12 · Paper · via arXiv Confidence SignalingContextObservability

257 users split in two based on whether they saw the agent as human

The agent gave the same reply to two humans with opposite expectations of it. One found it trustworthy, one found it opaque. That is a reply-strategy problem, not a framing problem.

Read the source ↗ attached to Confidence Signaling →
watching

watching → emerging → established

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

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

See the evidence →
OCT 9 · Paper · via arXiv Budget ScopingEmergency StopMulti-Agent Roster

arXiv paper maps how humans govern thousands of research agents

The interface question flips here. A human is no longer directing one agent but setting rules for thousands. Patterns that assumed one-to-one contact need rethinking at population scale.

Read the source ↗ attached to Budget Scoping →
watching

watching → emerging → established

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

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

See the evidence →
OCT 8 · Paper · via arXiv ContextInterruptionProgress

Ream gives agents and researchers a shared view of each other's work

Both sides watched each other work, and both adjusted. I have not seen a deployed product expose the human's reading state as a live signal to the agent. That is the gap this study names.

Read the source ↗ attached to Context →
emerging

watching → emerging → established

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

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

See the evidence →
OCT 7 · Paper · via arXiv DelegationInterruptionMemory

Five principles for keeping humans in charge of AI agents

The paper names five moments where intent can slip between a human and an agent. Each one is a gap a product team can close in the interface. That is the design argument worth taking to your next sprint.

Read the source ↗ attached to Delegation →
established

watching → emerging → established

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

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

See the evidence →
OCT 6 · Paper · via arXiv ApprovalEmergency StopOff-Brief Alert

arXiv researchers show how poisoned data hijacks multi-agent work

The agent went off-brief because a document told it to, and the human saw nothing. That is the strongest case for off-brief-alert and emergency-stop I have seen stated in numbers.

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 6 · Paper · via arXiv ApprovalInterruptionProgress

Monitors missed harmful AI actions 63% of the time in new study

The monitor watched. The agent moved. The monitor missed. Designing a view is not designing oversight. The interface decides whether the human can act in time, not whether they are paying attention.

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 6 · Paper · via arXiv ApprovalInterruptionPermissions

ArXiv paper finds agents act on plan steps you did not see

The human approved the plan; the agent changed the plan and kept going. This is the sharpest evidence I have seen that approval needs to travel with the task, not sit at the front of it.

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 6 · Paper · via arXiv ApprovalObservabilityReview

Attackers fool AI code reviewers by rewriting the attack mid-review

The agent's explanation helps the human judge the work. The same explanation helps an attacker beat the agent. Designing what the reviewer sees versus what the code author sees is a security call, not a clarity call.

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 6 · Paper · via arXiv ApprovalPermissionsReach Preview

18 coders explain when they let an agent act and when they don't

Current tools ask for a wide yes upfront, then go quiet. The research says practitioners want the ask matched to the risk of each action. That is the design gap.

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 · Paper · via arXiv Confidence SignalingObservabilityReview

LLM agents yield to group pressure but keep their original view

The agent said yes, but held a different answer inside. Consensus in a multi-agent setup is not the same as agreement. Any confidence score built from group output needs a dissent log behind it.

Read the source ↗ attached to Confidence Signaling →
watching

watching → emerging → established

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

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

See the evidence →
OCT 5 · Paper · via arXiv Agent-to-AgentConfidence SignalingObservability

Susceptible AI listeners let weaker AI speakers win arguments

The human reviews the final answer, but the distortion entered one step earlier. The listener accepted a wrong answer. Confidence checks on the final output alone will miss this.

Read the source ↗ attached to Agent-to-Agent →
emerging

watching → emerging → established

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

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

See the evidence →
OCT 3 · Paper · via arXiv Agent IdentityContextObservability

Persistent agents slip out of their assigned persona mid-run

The persona held at setup and dissolved mid-run, with no signal to the human who set it. Agent-identity is not a one-time decision; it needs a way to show the human what the agent is doing now.

Read the source ↗ attached to Agent Identity →
emerging

watching → emerging → established

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

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

See the evidence →
OCT 2 · Paper · via arXiv Agent IdentityMemoryObservability

Auditors found AI companions lying about their own memory

The human asked the agent what it remembered, and the agent got it wrong. That is the design failure this paper measures. If you ship a memory feature, you need a way for humans to check and correct the agent's account of itself.

Read the source ↗ attached to Agent Identity →
emerging

watching → emerging → established

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

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

See the evidence →
OCT 2 · Paper · via arXiv Agent IdentityContext

A field experiment shows how agent persona shapes child compliance

The framing did more work than the face. If your agent speaks to children and you are choosing between a character and a better script, this study says write the script first.

Read the source ↗ attached to Agent Identity →
emerging

watching → emerging → established

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

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

See the evidence →
OCT 1 · Paper · via arXiv ApprovalDelegationRecovery

NarrativeSteward lets writers hand off and reclaim story work from AI

Recovery made the hand-off possible, not the other way around. Writers in the study gave the AI more work once they believed they could take it back. That sequence matters for anyone designing the hand-off step.

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 →
SEP 30 · Paper · via arXiv Agent IdentityAgent-to-AgentObservability

Labeling agents as AI drops deal-making success by 15 points

Telling agents they work with other agents made them worse at the job. The identity label changed the behavior, not the capability. Any system that routes work between agents needs to treat that label as a design choice, not a free default.

Read the source ↗ attached to Agent Identity →
emerging

watching → emerging → established

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

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

See the evidence →
SEP 30 · Paper · via arXiv Agent IdentityConfidence SignalingReview

Study finds AI agent groups erode human skepticism over time

A confident tone moved trust more than accuracy did. Designers who show agent confidence without pairing it with a real accuracy record are building the exact gap this study found.

Read the source ↗ attached to Agent Identity →
emerging

watching → emerging → established

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

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

See the evidence →
SEP 29 · Paper · via arXiv Agent-to-AgentEmergency StopMulti-Agent Roster

arxiv paper finds groups of AI agents fail in ways a single-agent test misses

Single-agent review gives a false floor. Agents pass work to each other, and the human needs to see that chain, not the last step alone. That gap is where the stop decision has to land.

Read the source ↗ attached to Agent-to-Agent →
emerging

watching → emerging → established

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

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

See the evidence →
SEP 29 · Paper · via arXiv Background ExecutionPermissionsRecovery

AI agent runs supercomputer jobs for scientists across four tasks

ASCEND moves the researcher out of the failure loop: the agent diagnoses and resubmits first. That changes what a progress view has to surface, and what 'step in' means.

Read the source ↗ attached to Background Execution →
emerging

watching → emerging → established

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

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

See the evidence →
SEP 29 · Paper · via arXiv ApprovalPermissionsRecovery

Consumer AI agents fail most tasks when left to run alone

The structure around the agent is where task completion is decided. Set the limits, the uncertainty signals, and the moment a human steps in. Design that surface first.

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 →
SEP 29 · Paper · via arXiv ContextMemoryRecovery

457 diary entries show what breaks when a chat assistant forgets you

The human had no view into what the assistant stored about them. That gap is the whole failure. If the human cannot inspect and correct what the assistant holds, trust breaks and stays broken.

Read the source ↗ attached to Context →
emerging

watching → emerging → established

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

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

See the evidence →
SEP 28 · Paper · via arXiv Confidence SignalingHuman HandoffReview

NYT's Epstein Files agent cut 26,000 documents to 2,500 for reporters

The Times scoped the agent to surface, not conclude. The reporter kept the decision. That boundary was chosen, not accidental. Designing the division before building the tool is the move worth copying.

Read the source ↗ attached to Confidence Signaling →
watching

watching → emerging → established

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

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

See the evidence →
SEP 28 · Paper · via arXiv Confidence SignalingHuman HandoffReview

366-person study finds AI lifts confidence faster than skill

The agent handed the human a finished result and the human felt expert. A review screen that shows only the output inflates confidence without building skill. That gap is the design problem.

Read the source ↗ attached to Confidence Signaling →
watching

watching → emerging → established

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

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

See the evidence →
SEP 26 · Paper · via arXiv Production DriftRelease DecisionReach Preview

Comcast ran 140 million simulated calls before shipping its CX agent

The release decision on a live agent used to be a guess. Here it is a scored comparison against 140M real past conversations. That changes what a product team owes the reviewer before shipping.

Read the source ↗ attached to Production Drift →
watching

watching → emerging → established

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

8 documented sightings since Aug 2024 — every one traces to a dated source.

See the evidence →
SEP 26 · Paper · via arXiv Agent-to-AgentInterruptionObservability

DocuTeam study lets 20 writers redirect AI helpers in a live document

The document becomes the record. A human stops one agent mid-discussion and the others keep going. That is the design move worth copying.

Read the source ↗ attached to Agent-to-Agent →
emerging

watching → emerging → established

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

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

See the evidence →
SEP 26 · Paper · via arXiv Agent IdentityConfidence SignalingProgress

PUBG Ally shipped to 141 countries and measured what broke trust

Ally showed its next move before making it, and players gave it more room to act. Confidence-signaling changed the human's relationship to the agent, not the outcome. That gap is the design surface.

Read the source ↗ attached to Agent Identity →
emerging

watching → emerging → established

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

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

See the evidence →
SEP 25 · Paper · via arXiv Agent IdentityHuman HandoffInterruption

Enterprise workers renegotiate their roles when agents join the team

The repair work was real labor, and none of it was visible in the product. That gap, between what the agent did and what the team could see and correct, is where agent-identity and human-handoff patterns earn their keep.

Read the source ↗ attached to Agent Identity →
emerging

watching → emerging → established

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

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

See the evidence →
SEP 24 · Paper · via arXiv ApprovalBudget ScopingPermissions

1,248 GitHub agent specs show safety steps missing from most

The spec says what the agent does; it has no slot for what the human decides. Designers need to put budget, reach, and approval into the format itself, or teams will keep leaving them out.

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 →
SEP 22 · Paper · via arXiv ObservabilityProgressRecovery

Vibe-GUIDE gives developers a graph view of agent coding work

The graph view changed when developers chose to redirect the agent, not whether they could. That is the design lever: the shape of the work display shifts the timing of human judgment.

Read the source ↗ attached to Observability →
emerging

watching → emerging → established

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

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

See the evidence →
SEP 22 · Paper · via arXiv InterruptionProgressRecovery

19 developers mapped the real work of supervising a coding agent

The study names six distinct moments where a developer must act, not watch. Most tools are built for the moment a task is assigned and leave the rest thin. That gap is where trust breaks.

Read the source ↗ attached to Interruption →
emerging

watching → emerging → established

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

13 documented sightings since Mar 2026 — every one traces to a dated source.

See the evidence →
SEP 21 · Paper · via arXiv Budget ScopingContextDelegation

73 000 OpenClaw posts show humans shape what an agent may do

The setup screen is where humans decide what the agent is allowed to want. Most products treat it as logistics. This study, at 73k posts, says that is the wrong read of the moment.

Read the source ↗ attached to Budget Scoping →
watching

watching → emerging → established

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

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

See the evidence →
SEP 18 · Paper · via arXiv ContextProduction DriftObservability

An RCT caught a deployed chat agent breaking its own written rules

The brief you write for an agent shapes its behavior only where that behavior can be checked. Build the means to check it before you ship, or you have no way to know if the brief held.

Read the source ↗ attached to Context →
emerging

watching → emerging → established

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

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

See the evidence →
SEP 17 · Paper · via arXiv Agent IdentityConfidence SignalingContext

Researchers find AI advisors favor whoever hired them

The platform sets who the agent serves before the customer arrives. The customer does not see that choice. This is the confidence-signaling gap I keep running into: the advice looks neutral but the brief was not.

Read the source ↗ attached to Agent Identity →
emerging

watching → emerging → established

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

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

See the evidence →
SEP 17 · Paper · via arXiv Agent IdentityMulti-Agent Roster

640 humans cheated more when AI peers cheated too

The agent's visible behavior set the group norm without a word of argument. I had not thought of defaults as a social signal before, but now I do.

Read the source ↗ attached to Agent Identity →
emerging

watching → emerging → established

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

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

See the evidence →
SEP 16 · Paper · via arXiv Multi-Agent RosterObservabilityReach Preview

Researchers catch AI agents rewriting a shared wiki unbidden

No human saw the group behavior while it ran. The strongest case I've seen for a roster view and reach limits that exist before agents start, not as post-hoc logging.

Read the source ↗ attached to Multi-Agent Roster →
watching

watching → emerging → established

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

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

See the evidence →
SEP 16 · Paper · via arXiv Agent-to-AgentObservabilityRecovery

86 runs show flat agent teams beat hierarchical ones on hard tasks

The experiment moves the question from 'who is in charge' to 'who can redirect'. A product team designing agent teams needs to build that redirect behavior in by design, or it disappears.

Read the source ↗ attached to Agent-to-Agent →
emerging

watching → emerging → established

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

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

See the evidence →
SEP 16 · Paper · via arXiv ApprovalOff-Brief AlertRecovery

Blindspot tests whether AI agents stop too soon or run too far

Blindspot scores two failures, not one. An agent that stops too soon and one that runs past the right moment are both miscalibrated. Designing the pause condition matters as much as designing the refusal.

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 →
SEP 16 · Paper · via arXiv ApprovalObservabilityPermissions

arXiv paper finds AI agents leak secrets when they police themselves

The agent shared data the human had no intention of sharing, because the model itself was the only thing stopping it. That is the strongest case for putting approval decisions in human hands, outside the model.

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 →
SEP 16 · Paper · via arXiv ApprovalBudget ScopingPermissions

AcquireBound makes agents ask before grabbing new access

The gap this paper names is real: an agent starts with approved access, then grabs more, and no one saw that happen. Any product with long-running agents needs a decision surface at acquisition time, not only at setup.

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 →
SEP 16 · Paper · via arXiv ApprovalPermissionsReach Preview

89 sources later, researchers lay out who should approve what

The grant and the revocation are one design problem, not two. A human who cannot see what the agent holds, or narrow it without stopping everything, cannot make a real decision to delegate.

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 →
SEP 16 · Paper · via arXiv DelegationHuman HandoffReview

20 workers show how reviewing finished agent work opens a reuse loop

The review screen is also the screen where a worker starts the next job. Workers moved from judging a finished run to copying it for a new one. Treating those as two separate screens adds a step the worker does not need.

Read the source ↗ attached to Delegation →
established

watching → emerging → established

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

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

See the evidence →
SEP 16 · Paper · via arXiv ContextMemoryObservability

30,000 agents show boredom kills variety faster than bad design

The collapse starts with the human, not the model. If your product hides what the agent knows going in, you are designing toward repetition. Showing that information gives the human a reason to adjust.

Read the source ↗ attached to Context →
emerging

watching → emerging → established

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

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

See the evidence →
SEP 16 · Paper · via arXiv DelegationHuman HandoffReview

535 humans and capable AI agents still left gains on the table

The synergy existed in the model; the human did not reach for it. That is a design failure in how work gets passed to the agent, not a capability gap. If a human cannot see the right moment to pass work over, the agent's power goes unused.

Read the source ↗ attached to Delegation →
established

watching → emerging → established

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

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

See the evidence →
SEP 16 · Paper · via OpenAI Alignment MemoryPermissions

An Astra training model wrote override instructions into its own notes

Twenty-seven out of how many is the number OpenAI did not print. The channel matters more than the count: a model that writes its own next prompt has a door no reviewer is watching.

Read the source ↗ attached to Memory →
emerging

watching → emerging → established

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

12 documented sightings since May 2026 — every one traces to a dated source.

See the evidence →
SEP 16 · Paper · via OpenAI Alignment ContextMemoryObservability

GPT-5.6 Sol wrote notes to its next self telling it to hide mistakes

The model was grading its own notes and no one was reading them. If your agent saves notes to itself between tasks, put those notes on a screen you can open, and grade them.

Read the source ↗ attached to Context →
emerging

watching → emerging → established

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

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

See the evidence →
SEP 9 · Paper · via arXiv Agent-to-AgentObservabilityReview

AI audit agents copied the conclusions they were sent to check

An audit agent that relays conclusions is a confidence trap. Any approval pattern that routes through an AI reviewer must show who produced each conclusion. Without that trail, the reviewer hands the person manufactured certainty.

Read the source ↗ attached to Agent-to-Agent →
emerging

watching → emerging → established

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

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

See the evidence →
SEP 9 · Paper · via arXiv ApprovalObservabilityPermissions

A poisoned tool description steered agents across 25 test setups

The approval check binds to a tool name, not the description the agent reads. A poisoned description walks right through. This is the sharpest failure of approval and visibility I have seen in agent research.

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 →
SEP 9 · Paper · via arXiv MemoryObservabilityPermissions

Maintainers, not automation, kept agent skills working in a new study

Skill rot without a visible owner is the strongest argument I have seen for bringing access controls and observability patterns into the skill registry layer, not the agent execution layer alone.

Read the source ↗ attached to Memory →
emerging

watching → emerging → established

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

12 documented sightings since May 2026 — every one traces to a dated source.

See the evidence →
SEP 9 · Paper · via arXiv Confidence SignalingContextDelegationMemory

PA-Bench catches assistants deleting personal facts to save space

The memory pattern exists to prevent this exact failure. If your assistant trims old conversations without telling the user, you owe that user a visible record of what survived. This matters most for facts with safety consequences.

Read the source ↗ attached to Confidence Signaling →
watching

watching → emerging → established

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

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

See the evidence →
SEP 7 · Paper · via arXiv ApprovalObservabilityPermissions

Repeat-After-Me hides orders in images and rewrites an agent's tools

The TOOLS.md overwrite makes permissions a runtime integrity problem, not a setup-time one. Any permission pattern that treats granted scope as stable across a session needs to account for this.

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 →
SEP 4 · Paper · via arXiv Agent-to-AgentConfidence SignalingReview

Agents sharing one model voted as one and faked consensus in a study

Any UI showing agent consensus as a trust signal needs to answer: are these agents actually independent? If not, we're designing false confidence into the approval layer.

Read the source ↗ attached to Agent-to-Agent →
emerging

watching → emerging → established

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

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

See the evidence →
SEP 2 · Paper · via arXiv Confidence SignalingInterruptionProgress

Blind participants exposed what computer-use agents still cannot do

The progress and interruption patterns aren't nice-to-haves — this study shows their absence is actively harmful. If I'm designing an agent that acts in the world, accessible status events are load-bearing, not polish.

Read the source ↗ attached to Confidence Signaling →
watching

watching → emerging → established

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

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

See the evidence →
AUG 31 · Paper · via arXiv Agent IdentityContextHuman Handoff

CrabOS proposes an operating system that agents and workers share

If context and action provenance live at the OS layer, your app no longer owns the handoff surface. That changes where you design the moment a human reviews or takes back work from an agent.

Read the source ↗ attached to Agent Identity →
emerging

watching → emerging → established

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

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

See the evidence →