01 Designing how humans and agents work together

The agents act. The humans set the terms.

29 patterns now describe how that works in shipping products, from Claude Code to Codex and ChatGPT. Four have settled. Eight are picking up this month.

Agents & Humans counted 199 sightings of them in the last 30 days, recorded in daily field notes, and names the patterns that hold in essays.

FIG. 0 · THE STATE OF THE FIELD 29 PATTERNS · SIGHTINGS IN THE LAST 30 DAYS · AS OF OCT 23, 2026 0 10 20 30 40 HANDOFFSUNDERSTANDINGDECISIONSTRUSTCONTEXTMANY AGENTSSURFACES Observability 16 IN 30 DAYS · STEADY Approval 26 IN 30 DAYS · STEADY Review 14 IN 30 DAYS · PICKING UP Confidence Signaling 15 IN 30 DAYS · PICKING UP
Top insight · from 199 sightings across 29 patterns

Confidence Signaling doubled from 6 to 15 sightings in a month, the fastest climb in the library. Approval leads at 26 and has held steady. The 4 settled patterns carry 20 percent of everything seen this month.

4 of 29 patterns have settled, 8 are picking up, 199 sightings in 30 days FIG. 0 · THE STATE OF THE FIELD · OCT 23, 2026

solid = established halftone = emerging outline = still watching hairline = the 30 days before beacon = picking up One tower per pattern, height = confirmed sightings in published field notes over the last 30 days, grouped by family · n = 199 sightings across 29 patterns · snapshot 2026-10-23.

02

This week in the field

ALL FIELD NOTES →
OCT 23 Paper via arXiv arXiv paper shows agent groups copy each other into bad answers High confidence from a group of agents can mean they all copied the first one. The review surface needs to show where agreement came from, or the human deciding on the output has nothing real to judge. → CONFIDENCE SIGNALING OCT 23 Paper via arXiv DoorDash ran 35,000 code changes through AI agents for $4.79 each The reviewer approved or rejected based on a summary the agents wrote, not on direct inspection of the work. The handoff summary is the interface, and that makes its accuracy the design problem. → AGENT-TO-AGENT OCT 23 Paper via arXiv Open index maps how much of a job agents can take over This index shifts the design question from whether an agent touches a task to how much of it a human can hand over. Reach for approval and review patterns before you allow background execution. → APPROVAL OCT 23 Paper via arXiv Atlas gives designers a map of what a long agent run actually did The agent ran; the human arrived after. Atlas shows that the review screen is its own design problem, separate from delegation or progress. Most products have not built it yet. → HUMAN HANDOFF OCT 23 Paper via arXiv ABRA gives each agent its own reusable screen panel The view is bound to the agent that made it. That one design move changes what a human can do: they can see who built the surface before they touch it. Generative-ui without that binding leaves the human with no footing. → AGENT IDENTITY OCT 23 Paper via arXiv HCI researchers map how shared workspaces change agent work The workspace holds the knowledge, not the agent alone. A product team that designs the agent first and the workspace second will build something where the human approves without seeing enough to judge. → APPROVAL

03

Essays

ALL ESSAYS →

SIGHTING · OCT 22

30 audited platforms ask what an agent can do, not what it shares

Approval screens ask what an agent may do, then stop. The question of what an agent may share goes unasked, and a new wave of research shows what breaks when that question has no answer.

 → PERMISSIONS

SIGHTING · OCT 21

Designers said yes to errors they did not look at

A researcher watched reviewers look at an approval screen, click yes, and miss the error in front of them. That finding breaks the premise of a review step built on presence alone.

 → APPROVAL

SIGHTING · OCT 20

A forged fact fooled 18 agents because each checked one detail

An agent confirms one detail and waves through the rest. The human approving downstream inherits the agent's confidence, not its evidence. That gap is a design decision, and most products leave it blank.

 → APPROVAL

04

The field, measured

ALL INSTRUMENTS →

Where the month moved · by family

Understanding fell the furthest, from 47 to 27 sightings in 30 days.

0 20 40 60 80 Decisions 73 +11 Trust 47 +7 Understanding 27 −20 Handoffs 18 −2 Context 15 −4 Many agents 14 +2 Surfaces 5 +1

the 30 days before the last 30 days

Table
FamilyLast 30 days30 beforeChange
Decisions7362+11
Trust4740+7
Understanding2747−20
Handoffs1820−2
Context1519−4
Many agents1412+2
Surfaces54+1

Climbers and coolers · change in sightings

14 patterns gained sightings and 10 lost ground against the month before.

0 Confidence Signaling +9 Approval +6 Review +5 Human Handoff +4 Observability −14 Off-Brief Alert −8 Permissions −7

gained · right of zero lost ground · left of zero

Table
PatternLast 30 days30 beforeChange
Confidence Signaling156+9
Approval2620+6
Review149+5
Human Handoff128+4
Observability1630−14
Off-Brief Alert210−8
Permissions1522−7

All three figures read the 2026-10-23 snapshot of pattern_drift_daily: confirmed sightings in published field notes, the last 30 days against the 30 before · n = 199 sightings this month, 204 the month before, across 29 patterns in 7 families.

At the desk Drafts ride a belt to a gate a person holds: 1 waiting before it, 5 published past it this week.
Approval is the most-sighted pattern of the last 90 days
Approval
46none prior
Observability
46none prior
Permissions
38none prior
Review
23none prior
Confidence Signaling
21none prior
Context
21up from 1
Human Handoff
21none prior
Agent-to-Agent
20none prior

Published, annotated sightings attached to each pattern, trailing 90 days (Jul 25 – Oct 23). The 1px tick on each track is the prior 90 days (Apr 26 – Jul 25). n = 236.

View as table
PatternTrailing 90dPrior 90d
Approval460
Observability460
Permissions380
Review230
Confidence Signaling210
Context211
Human Handoff210
Agent-to-Agent200
Where the momentum came from, week by week
Approval10 this week
Observability4 this week
Permissions4 this week
Review5 this week
Confidence Signaling3 this week
Context3 this week
Human Handoff5 this week
Agent-to-Agent5 this week

Weekly counts of published, annotated sightings per pattern over the last 12 weeks (Aug 7 – Oct 23), every row on one scale; the dot is the latest week. Hover a week to read every pattern at once. n = 236.

View as table
PatternAug 7Aug 14Aug 21Aug 28Sep 4Sep 11Sep 18Sep 25Oct 2Oct 9Oct 16Oct 23
Approval0000945336610
Observability0001861413454
Permissions010194633344
Review000031503245
Confidence Signaling000041105253
Context000052512213
Human Handoff010040412045
Agent-to-Agent000042203225

The field is still forming: only 4 of 29 patterns are established.

established · 4 · stable across independent vendorsemerging · 12 · seen across products, shape settlingwatching · 13 · candidate, accumulating sightings

Current lifecycle stage of every catalogued pattern · stages per the promotion bar on /methodology · n = 29.

How long maturity takes
ESTABLISHEDEMERGINGWATCHING0481216202428Agent-to-Agent· 2 mo2Review· 2 mo2Observability· 2 mo2Budget Scoping· 2 mo2Multi-Agent Roster· 2 mo2Ambient Status· 2 mo2Confidence Signaling· 2 mo2Permissions· 3 mo3Emergency Stop· 3 mo3Reach Preview· 3 mo3Off-Brief Alert· 3 mo3Context· 4 mo4Generative UI· 4 mo4Background Execution· 4 mo4Delegation· 5 mo5Approval· 5 mo5Eval Run Setup· 5 mo5Release Decision· 5 mo5Planning· 6 mo6Memory· 6 mo6Progress· 7 mo7Human Handoff· 7 mo7Interruption· 8 mo8Recovery· 8 mo8Agent Identity· 9 mo9Case Drilldown· 26 mo26Production Drift· 26 mo26Eval Set Authoring· 27 mo27Comparison View· 27 mo27

MONTHS SINCE FIRST SIGHTING

First sighting = earliest observed date attached to the pattern · promotions from the pattern changelog · n = 29 patterns.

View as table
PatternLaneFirst sightedMonths since
Agent-to-AgentEMERGINGAug 20262
ReviewEMERGINGAug 20262
ObservabilityEMERGINGAug 20262
Budget ScopingWATCHINGAug 20262
Multi-Agent RosterWATCHINGAug 20262
Ambient StatusWATCHINGAug 20262
Confidence SignalingWATCHINGAug 20262
PermissionsEMERGINGAug 20263
Emergency StopWATCHINGJul 20263
Reach PreviewWATCHINGJul 20263
Off-Brief AlertWATCHINGJul 20263
ContextEMERGINGJun 20264
Generative UIEMERGINGJul 20264
Background ExecutionEMERGINGJun 20264
DelegationESTABLISHEDMay 20265
ApprovalESTABLISHEDJun 20265
Eval Run SetupWATCHINGJun 20265
Release DecisionWATCHINGMay 20265
PlanningESTABLISHEDApr 20266
MemoryEMERGINGMay 20266
ProgressESTABLISHEDApr 20267
Human HandoffEMERGINGMar 20267
InterruptionEMERGINGMar 20268
RecoveryEMERGINGFeb 20268
Agent IdentityEMERGINGFeb 20269
Case DrilldownWATCHINGAug 202426
Production DriftWATCHINGAug 202426
Eval Set AuthoringWATCHINGJul 202427
Comparison ViewWATCHINGJul 202427

05

The pattern index

ALL PATTERNS →
Approval ● established Deciding, with enough in view, before an agent does a thing that is hard to undo. npx shadcn add @agentsandhumans/approval-gate Planning ● established Agreeing on the shape of the work before the agent does it. npx shadcn add @agentsandhumans/plan-preview Progress ● established Knowing what the agent is doing, how far along it is, and whether to step in. npx shadcn add @agentsandhumans/progress-trace Interruption ◐ emerging Changing an agent's course while it runs, without starting over. npx shadcn add @agentsandhumans/interruption Recovery ◐ emerging Putting things back, or taking over, after an agent makes a mistake. npx shadcn add @agentsandhumans/recovery Delegation ● established Handing an agent a piece of work so it understands the job the way you do. Context ◐ emerging Shaping what the agent knows before it starts, and seeing where that knowledge came from. Memory ◐ emerging Knowing what the agent remembers about you, and being able to correct it.

● ESTABLISHED — A STABLE CONVENTION ACROSS INDEPENDENT VENDORS · ◐ EMERGING — SEEN ACROSS PRODUCTS, SHAPE STILL SETTLING · ◌ CONTESTED — VENDORS ACTIVELY DISAGREE

06

WEEKLY · FREE
FIVE-MINUTE READ
NO ADS · NO NOISE

The important shift isn't that AI can generate things. It's that software can increasingly act.