— MISt · HCI Focus · ACT Research Group (McGill SIS) —

Gainshin · Joshua Hsiao

profile · Apr 2026 Years shipping UX.
Now studying why it breaks.
I'm finishing a Master's in Information Studies at McGill, working in Dr. Karyn Moffatt's Accessible Computing Technologies (ACT) Research Group, after years of practice shipping UX and advising AI startups. What pulled me back into research: I kept running into AI systems that were confident and wrong, and I wanted to study why people trust the wrong outputs with actual controls, not just opinions. My current work is a health-assistant prototype I built to test exactly that.
It's a conversational assistant for now. Where I actually want to take it is voice — the lab's work is with older adults, and most of them will never open a screen-first health tool, which makes me wonder whether any of the trust findings survive when the reasoning can only be heard, never seen.

Quick Contact

EMAIL
gainshin.hsiao@mail.mcgill.ca
LOCATION
Pointe-Claire, Montreal QC
PROGRAM
MISt · Information Studies · McGill
LAB
ACT Research Group · Accessible Computing Technologies
LANGUAGES
English (B2) · Mandarin (native) · French (basic)
01/03
— What I Bring
Practitioner Lens, Research Rigor
HCI researcher in McGill's ACT Research Group, with years of AI/UX practice behind me. I work the slow way: take a vague question, design a study around it, then build whatever prototype I need to actually run that study. The health-assistant work with Dr. Moffatt is the current example.
// 01 · what-i-bring

Evaluating Probabilistic Systems

System Fluency × Methodological Rigor

Member of McGill's ACT Research Group, studying how humans collaborate with probabilistic AI assistants, multimodal interfaces, and agentic workflows. Years in consulting taught me to quickly identify system failure modes; MISt training provides the methodological rigor to isolate variables, design mixed-method studies, and evaluate AI quality beyond traditional usability (e.g., trust calibration, error recovery, and controllability). I don't just study AI systems; I understand their underlying ML constraints and prototype alternative human-in-the-loop interaction models.

Non-Traditional Return to Research

Design → MISt → ACT Lab

I spent years shipping UX and advising AI startups before coming back to McGill — not to leave practice, but to study it properly. The lab work lets me actually run the studies I only used to sketch.

Trained in HCI Methods

Coursework + Lab Application

Through MISt coursework and ACT lab projects I've run semi-structured interviews, think-aloud protocols, heuristic audits, and qualitative coding—applied directly to AI health interfaces and agentic UX. I can follow a research plan rigorously; I also know when a finding needs a prototype, not another interview.

From Loose Criteria to Testable Artifacts

Structured Evaluation & Prototyping

My heuristic audit tool and Proxy Auditor prototypes both started as open, ambiguous prompts. I scoped the evaluation criteria, built the interfaces for inspecting AI execution traces, and versioned the code and audit artifacts on GitHub. That move — vague ask in, something runnable and reviewable out — is most of what the work actually is.

Writing as Research Infrastructure

Agent Governance Column

I publish weekly on agentic UX and privacy—AI literacy, dark patterns, governance. The point isn't the audience; it's that writing forces me to commit to a position before I've built anything, and half my arguments fall apart the moment I have to defend them in print. The ones that survive are usually what I prototype next.

Privacy & Accessibility by Design

Ethics + Compliance Foundation

Seven Mila certificates (AI Practitioner Journey, Privacy Safeguarding) plus TCPS 2 research ethics. ACT lab focus on accessible computing; my consulting work centers privacy-first agent design. Relevant when research involves health data, AI transparency, or consent-flow evaluation—not just compliance checkboxes.

"I'd rather prototype the question, write down what broke, and iterate—than ship an answer I haven't stress-tested."

Personal note
02/03
— Research Projects
Studies, Apparatus & Frameworks
Lab and course projects — but built like research. Each one takes an ambiguous question, manipulates a variable or applies an explicit criterion, and ends in something runnable.
// 02 · coursework

Proxy Auditor — Trust-Reasoning Study Apparatus

Within-Subjects Study Design & Runnable Prototype · 2025–2026

I built a working health assistant that gives screening recommendations — but the real point is what it manipulates. The same recommendation shows its reasoning two ways (a hover tooltip, or an always-visible list), and participants go through both across counterbalanced sequences of synthetic cases: colorectal screening, a couple of drug-interaction scenarios. The question is whether that format changes how well people calibrate their trust, and whether they catch it when the assistant is wrong. I wrote the protocol — vignettes, the interview guide, the rubrics for trust and error recovery — and built the apparatus itself in Cursor. Supervised by Dr. Karyn Moffatt. It's a conversational assistant for now, but the manipulation isn't tied to that; it would carry to a voice or multimodal version of the same task.

Heuristic Audit Tool + Evidence Warrant

Structured Evaluation, Grounded in Literature

This one started as "evaluate whether this AI health interface is safe" — no rubric, no criteria, figure it out. So I did two things. First I read the healthcare-decision literature (GRADE's Evidence-to-Decision framework, the DISCERN instrument) and pulled it into a structured warrant, tagging each criterion by the kind of friction it addresses and where it sits in a decision-transparency hierarchy. Then I turned that into an actual audit tool: a set of safety heuristics, the review runs, the artifacts, all versioned on GitHub, with critique framing borrowed from Google Research's UICrit dataset. What I care about is that every check traces back to a source — it isn't me deciding what "safe" means by feel.

Agentic UX — Weekly Research Column

Publications · Frameworks · Stakeholder Translation · 2023–Present

I've published weekly on agentic UX and AI governance since 2023, for 1,000+ subscribers — a "Top 25 Rising" newsletter in 2025, and "Top 9 Rising" in design this past quarter. It's where I work ideas out in public: most of my frameworks, like the governance ladder and the writer-as-orchestrator model, got their first draft there before they showed up in anything I built. I also mentor early-career UX practitioners 1:1 on ADPlist — mostly practice at explaining research to people who don't have the jargon.

03/03
— Education
Where I'm Training
McGill MISt researcher with the ACT Research Group (Accessible Computing Technologies, School of Information Studies)—HCI track focused on accessible computing and AI health interfaces. Research funded through NSERC Discovery Grant on ethical AI for active aging; thesis work examines how replay formats shape trust in proxy audit evidence during medical decision-making.
// 03 · education

McGill University · MISt · ACT Research Group

Accessible Computing Technologies Lab · Expected Summer 2027

Member of the Accessible Computing Technologies (ACT) Research Group (McGill School of Information Studies).
Degree: Master of Information Studies — Information Management & HCI track.
Research question: How do different replay formats shape how participants notice, refer to, and draw on proxy audit evidence when they reason about trust in an AI health recommendation during medical decision-making?
Supervisor: Dr. Karyn Moffatt (Principal Investigator). NSERC Discovery Grant, 2024–2029: Ethical and appropriate AI enhanced services to support active aging in later life.

Certifications

Mila · Research Ethics · Continuing Education

Mila — Quebec AI Institute (7 credentials)

  • AI Practitioner Journey
  • Decoding AI: Transparency & Explainability
  • Safeguarding Privacy in AI
  • + 4 additional certificates

Research ethics & method

  • TCPS 2: CORE Research Ethics (Tri-Council)
  • IDEO U: Design Thinking
  • Actionable Strategies for AI Impact Assessments
  • Responsible AI & AI Ethics

Languages

Working Levels
  • English: B2 (working professional, daily writing)
  • Mandarin Chinese: Native (Traditional & Simplified)
  • French: Basic, learning to support QC context

Study × Build × Publish

What I Bring

I bridge practice and research: years advising on agentic UX and privacy-first design, now grounded in ACT lab work on accessible AI and proxy-audit trust. Most of what I study now came straight out of problems I couldn't solve as a consultant.

×

What You'd Get

Runnable research artifacts—prototypes, heuristic audit tools, interview guides, evaluation rubrics. And the habit of writing things down—protocols, decisions, what didn't work—so whoever picks up the project next isn't starting from a blank page. Everything versioned on GitHub.

×

How to Reach

Email gainshin.hsiao@mail.mcgill.ca—fastest reply. Portfolio and project samples at gainshin.github.io. Available now for human-AI interaction research, collaboration, or consulting conversations. Montreal-based · Canadian resident, no sponsorship needed.

— UX Writer's CoT · Agent Orchestration —

Curate × Orchestrate

figure 00 · thesis Writer as
Orchestrator.
No agent remembers how that interview two weeks ago got resolved.
Karpathy's LLM Wiki is the pattern I kept reaching for: humans curate the sources and ask the questions; the AI does the summarizing, cross-referencing, and filing. The bet isn't new—Bush wanted the same from his 1945 Memex—it just needed something that could actually do the upkeep. And upkeep is the whole game. Knowledge nobody maintains rots, and a wiki nobody weeds is just a slower mess.
The job has already changed: every UX practitioner—PM, researcher, designer—now carries a second identity on top of the first, the UX Writer / Curator. You write in CoT, treat markdown as your interface, and orchestrate a team of agents—Design, Research, Copy, Red Team—each with its role, all sharing one wiki as their context.

Technical Grounding

Agent Development
MCP servers & tool schemas · agent skills · subagents · multi-agent orchestration
API & Tooling
LLM APIs · agentic coding workflows · prompt engineering
AI Fluency
AI fluency frameworks · applied across education & nonprofit work
— Wiki-as-Interface

How an AI/UX Writer's CoT Orchestrates Multiple Agents

figure 01 · flow
RAW SOURCES — immutable material INGEST → LLM WIKI — Karpathy, n.d. ↔ QUERY UX AGENTS — focused workers PRD / Feature List PRODUCT SPEC Journey Map USER JOURNEY Module List FEATURE MODULES Page List SCREEN INVENTORY User Flow TASK FLOW LLM Wiki — LLM-maintained markdown index.md Catalog CATALOG log.md Timeline CHRONOLOGICAL persona/ · decisions/ Topic Pages CURATED PAGES cross-ref · backlinks · tags THE THING THAT DEGRADES IF UN-MAINTAINED Schema / CoT — writing rules · configuration cross-ref conventions · naming rules · lint rules · voice & tone Editing the schema scales further than editing each page ↑ LINT · periodic audit ↑ Design Agent UI · prototype Research Agent interviews · insights Copy Agent UX microcopy · voice Red Team Agent adversarial review Orchestrator = YOU · the curator after Bush (1945) · Karpathy (n.d.)
Ingest · Take in raw material New PRDs, journey maps, and module lists arrive—the AI reads them, summarizes, and builds cross-references between pages; you decide whether each source is worth committing to the wiki. Specs that used to live only inside docs become knowledge an agent can query.
Query · Pull and return Agents pull context from the wiki instead of being briefed from scratch every time; valuable answers get filed back as new pages—chat history is not knowledge, the wiki is.
Lint · Periodic audit Run automatic checks on a schedule: contradictions between pages, orphan pages no one references, missing cross-refs. Rules live in the schema, so editing one rule scales across every page.
USER · REQUEST ↓ L1 UserPersona Identity & Guardrails L2 AestheticPrompts Design Taste L3 FeatureWording Workflow L4 AgentGovernance Tools & Protocols L5 COT_Lexicon Tech Specs GUIDE · feed-forward LOOP Agent Generator Loop explore → sketch → build → show → iterate OUTPUT HTML Artifact SENSOR · verify done() + verifier silent on pass iterate if fail
Guide · Feed-forward constraints L1–L5 set out taste, discipline, and tool boundaries before the agent acts. Taste comes first, tools come second—designers develop an aesthetic before they pick up technique.
Loop · Generator cycle Inside the guard rails, the agent runs: explore → sketch → build → show. Showing the user early beats working in isolation—every preview is a chance to converge on direction.
Sensor · Silent verification Once the agent ships output, the system runs quality checks in the background. No issues, no noise—you only hear about it when something breaks.
01/05
— Failure Mode
The Tribal Knowledge Trap
This isn't an aesthetic problem—it's a memory problem. The HITL single-agent model holds up for a few people over a few weeks; once you cross that threshold, information starts decaying. Decisions disappear, every conversation re-briefs from scratch, and critical judgment walks out the door when people leave.
// 01 · why-it-breaks

Orphaned Decisions

No Owner, No Trail

Who decided the wording on onboarding step 3? Why can't it change? The answer lives in some Slack thread, a meeting recording, a slide buried in someone's drive. Can't find it = decide again = gamble again.

The Re-Briefing Tax

Every Conversation Starts From Zero

Every new chat, the agent forgets your persona, your design system, your legal constraints. The cost isn't the tokens—it's the attention tax of explaining the same things every single day.

Departure Amnesia

Knowledge Walks Out

The PM who knew how to talk to legal leaves, and within two months the product's copy starts drifting. Knowledge that lives only in someone's head has a lifespan equal to that person's tenure.

"Didn't We Decide This?"

The Re-Decision Loop

Someone asks it every week. Usually no one can answer. You're not making decisions, you're re-making them—because last week's decision was never filed, never backlinked, never retrievable by any agent or human.

No Single Source of Truth

Three Slightly Wrong Versions

One copy lives in Figma, another in Notion, a third in a Slack pin—each subtly different, and everyone thinks they're looking at the latest version. Multiple truths = no truth.

HITL Hits the Ceiling

The Bottleneck Moves to You

"Human supervises one agent" looks great in demos and stalls in production after a couple of weeks. The agent's iteration speed went up; your context-switching speed didn't. The bottleneck isn't the AI anymore—it's how fast you can manually curate.

"When everyone is responsible, no one is."

Agentic UX · Anthropic's $3M Rental of Open Source Elite
02/05
— The Wiki
A Three-Tier Architecture for Shared Memory
Karpathy's LLM Wiki splits cleanly into three tiers: raw material stays immutable, markdown pages get maintained by the LLM, and the schema is the rule layer itself. Clear boundaries mean clear ownership—humans decide what matters, the AI handles maintenance.
// 02 · architecture

Raw Sources

— Immutable Material

PRD / Feature List, Journey Map, Module List, Page List, User Flow. Immutable—never edited, only referenced. This is the anchor of fact—every wiki page has to trace back here.

The Wiki

— LLM-Maintained Markdown

Each page is one concept (persona/ / feature/ / decision/) or one summary. Humans curate the topics; the AI maintains cross-refs. Mutable but structured—not a chat history dump.

Schema

— Rules as Configuration

Writing style, naming conventions, cross-ref rules, lint policy. This tier is the rules themselves. Editing the schema scales further than editing each page—one patch propagates to every page on the next maintenance pass.

index.md · The Catalog

One-Line Summaries

One line of summary per page, organized by category. The entry point to the wiki—the first place an agent looks. The index decides which pages to read and which to skip, instead of scanning every file every time.

log.md · The Timeline

Append-Only Chronological

"Who wrote what, when." Old entries are never edited—new ones get appended. This makes context evolution traceable: the diff is the history. The orchestrator's audit trail.

Cross-References

The Anti-Rot Layer

[[persona/a]] wiki links, #onboarding tags, automatic backlinks. This is what stops the rot—orphan pages get caught by lint, hub pages emerge naturally, and you can find every place a concept is referenced.

Humans curate sources, ask questions, and think critically. The AI handles summarizing, cross-referencing, filing, and bookkeeping — the maintenance work that degrades human-maintained wikis over time. — Karpathy (n.d.), LLM Wiki

"If your design system still stops at 'we have a component library' rather than machine-readable tokens and naming rules, this shift will surface your existing debt before it pays it down."

Agentic UX · Agentic UX in Practice — Part 1: Design Critique and UX_Skill Distillation
03/05
— Compression Strategy
Why Memory Belongs in the Substrate, Not the Model
The claude-design-harness doesn't rely on the model's long-term memory—it actively manages context instead. Five compression layers fire in order, from light to heavy, preserving the most important information while pulling token count down.
// 03 · harness-compresses

Remove Duplicates

Deduplicate · Lightest

Clear redundant content first—the same file read twice, the same command run three times. Cheapest move, almost no information lost. Always start here.

Summarize Tool Output

Summarize Outputs · Low

Bash returns, file reads—high volume, low density. Compress them into short summaries that keep "what was done, what conclusion came out" and drop the verbose middle.

Merge Conversation Turns

Merge Turns · Medium

Collapse multiple short turns into one. "You asked → I answered → you clarified → I clarified" becomes "the conclusion of this exchange is X." Lower turn overhead, same meaning preserved.

Generate Global Summary

Global Summary · Heavy

Produce a structured summary of the entire conversation history—task state, key decisions, open todos. Like auto-writing a checkpoint log, so the next turn can restart context from this summary.

Truncate Oldest

Truncate · Last Resort

Only as a last resort—discard the earliest turns, keep recent and critical content. Highest information loss, but sometimes the only option. The harness records "what got truncated" in the persistent view.

Light Before Heavy

Graceful Degradation

The harness doesn't reach for the heavy moves first. Levels 1–5 fire on demand: token pressure rises → dedupe; still not enough → summarize outputs; and so on. Graceful degradation, never blunt truncation.

"You need governance at the system level—and that governance has to answer a question traditional HR has never faced: are the tokens an employee burns training agents a cost or an investment?"

Agentic UX · Agentic UX in Practice — Part 3: Is $2,400 in Tokens a Cost or an Investment?
04/05
— Dual-View
Let the Harness Run the Show
The context the model sees and the history the harness stores are two separate views. The model view is lean—just the current task. The persistent view is complete—everything kept. The split keeps each model turn light while the harness never loses context.
// 04 · harness-manages

Model View

What the Model Sees

The compressed context the model actually sees this turn—only the relevant wiki pages, the compressed conversation history, and the live task state. Light, focused, rebuilt every turn.

Persistent View

What the Harness Stores

The full task history and state—every turn, every tool call, every decision trail. Stored at the harness layer, not stuffed into the context window. The model never sees it; the harness can pull any slice on demand.

Splitting the Two Views

Decoupling

This separation is the core of claude-design-harness. The model doesn't need to "remember everything"—it just focuses on this turn. The harness doesn't need to "fill the context window"—it holds the complete state and ships only what's needed.

Delivery Mechanism

How the Harness Feeds the Model

Each turn starts: the harness picks task-relevant fragments from the persistent view → applies compression (Stage 03) → assembles the model view → ships it to the context window. The harness makes the call, not the model.

Retrieval Mechanism

How the Model Requests Context

The model needs an older slice → emits a request → the harness retrieves from the persistent view → summarizes and injects it into the next turn. Pull on demand, don't preload—mirrors the wiki's query pattern.

Three Nested Layers

Wiki × Harness × Model

Wiki = the persistent layer for team-wide knowledge (shared); harness persistent view = the persistent layer for a single task (internal to the agent); model view = just this turn. Each layer has its own compression and retrieval, sitting at a different point in the stack.

figure 04 · harness for practitioners A Practitioner's View— from design specs to agent governance
GUIDE × SENSOR · AI/UX PRACTITIONER VERSION COMPUTATIONAL specs a machine can verify INFERENTIAL things that need human judgment GUIDE · feed-forward SENSOR · feedback Q1 · Quantifiable Design Specs Static Contracts · Component naming conventions (Button vs Btn) · Spacing / type / color token definitions · Page hierarchy (matched to Page List) · API field ↔ UI field mapping → Agent can verify 100% automatically Q2 · Judgment-Based Design Guides Semantic Guides — most often missing · UserPersona — voice, tone preferences · AestheticPrompts — brand mood · FeatureWording — commercial trade-offs · Edge case priorities → Only practitioners can write these — can't outsource to agents Q3 · Auto-Run Checks Deterministic Checks · Text length doesn't overflow components · Color contrast ≥ WCAG AA · Tap targets ≥ 44px · Required fields have error states ← Most teams stop here Q4 · Human Quality Review Semantic Review · Design Critique — does this flow make sense? · Red Team — could this mislead users? · Business judgment — can we trade off this step? · A/B hypothesis — which way will metrics move? → AI can flag, humans decide BLIND SPOT Q2 + Q4 = right column. Most teams only invest in the left. after Böckeler / martinfowler.com — adapted for AI/UX practice
FINDING
Anyone can do the left column (the auto-checkable stuff). The right column—the parts that need human judgment—is where AI/UX practitioners are irreplaceable: voice, brand mood, commercial trade-offs, edge case priority. None of this fits in a linter. It only fits in a Guide.
STEERING LOOP · A PRACTITIONER'S FEED-FORWARD × FEEDBACK LOOP GUIDE · feed-forward written before the agent acts PRD / Feature List Journey Map Page List / Module List User Flow Aesthetic Prompts ↑ More precise = less trial-and-error INSTRUCT AGENT Design Agent generate · act · ship OUTPUT Design Output SENSOR · feedback checks after the agent acts · Design Critique (quality) · Red Team (adversarial review) · QA Checklist (acceptance) VERIFY PASS FAIL → fix the GUIDE (not just the output) ⚠ Most common mistake Only feedback, no feed-forward
FINDING
Most practitioners only work the feedback half—they wait for output, then point out what's wrong. But agents need feed-forward: tell them what "right" looks like before they act. Writing a good Guide pays off more than fixing things after the fact. When something fails, fix the Guide—not just the output.
IMPLEMENTATION LADDER · A PRACTITIONER'S GOVERNANCE MATURITY Each rung is additive, not a replacement — L5 stands on the shoulders of L1→L4 BASELINE · ZERO HARNESS Verbal handoffs, no docs, agent starts from scratch every time LEVEL 01 Write Your First Spec First Guide Turn PRD, Journey Map, Page List into agent-readable markdown. → Q2 quadrant LEVEL 02 Add Auto-Verifiable Checks Computational Sensor Naming, spacing, contrast, tap targets—linters the agent runs itself. → Q3 quadrant LEVEL 03 Automate the Process Automation L2 checks fire after every output—you only review the failures. LEVEL 04 Semantic Review Inferential Sensor A second agent runs Design Critique / Red Team—catches what linters miss. → Q4 quadrant LEVEL 05 Observability · Closed Loop Agent failures = gaps in your Guide HARNESS MATURITY → ⚠ Most common mistake Skip L1, jump to L2 — no feed-forward, no learning
FINDING
L1 is where everything starts: turn the design judgment in your head into agent-readable docs. Skipping straight to a linter (L2) is the most common mistake—without feed-forward, agents can only trial-and-error, and no amount of feedback fixes that.

"HCI is no longer just about making systems usable—it's the only mechanism keeping them controllable."

Agentic UX · When AI Becomes a Swarm: What Interface Design Can (and Can't) Do for Governance
05/05
— The Sixty-Year Debt
Not a New Invention — a Debt Coming Due
Agentic UX isn't a 2026 invention. Its roots run back past 1997—to a sixty-year fork in how we relate to machines. This closing stage pins the term back onto its historical ground: not a new discipline, but an old governance debt coming due, and the two layers where it gets repaid are the ones this whole tab is built on—harness and governance.
// 05 · bloodline

The Mother Fork

Augmentation vs Automation · 1960s

Decades before the marketing term, the human–machine relationship already split in two. Licklider's "Man-Computer Symbiosis" (1960) and Engelbart's "Augmenting Human Intellect" (1962) on one side—amplify the human. Early AI, McCarthy and Minsky, on the other—let the machine do it, the human steps aside. Everything after is this sixty-year fork replaying in new technology. Shneiderman is Engelbart's heir; Maes is the AI line's.

Control Meets Agency

Shneiderman ↔ Maes · 1983–1997

Shneiderman (1983) coins "direct manipulation": the human must feel in full control; the system must be predictable, immediate, reversible. Maes (1994) proposes the opposite—an interface agent that acts for you, cutting your load. At CHI '97 they collide head-on. What Shneiderman refuses to concede isn't capability—it's three things: anthropomorphism breeding false mental models, unpredictability, and blurred accountability.

Horvitz Dissolves the Binary

From On/Off Switch to a Dial · 1999

The debate didn't go silent for twenty-seven years. Two years later, Horvitz's "Principles of Mixed-Initiative User Interfaces" (1999) names the Shneiderman–Maes fight in its opening line and answers it: couple automation and direct manipulation, switching control by the uncertainty of the goal and the cost of interrupting the user. The 1997 on/off switch becomes a continuous, context-tuned dial—the academic ancestor of today's Autonomy Dial.

The Debt Comes Due

Maes Won Agency · Shneiderman Won Governance · 2026

Generative AI finally gave the 90s agent vision a working substrate—Maes won the agency argument, not because Shneiderman was wrong, but because the engineering caught up. And Shneiderman's three fears, once shelved for lack of capability, all turned from paper debate into live risk the moment agents shipped at scale. That's the debt: the governance bill from the deterministic era, due with interest. Elish (2019) later did the math on his third fear—the accountability black hole.

The Operational Definition

Why This Sits Under Tab II

So the series lands on one definition: Agentic UX is the practice of redistributing control and accountability as systems shift from "human operates" to "human supervises a swarm of agents"—and the core tension is how Maes's promise of agency and Shneiderman's insistence on control get re-contracted at the harness and governance layers. Those two words are the load-bearing columns of this tab. Tab II isn't adjacent to the column; it's the contract table where the sixty-year argument gets re-signed.

Two Lineages, One Corner

Read the Map Below →

The figure plots two separate genealogies on two axes. Across the bottom: the agent debate over time (Shneiderman ↔ Maes → Horvitz → 2026)—the control-versus-agency tension. Down the left: the design worldview descending its responsibility boundary (Garrett → Mill → Campbell). Agentic UX is where the latest moment meets the deepest layer—the bottom-right corner. That corner is where this tab's system lives.

figure 05 · the sixty-year map
Y · responsibility descends ↓ design worldview · Garrett→Mill→Campbell X · time × control tension → the agent debate · 1960s→2026 Garrett 2002 · five planes shallow · deterministic control Mill 2021 · anticipatory design mid · problem space Campbell 2026 · six layers deep · emergence tail 1960s fork 1983 control 1994 agency 1997 collision 1999 dial 2026 due the sixty-year arc — responsibility down, control right Shneiderman 1983 direct manipulation Maes 1994 interface agents ↕ 1997 collision Horvitz 1999 mixed-initiative · proto-dial Tab II · Writer-as-Orchestrator harness × governance AGENTIC UX INTERSECTION

Where the two axes meet — the latest moment on X × the deepest layer on Y = Agentic UX. Tab II sits in this cell: not a new invention, but the point the lines converge on.

"Agentic UX isn't a pure invention—it's engineering finally catching up to a path HCI sketched out decades ago. The vision can be revived, but Shneiderman's governance warning doesn't expire just because the models got stronger."

Agentic UX · Pinning Down Agentic UX's Sixty-Year Bloodline

Curate × Orchestrate

One More Layer of Deliverables

You used to ship design files and research reports. Now you also ship wiki pages—written so the next reader sees "why this step looks like this," "which alternatives got cut," "how edge cases are handled." Next time an agent picks up the project, that wiki is its Guide. No re-briefing.

×

From Watching One Lane to Routing Many

HITL (human-in-the-loop) means watching one agent on one thread. The orchestrator runs four agents in parallel—Design, Research, Copy, Red Team—and decides who starts first, whose output feeds whose, when to merge, and when to throw something back.

×

Decisions Move From Chat to Documents

Decisions used to scatter across Slack threads, meeting recordings, and slide deck comments—unsearchable, gone the moment people left. Now they land in version-controlled markdown: queryable by agents, citable through cross-refs, and auditable by lint to catch when they go stale.

Tacit-knowledge boundary · after Son et al., CHI'24

Where Generative Tools Stop — and the loop that crosses it

Generative tools absorb the explicit layer—tokens, brand rules. The tacit why stays in a few heads; the round's real job is encoding it back so the next pass doesn't re-decide it.
scroll · drag · hover