AI-Native Expert Platform
Designing the control surface for continuous human–AI collaboration
Overview
As agentic AI matures — models, tools, memory, and governance evolving together — we are rethinking how AI should participate in expert workflows. Intuit experts work on tax and bookkeeping: high-stakes knowledge work with accuracy, legal, and compliance consequences, where a human must remain the final accountable party.
This case is about what happens when AI becomes a continuous participant in that work — and what the interface becomes when the system no longer waits to be asked.
AI prepares ahead of the human. The human decides what matters.
The shift
AI in knowledge work is moving from copilots that generate text to orchestrated systems that retrieve evidence, plan multi-step work, and take constrained actions inside real tools and data environments.
In expert service, the shift is concrete. The system assembles customer context from systems of record, surfaces grounded guidance, and prepares next steps as the conversation unfolds — before the expert asks.
That changes both the interface and the expert's role. The interface is no longer the workspace where work happens. It is the control surface where the human intervenes in a system already running. The expert's value shifts from retrieval and synthesis to judgment. AI absorbs the preparation layer. The expert decides what matters.
This is not a productivity improvement. It is a different allocation of cognitive work. And if AI is always preparing, structure is what keeps the human in control.
DIAGRAM
The interface
role shift
BEFORE
Workspace
Human drives.
Tools responds.
AFTER
Control surface
System runs continuously.
Human intervenes.
Exploring the architecture
If the interface is a control surface, what should it look like? I explored three directions, pushing each until its failure mode became clear.
Open canvas — spatial.
The open canvas has infinite space. AI-prepared content lives as cards on the canvas; the expert pans and zooms to navigate.
But expert service is not spatial work — it is sequential and time-bound, organized around a conversation that unfolds in real time. Pan and zoom while a customer is talking is friction, not flexibility.
Single thread — sequential.
Everything lives in a single scrollable thread; deep work happens inline. A pop-out option lets the expert focus on one workflow when needed. Simple, low-friction.
But the conversation form factor locked attention into a single thread — the expert couldn't reference the copilot's reasoning while filling out a form, or check live transcription while reviewing a document. The single thread became a ceiling on parallel work.
Copilot with Canvas — parallel.
Copilot stays visible, canvas conditionally opens alongside for deep work.
When the expert only needs AI's preparation, the copilot has full focus. When deep work calls, the canvas opens alongside — and the copilot keeps preparing. Two states, one continuous system.
This was the direction we shipped. The model that matched the actual shape of expert work: a conversation that runs continuously in time, with moments of deep focus that need to happen in parallel — not sequentially, not spatially.
The primitives
Four primitives structure the control surface for human–AI collaboration.
Global rail
The persistent anchors: Home, Customer, Notifications, Schedule, expert status.
AI Copilot
Where the system's continuous preparation is visible — retrieving, grounding, staging next steps. The expert monitors, reviews, and acts.
Command bar
How the expert directs the copilot: ask, search, invoke tools, override. The input layer that keeps the human in command of a system already in motion.
Canvas
Opens alongside the copilot for deeper work. The expert gains workspace without losing visibility into the copilot's preparation.
The collaboration matrix
When we design the push and pull between AI and human, we map them on a matrix defined by two axes — who initiates, and what happens to context — over a shared substrate of ambient context, always collecting in the background.
1. Proactive guidance
AI listens continuously. When a substantive question emerges in the conversation and clears a confidence threshold, the system notifies the expert that it has a grounded answer ready before the expert asks. AI push, and it's essentially automated Q&A — the search anticipated before it's typed.
2. Ask AI
The human pull. AI responds using the ambient context already collecting in the background — and the chain of thought is exposed for a deliberate beat before the answer resolves. In a regulated domain, the expert needs to see how the model got there, not just what it concluded. Showing the reasoning is part of the trust contract.
3. Human handoff
When AI is not enough, the expert escalates by typing /lead. AI packages the context into a structured handoff. The same pattern explored in depth in Case 3 — context forwarded when responsibility transfers.
The fourth quadrant — system-initiated handoff — is the unbuilt frontier. When should the system itself decide that a case has reached its boundary, package context, and route to a more senior expert without being asked? This is where preparation begins to cross into execution.
The shift in expert behavior across all three: less composing, more reviewing, steering, and deciding.
Graceful fallback during automation rollout
The matrix describes the shipped patterns, but the system isn't fully automated yet. Most expert work today still happens through manual tool selection — opening a workbench, pulling up a document, invoking a workflow. Until AI can reliably automate every one of those moves, design's job is to keep the manual path as fast as the automated one.
The most-used workbench tools are surfaced as one-click buttons inside the command bar's input area, ranked by frequency. The expert never navigates to find them — they're already there, alongside Ask AI. Human pull stays fast even as automation expands. As more capabilities move from manual to automatic, the buttons fade; until then, the path stays first-class.
Tuning the system
Continuous preparation creates problems that request-response systems do not have. What if suggestions arrive too often — does the expert tune them out? What if the thread of preparation grows too long — how does the expert navigate it?
Suggestion overload
Getting the right amount of AI suggestions is a fine balance — too much becomes noise, too little becomes useless. We carefully tuned the trigger threshold to find that balance.
The deeper lever was what the notification revealed. We tested two patterns: a blue pill that read "New guidance available," vs. a notification with a preview — "Customer said X — do you want Y?" — with "Show answer" and dismiss controls.
The pill behaved like a message app, with no preview of what was coming, and nothing could be dismissed — so on paper, we were putting more content in front of the expert.
The notification with a preview let the expert assess relevance before committing. Counterintuitively, giving them a dismiss option built more trust — every push felt more intentional, and dismiss became an act of judgment, not a missed signal.
Lost in the thread
Continuous human–AI collaboration produces a thread that grows long fast, and the expert ends up scrolling a linear stream to find what mattered. Past a certain length, the stream stops being navigable.
Knowledge work is rarely linear — experts need to jump between moments. So we gave the thread a workflow: a table of contents on the left, with each step in the call (review information, recommend approach, prepare next action) as a navigable entry. The expert could jump to any moment, not just the most recent.
Design leadership at platform scale
As the industry moves toward agentic AI and AI-native workflows, we are uniquely positioned to pioneer this paradigm at real-world scale. The Intuit Expert Platform supports tens of thousands of experts serving tens of millions of customers across TurboTax and QuickBooks. This is not a startup iterating with a small user base — every paradigm decision lands at scale on day one.
That made design's role specific: derisk the build by reasoning through the end-to-end experience before engineering committed. I worked across product, AI Science, engineering, and senior leadership, building interactive prototypes that let partners argue with the design through artifacts rather than abstractions. The prototype was the meeting room — debates happened against working ideas, not slides.
I presented at VEP Design E2E, the CEO staff meeting, and design all-hands for TurboTax and Credit Karma. QuickBooks adapted the framework for All-in-One. Credit Karma leadership aligned. Intuit's CTO cited the work as directly supporting the company's core AI bet. What started as a design direction became infrastructure for multiple product lines.
What comes next
Execution
The next stage isn't preparing answers, it's executing actions. As AI moves from preparation to constrained action — updating records, routing cases, scheduling follow-up — the design problem shifts from oversight of suggestions to oversight of outcomes. How does the expert stay accountable for outcomes the system increasingly authors on its own? When should the system act without instruction? How are actions bounded, reversible, audit-trailed?
Memory
Expert-customer relationships in this domain are not single-session. TurboTax customers return every year. QuickBooks customers return many times per year, often weekly. The relationship is the unit of value, not the call. But each session today starts effectively stateless — the system carries forward summaries, but summaries compress, they do not preserve structure.
The deeper direction is treating each customer as persistent state: stable facts, interaction history, prior resolutions, patterns that accumulate. Each interaction would not just consume context but update it. AI would no longer re-derive what it should already know.
This emerged from collaboration with a platform architect and has been filed as a patent. The design question is the same one underneath the entire case, raised one level: how does the expert trust, verify, and override a system that now remembers more than they do?
Final thoughts
The specifics in this case study are TurboTax and QuickBooks expert service — regulated, high-consequence, operating inside systems of record.
But the design problem is general. Every knowledge workflow where AI can retrieve, ground, suggest, and begin to act will face the same question: how do you build a system where AI operates continuously and the human's judgment still governs the outcome?
When systems no longer wait for humans, the interface is no longer the product. The system is.