Intake was a person. Now it’s a process.
AI ideas used to reach the Lean AI team through scattered channels: license queues, direct emails, hallway asks, threads that bounced between teams for weeks before anyone could scope them. The AI Intake Coordinator productized the intake process itself, so any associate can submit a well-formed, correctly routed AI idea conversationally. Its second generation lives on the AISE site: share a link and anyone can submit, with no install, in a conversation grounded in our own projects.
What a submitter gets
A well-formed, classified, correctly-routed request — with the brief and the ticket already written.
An 11-stage guided session
From a vague idea to a scoped, routed, submitted request — the associate just answers questions.
From an epic to a breakthrough
Logged as epic ASE-5 on February 18, 2026 — “streamline intake of new AI project requests.” Its shape came out of a design conversation between Chris Miller, Shelby Corbitt, Harvey Schaefer, and Michael Pietrangelo: an orchestrator on top, agent-to-agent. The pivotal moment was a deterministic-design correction.
“The orchestrator has been fighting me because we’re asking it to be the conversational agent and telling it to stay out of things. Re-architecting so it has one job and stays behind the scenes, with dedicated agents for welcome and end-of-conversation.”
— Shelby Corbitt, Staff AI Solutions Engineer
“The intake breakthrough is huge… we were breaking our own rules and didn’t realize it.”
— Michael Pietrangelo
Three principles
One job for the orchestrator
An orchestrator that both coordinates and decides is doing two jobs at once — a subtle flaw that looks fine in isolation. Evals surfaced it; the fix was a single-responsibility orchestrator that sequences only and delegates every decision.
AI tested the AI
Rather than trust the orchestrator by inspection, evals ran it against representative cases — and caught the design flaw before anything shipped to Production. The same eval discipline re-verified the re-architecture.
The agent that knows all our agents
Intake was the first step toward a true orchestrator-of-agents — a single conversational front door that routes every associate’s idea to the right team and the right next agent.
A link, not an install
The first version lived in Copilot Studio, so people had to find the agent and add it before they could use it. The new intake is part of the AISE site. Share a link and anyone can submit an idea, with nothing to install and nothing to set up. The easier it is to bring an idea, the more of them we see.
Grounded in our own work
The intake draws on this site and our project history, so it knows what we have built, which connectors and platforms exist, and where a request belongs. It points people to the lightest option that works, a prompt or Agent Builder, when that serves them better, and to a past case study when someone has already solved something close.
Scored to help us prioritize
Every intake gets a weighted score that helps the team decide what to take on first. It is a tool for the team, not a gate for the submitter, and the weighting stays with us.
A real soft launch
Nate Mackovjak — who scopes the team’s projects and routes them to the right backlog — tested for two weeks before rollout, which doubled as proof that submissions landed scopeable. Harvey Schaefer stress-tested the conversational flow; John McNally sits on the Data Science arm the Coordinator routes into. Testing surfaced concrete bugs — the orchestrator generating ideas unprompted, file uploads failing after the first message, missing error handling on bad files — each fixed before the formal MyMillerKnoll announcement.
Where it stands
The first AI Intake Coordinator has been in Production since March 31, 2026, open to all MillerKnoll associates, with real intakes already scoped from it. It runs an 11-stage conversation across a single-responsibility orchestrator, eight child agents, and three prompt tools. The next generation is the intake mode of the AISE Assistant, on the AISE site behind MillerKnoll sign-in: one link, no install, grounded in the site and our projects, scored to help us prioritize, and filed straight to the Lean AI board. Shelby Corbitt is also re-platforming the original onto the new skills-based experience, toward the vision behind both: the agent that knows all our agents.