The Next OAC Meeting Will Be a Room Full of People Prompting Agents

The biggest shift may be a new verbal protocol for assigning agent work, adding context, and running dozens of studies at once.

We ran a two-hour work session with our MEP team and one or two software developers. By the end of it, we had generated somewhere between 10 and 20 pull requests. Many were reviewed, merged into the platform, and available to users that same day.

These were real changes to our engineering platform. Bugs fixed. Interfaces cleaned up. Features added. Work that would normally get written down, interpreted later, turned into tickets, prioritized, clarified, built, and eventually tested happened while the people experiencing the problem were still using the product.

The number of pull requests is crazy. The more interesting part is the verbal protocol we had to create to make the room work.

The live software protocol

1. Caller says “Bug,” “Feature,” “UX,” or “Question” — then stops.
2. Every developer listening answers “Ready.”
3. Caller describes the issue in one sentence.
4. Optional: any listener asks “Clarify: …” before claiming.
5. One developer repeats it back: “Heard … Mine.”
6. Owner says “Prompting now” and reads the prompt aloud (~30 seconds of silence for the room).
7. Owner says “Finished” when it is done, parked, or the PR is up.

It sounds small. It has changed how I think meetings will work in an agent-driven industry.

We are learning to co-prompt

AI work is moving into rooms full of people. Each person may own different agents, tasks, and areas of responsibility.

Internally, we spend a lot of time talking to agents. We also co-prompt. One person starts a prompt, another person hears it and adds a constraint, and someone else remembers a project condition that changes the whole direction.

Reading the prompt aloud has become an important confirmation step. “I’m working on it” tells the room almost nothing. Hearing the actual prompt tells everyone what the person understood, what the agent is about to investigate, and whether an important piece of context is missing.

You can interrupt before ten minutes of agent runtime heads in the wrong incomplete direction.

• Add: the ceiling height.
• Add: check the adopted code year.
• Add: the owner already rejected that manufacturer.

Every person in the meeting will have agents working

Now move this from a software session into an AEC design charrette.

An architect identifies a coordination question. The MEP engineer says, “Listening.” The architect explains the issue while everyone can see the model. The MEP engineer repeats the task back, prompts an agent aloud, and monitors progress as the meeting continues.

• A contractor sends an agent to compare installation approaches.
• An estimator launches a pricing study.
• An electrical engineer runs a load check.
• A mechanical engineer tests duct sizes against ceiling depth.
• A plumbing engineer investigates a code question.
• A project manager drafts a first-pass RFI response.
• A product rep’s agent searches manufacturer data against real constraints.

Each person may have several tasks running for 10 or 15 minutes. The meeting continues while the agents work. Results come back into the room, get reviewed by the responsible professional, and either move the project forward or go back for another pass.

The important question becomes: Who owns each agent task?

Meetings will need a protocol

This future gets chaotic quickly without a shared way of speaking. If five people launch agent work at once, the room needs to know what was claimed, whether context was included, whether to wait or move on, and who reviews the result.

Protocol steps

1. Call the task. Say what kind of issue has surfaced and stop.
2. Confirm listeners. The people capable of owning it respond.
3. Describe it briefly. State what needs to be studied and where.
4. Claim ownership. One person repeats the task and owns the agent work.
5. Prompt aloud. The room hears the prompt and adds missing context.
6. Launch and monitor. The owner runs the agent while the meeting continues.
7. Return with a result. Report findings and what still needs professional judgment.

Listen. Claim. Prompt. Add context. Launch. Review. Finish.

What gets called / who owns it

CallWhenOwnerClashTwo systems want the same spaceDiscipline that movesRoutingWill it fit / where does it go?Discipline that movesLoadElectrical, cooling, ventilation, waterEngineer of recordCodeAdopted code / jurisdiction / listingSealing professionalPriceCost or VE comparisonEstimator / contractorBuildConstructability / sequenceContractorRFIFormal response owedPM + discipline reviewProductManufacturer data vs constraintsSpecifying engineer

What a prompt sounds like

When ownership is claimed, the owner reads something like this aloud before the agent starts:

Prompting: compare a dedicated solid-fuel exhaust against the current kitchen shaft using the duct layout on the kitchen level. Flag where it has to dogleg. Smoker is 12x12 with its own flue. Ceiling below the kitchen is already tight. Needs my review before anyone builds to it.

PermitZIP is already working this way

We are already doing versions of this at PermitZIP.

Our team has agents. We talk to them. We hear one another’s prompts. We continue prompts for each other. We send multiple tasks to work while the team keeps moving. The live UI protocol came from needing a practical way to manage that behavior with our developers and MEP users in the same room.

AEC has a parallel opportunity. Imagine a two-hour charrette producing completed code studies, coordinated routing options, pricing comparisons, equipment research, first-pass RFI responses and submittal reviews, and tested design alternatives while the meeting is still happening.

The firms that learn how to orchestrate that room are going to move projects forward at a pace that currently sounds a little crazy.

We know it sounds crazy because we are already watching it happen.