AI agents

An AI workforce that works like your best people.

Fulcrum’s agents take on the legwork of construction: chasing RFIs, checking submittals, writing daily logs, reconciling invoices, and finding hazards. Each one has a job, a supervisor, and limits you set, and every step it takes is on the record.

The Agents node on the Fulcrum map: Relay, Vetta, Atlas, Scribe, Tempo, Ledger, Sentinel, Plumb, Quarry, and Beacon as hexagonal nodes around the Agents hub, with Roster, Live activity, and New agent.

How agents work

Colleagues, not black boxes.

Agents in Fulcrum follow the same rules as your team, with a few stricter ones of their own.

Agents are members

Each has a role, a supervising person, a permission template, and an activity record, just like the people it works with.

Autonomy is a dial

Observe, Suggest, Act with approval, or Autonomous, set per agent and per tool.

Some things stay human

Committing money, signing, changing permissions, and deleting records are never done by agents.

Everything is logged

Every agent action records its reasoning, inputs, and tool calls, and shows up in the audit log.

The roster

Ten roles, ready on day one.

Start from these role templates and name them whatever you like. These are the agents at work in Fulcrum’s sample workspace, and what each one is doing right now.

  • Relay

    RFI Coordinator

    Working

    Routes, drafts, and chases RFIs. Finds precedent in past answers, specs, and drawings before anything goes out, and keeps ball-in-court honest.

    Now

    Drafting a response package for RFI-142

    Autonomy
    Act with approval
    Triggers
    • An RFI is created or returned
    • Weekdays 6:30 AM, overdue sweep
    • @Relay in any thread
    Works in
    RFIsDrawingsSpecificationsCorrespondence
  • Vetta

    Submittal Reviewer

    Working

    Checks submittals against spec sections and the drawings before they reach the design team. Flags every deviation with the paragraph it breaks.

    Now

    Checking 23 73 13-01 AHU product data against spec

    Autonomy
    Suggest
    Triggers
    • A submittal is received from a sub
    • @Vetta in any thread
    Works in
    SubmittalsSpecificationsDrawings
  • Atlas

    Document Controller

    Idle

    Ingests drawing and spec sets, splits and names sheets, slip-sheets revisions, clouds the deltas, and keeps everyone on the current set.

    Next

    Watching for new drawing and spec uploads

    Autonomy
    Autonomous
    Triggers
    • A drawing or spec set is uploaded
    • A transmittal is received
    Works in
    DrawingsSpecificationsDocumentsCloseout
  • Scribe

    Field Reporter

    Working

    Builds the daily log from crew check-ins, gate deliveries, weather, photos, and voice notes. Takes meeting minutes and assigns the action items.

    Now

    Compiling today’s daily log from 14 sources

    Autonomy
    Act with approval
    Triggers
    • Daily at 3:30 PM, draft the daily log
    • A meeting recording is uploaded
    Works in
    Daily LogMeetingsPhotosTimesheets
  • Tempo

    Scheduler

    Needs review

    Keeps the schedule honest. Reads daily logs and delivery data, forecasts slips, and models recovery options on the critical path.

    Ready

    Recovery options for the L24 pour delay are ready

    Autonomy
    Suggest
    Triggers
    • Mondays 5:00 AM, three-week lookahead
    • A weather or delivery delay is logged
    Works in
    ScheduleDaily LogWorkforce Planning
  • Ledger

    Cost Controller

    Working

    Reconciles invoices against schedules of values, prices change events, tracks commitments, and forecasts cost at completion.

    Now

    Reconciling 14 subcontractor invoices against SOV

    Autonomy
    Act with approval
    Triggers
    • A subcontractor invoice is submitted
    • A change event is created
    • Monthly on the 20th, pay app prep
    Works in
    BudgetCommitmentsChange EventsInvoicing
  • Sentinel

    Safety Officer

    Working

    Scans site photos and 360 captures for hazards, pre-fills JHAs, tracks certifications, and opens observations with the photo as evidence.

    Now

    Reviewing 212 site photos from this morning’s walk

    Autonomy
    Act with approval
    Triggers
    • Photos or a 360 capture are uploaded
    • Daily 6:00 AM, certification expiry check
    Works in
    ObservationsIncidentsPhotosForms
  • Plumb

    Quality & Punch

    Idle

    Turns walkthrough video into punch items with locations and trades, runs inspection checklists, and verifies closed items against new photos.

    Next

    Next: L6 corridor walkthrough at 1:00 PM

    Autonomy
    Act with approval
    Triggers
    • A walkthrough video is uploaded
    • A punch item is marked ready for review
    Works in
    Punch ListInspectionsPhotos
  • Quarry

    Estimator & Buyout

    Working

    Runs quantity takeoffs from drawings, levels bids, finds scope gaps between bidders, and drafts buyout recommendations.

    Now

    Leveling 6 bids for package 05 12 00 Structural Steel

    Autonomy
    Suggest
    Triggers
    • A bid is received
    • Drawings are added to a pursuit
    • @Quarry in any thread
    Works in
    EstimatingBid ManagementPrequalification
  • Beacon

    Owner Reporting

    Paused

    Assembles the monthly owner report: progress narrative, photos, cost and schedule summaries, and the risk register, led by the decisions the owner needs to make.

    Paused

    Paused while the owner’s new report format is set up

    Autonomy
    Suggest
    Triggers
    • Monthly on the 25th, owner report draft
    Works in
    InsightsPhotosBudgetSchedule
  • Procurement Expediter

    Role template

    Tracks lead times, confirms deliveries, and flags long-lead risk.

    Add it to any project and give it a name

  • Closeout Coordinator

    Role template

    Collects warranties, O&M manuals, and attic stock from every trade.

    Add it to any project and give it a name

Need a role that isn’t here? Describe the job in plain words and Fulcrum drafts the agent for you.

Anatomy of a run

Watch an agent think, step by step.

When an RFI comes back, Relay reads it, finds the location on the drawings, searches every past answer for precedent, and drafts a response. Sending it to the structural engineer is a message to another company, so it waits for Elena’s approval.

  • Every tool call is visible, with its inputs and results
  • Precedent and references cited, never invented
  • Gated steps stop and wait for the right person

Relay Working

Drafting a response package for RFI-142

  1. rfi.read Read the question and photos PH-8811 and PH-8812
  2. drawings.locate Located Grid C/7 on S-224 and detail 7/S-501
  3. rfi.search_precedent Found RFI-118, an embed conflict at L18 answered Jun 12. 91% similar.
  4. rfi.draft_response Drafted a suggested resolution: shift EP-7 six inches east and add two #8 trim bars
  5. email.send Send to Bright & Lund Structural Waiting for approval
Runs with Relay’s permissions run-31882

Autonomy

You decide how much each agent does on its own.

Turn the dial per agent and per tool. A new agent might start at Suggest, then earn Act with approval once its drafts are landing. Company guardrails always win, and agents can be made stricter, never looser.

The agent builds a plan and runs it the moment the right person approves it from their Inbox.

  1. 1 Agent plans
  2. 2 Person approves
  3. 3 Agent runs it

Relay packages the RFI-142 response and sends it to the engineer once Elena approves.

Guardrails

Hard lines every agent respects.

Guardrails apply to every agent in the company. Admins set them once in AI governance; individual agents can be stricter, but never looser.

People only

No agent, at any autonomy level

  • Commit or release money Approve invoices, execute change orders, issue purchase orders.
  • Sign on behalf of a person Signatures always belong to the accountable person.
  • Change permissions or invite users Only people with Admin can change who has access.
  • Delete records Agents can void or archive with a reason, never hard delete.

Ask first

Agent proposes, a person approves

  • Send messages to other companies Email, RFI distribution, transmittals, and notices.
  • Draft financial changes over $25,000 Budget modifications, change event pricing, and forecasts.
  • Modify the baseline schedule Lookaheads and forecasts are fine; the baseline is not.
  • Publish drawing and spec sets Makes a new set current for every user.

Allowed

Inside the agent’s tools and projects

  • Create and update internal records Within the tools and projects the agent can access.
  • Search drawings, specs, and past answers Read anything its permission template allows.
  • Draft documents and messages RFIs, logs, reports, and replies, left for review or sent per policy.
  • Remind and assign internal tasks Nudge people on your team and log what it asked for.

Agent studio

Describe the job. Fulcrum drafts the agent.

Write what you need, the way you would onboard a new hire: “Track long-lead equipment on Harbor Point and warn me if anything will arrive after it’s needed.” Fulcrum picks a role, writes the instructions, and suggests access, then you review it step by step.

  • Role, identity, access, autonomy, triggers, and review
  • Triggers on events, schedules, or an @mention
  • Agents appear in the directory and can be @mentioned and audited
The Create an agent screen in Fulcrum, with a plain-language job description, role templates, and a preview of the drafted agent.

Performance & spend

Know what every agent is worth.

See actions taken, hours returned to the team, how often proposals are approved as written, and escalations to people. Compute budgets, reasoning tiers, and a company-wide cap keep spend predictable.

  • Approval rate and accuracy by agent
  • Hours returned to the team each week
  • Monthly caps with alerts at 80% of any budget
The Fulcrum agent roster with actions this week, hours returned, approval rate, escalations, and compute spend.

FAQ

Questions about agents

Have a question that is not here? Ask us

Which agents come with Fulcrum?

Fulcrum starts you with role templates for an RFI Coordinator, Submittal Reviewer, Document Controller, Field Reporter, Scheduler, Cost Controller, Safety Officer, Quality & Punch, Estimator & Buyout, Owner Reporting, Procurement Expediter, and Closeout Coordinator. You can also describe a job in plain words and Fulcrum drafts a new agent.

Who is responsible for what an agent does?

Every agent has a supervising person. The agent works inside that person’s access and can never exceed it, its proposals route to the right approver, and every action is attributed to the agent in the audit log.

Can agents talk to people outside our company?

Only with approval by default. Sending email, distributing RFIs, transmittals, and notices to other companies is an “ask first” action. You can pre-approve specific cases, such as reminders to the design team.

How do we control what agents cost?

Each agent has a compute budget and reasoning tier (Deep, Balanced, or Fast). You set a monthly company cap and get alerts when any agent reaches 80% of its budget.

Can we pause an agent?

Yes. Any supervisor can pause their agent, and admins can pause every agent across the company with one switch. Running steps finish and nothing new starts until you resume.

Put an agent on your next RFI.

We will show you Relay, Scribe, Ledger, and the rest working on projects like yours, and help you choose where to start.