facebook-pixel
Field ops on autopilot →AI Dispatcher → 1:1 demo

Estimate Drafter

The Estimate Drafter is an AI agent in FieldCamp that activates on new service requests, analyzes what's being asked, searches your past similar jobs for real quantities and pricing patterns, and drafts a detailed estimate — exact catalog items, quantities, unit prices, and one-line descriptions — that waits for your approval before sending.

Triggers on new requestsSearches similar jobsDrafts detailed estimates

A real template from the FieldCamp marketplace, configured on your operation. Setup included in your plan.

About this agent

Where it came from

Ships in the FieldCamp agent marketplace — the heavyweight drafter for shops whose job history already knows what things cost.

Your past jobs are your best estimator: somewhere in last year's history is almost exactly this job, with the real quantities and the price that won. Experienced estimators carry that history in their heads — which is why estimates bottleneck on experienced estimators.

This drafter carries it in the database. For each new request it searches your completed jobs for the closest matches, reads what they actually took, and builds the estimate from evidence: exact catalog names, quantities the history supports, your unit prices, a one-line description per item. The draft cites its precedents and waits in the approval queue — your judgment, applied to a draft that did its homework.

What it actually does

Trigger: Request created

  1. 1

    Analyzes the requestrequest_created

    What's being asked, in the customer's words — service, scale, and any specifics.

  2. 2

    Finds the precedentssearch_similar_jobs

    Your closest completed jobs — what they actually took in items, quantities, and hours.

  3. 3

    Builds evidence-based line itemsbuild_line_items

    Exact catalog names, quantities from history, your unit prices, one-line descriptions.

  4. 4

    Drafts behind approvalcreate_estimate

    The full estimate waits in your queue, precedents cited — approve, adjust, send.

What you get

Detailed estimates drafted from your own job history — precedents cited, approval-gated, same-day by default.

A run, as you’d see it

Agent runs land on a timeline — what fired, what the agent found, and the action waiting for a human. This is that screen.

Request received

Water heater replacement · call-in

88% confidencePending

Details

Precedents

4 similar jobs found

Summary

Drafted a $1,840 water heater replacement from four similar completed jobs: 50-gal unit at your catalog rate, 3.5 labor hours (history median), haul-away and permit lines included — #JOB-1762 nearly identical.

DismissApprove estimate

Estimate creation is approval-gated — every draft waits for your tap. The agent cites its precedent jobs so review takes a minute.

By trade

Same agent, configured to how your vertical actually works.

HVAC

Replacement quotes pull unit specs from the equipment history into good-better-best tiers.

Plumbing

Repair-versus-replace precedents both surface, priced, when history shows the fork.

Questions, answered

What does it need from my job history to work well?

Some volume of completed jobs with line items — six months of FieldCamp history is plenty; migrated history works too. Below that, it leans on your price book and flags lower confidence honestly.

Will two similar requests get identical estimates?

Similar, not identical — each draft re-derives from the request's specifics and the closest precedents. Consistency is the point: your pricing stops depending on who drafted and how tired they were.

Can it send the estimate to the customer?

Only after your approval — creation is gated in the template. One tap from your phone approves and sends, which is why same-day survives busy weeks.

Have an agent idea we haven’t built?

The ideas section of this library exists because customers keep asking "could it just…?" Bring yours. If it should exist, we build it — and it ships as a template like this one.

No demo deck. Just your business and ours.