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

Request-to-Estimate Drafter

The Request-to-Estimate Drafter is an AI agent in FieldCamp that fires when a request is created and drafts the estimate scope from it — matching the described work to your price book, checking similar past jobs for sanity, stating its assumptions, and waiting for your approval before anything exists officially.

Triggers on new requestsPrices from your bookDrafts behind approval

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 — because the gap between "request received" and "estimate sent" is where competitors get hired.

Estimates are lost to speed more than price: the customer who described the job on Tuesday signs with whoever quoted by Wednesday. The information to quote was in the request the whole time — what was missing was an hour of someone's evening to turn description into line items.

The drafter spends that hour in seconds. From the request's own words it builds the scope: matched price-book line items, quantities where stated, similar past jobs as a sanity check, and explicit assumptions where the request is vague — "assumed single-story access" — so your reviewer knows exactly what to verify. The draft waits in your approval queue; estimates leave the building on a human's tap.

What it actually does

Trigger: Request created

  1. 1

    Reads the new requestrequest_created

    Fires on creation, with the customer's own description of the work.

  2. 2

    Matches your line itemsmatch_price_book

    Described work mapped to your actual catalog — your names, your rates. Gaps get flagged, not guessed.

  3. 3

    Sanity-checks against historycheck_similar_jobs

    Similar past jobs inform quantities and catch the scope you'd otherwise forget.

  4. 4

    Drafts behind approvalcreate_estimate

    The estimate and any follow-up task draft into your approval queue — stated assumptions on top.

What you get

A priced, assumption-stated draft estimate waiting for review minutes after the request arrives — same-day quoting as the 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

Garage floor coating · web form

86% confidencePending

Details

Draft

$2,150 · 3 line items

Summary

Drafted from the request: two-car garage epoxy coating, ~400 sq ft assumed from "standard two-car." Matched 3 price-book items; similar job #JOB-1980 supports the quantity. Assumption flagged: square footage unverified.

DismissApprove estimate

Estimate and task creation are approval-gated in the template — drafts wait for your tap, always.

By trade

Same agent, configured to how your vertical actually works.

Painting

Room counts and surface hints in the request drive the assumed quantities.

Fencing

Linear footage stated or assumed, with the assumption flagged for the site check.

Questions, answered

What if the request doesn't have enough to price?

The draft says so — priced for what's stated, explicit assumptions for what isn't, and a flagged list of what to confirm. A draft that knows its gaps still beats a blank page Thursday night.

Where do prices come from?

Your price book, only. Work that matches no line item gets flagged for a human price, never invented. Your margins are configuration, not model output.

How is this different from the Estimate Drafter template?

Same family, different depth: this one drafts the scope from the request text; the Estimate Drafter digs further into similar-jobs analysis before drafting. Shops usually pick one based on how much history they have in FieldCamp.

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.