Choose your plan
Home About Features Pricing Choose your plan

  About Mapsy

What is a document worth if someone still has to retype it?

Every invoice, contract and form already contains the data your systems need. It is locked in a layout meant for human eyes. Mapsy exists to read that layout, return typed fields with a confidence score on each, and make sure a person sees only the values the model is unsure about.

01 / 04 — The problem

OCR gave teams text. It never gave them records.

Character recognition turned scans into strings, and left the hard part to people: find the total, decide which date is the due date, check that the tax adds up, paste it into the ledger. Mapsy was built for the step after the text.

  • A.01

    The total is a string, not a number

    “4,218.60 USD” and “USD 4.218,60” are the same figure. A text dump leaves your team to normalise currency, separators and dates by hand.

  • A.02

    Nobody knows which values to doubt

    When every field arrives looking equally certain, reviewers either check everything or trust everything. Both are expensive.

  • A.03

    Corrections vanish into a spreadsheet

    Someone fixes a tax figure at month end. Weeks later an auditor asks who, when and from what value. The answer is a shrug.

  • A.04

    Automation scripts rot quietly

    Hand-written glue between the inbox and the ledger breaks when a vendor changes its template, and nothing tells you until a bill is missing.

02 / 04 — Principles

Four design constraints we do not trade away

Each one is a testable property of the product, not a slogan.

P1

Typed output, always

A field is a decimal, a date or an enum, never a paragraph of text. Line items come back as arrays so the next system can consume them without parsing.

invoice.total: decimal · due_date: date · line_items: array
P2

Uncertainty is a first-class value

Every field carries its own confidence score. You set the threshold per field or per document type, and only what falls under it asks for a human.

auto_approve_if: confidence.min ≥ 0.90
P3

Validate against arithmetic, not vibes

Rules such as subtotal + tax = total catch a misread digit that a confidence score alone might let through. A failed rule names itself in the review queue.

rule: subtotal + tax == total → else route(review)
P4

Nothing changes without a record

Each run stores the input, the model version, the workflow version, every edit as a before and after, and the approver, in UTC.

run.stamp: model v3.2 · workflow v14 · hash 9c41e7

03 / 04 — How it is built and supported

A pipeline you can open, and a support inbox with a person behind it

Mapsy is four stages (read, route, review, record), and each one exposes its inputs, thresholds and output so you can see why a document went where it did.

  • Prebuilt models for invoices, receipts, contracts and forms; custom models trained on your own labelled samples.
  • Workflows are versioned drafts. Nothing reaches QuickBooks or Salesforce until you publish.
  • Support runs by email at contact@mapsyai.com; Orchestrate accounts also get a dedicated success manager.
  • Status and API pages are linked from the footer of every page.

  Pick a ceiling

500 pages, 10,000 pages, or no cap at all

Plans are sized by monthly volume, so the cost tracks your inbox rather than your headcount.

See the three ceilings

04 / 04 — Where it is going

The direction, stated as engineering goals

No dates promised here: each item is a direction we are working toward, listed so you can judge the fit.

Models

Sharper reads on messy layouts

Better handling of skewed scans, multi-page line-item tables and handwritten approvals, with confidence scores that stay calibrated as accuracy improves.

Ongoing

Workflows

Richer rules and approvals

More condition types in the builder, reusable rule sets across workflows, and approval steps that escalate when a reviewer has not responded.

In design

Connectors

More places for clean fields to land

Additional accounting, CRM and storage connectors alongside the 40+ available on Automate, each stamped into the run history.

Rolling

Have a document type you need read? Write to contact@mapsyai.com with a description of the fields you need.

“What convinced us was the audit log. We could open one run and see the input, the model version, the edit and who confirmed it. That is a conversation with an auditor that takes a minute.”
— Odalys M., Finance Director, Kestrel Print & Pack

  Next

Stop retyping. Start routing.

Pick the volume ceiling that fits your inbox, connect it, and publish your first workflow.

Choose your plan