*** September 2026 Major Release ***Read and watch
Document type

Extracting data from flood certifications

Flood determination vendors complete FEMA's Standard Flood Hazard Determination Form for every federally backed mortgage, one standard layout filled by each vendor's system. Lenders receive one for every loan in the pipeline, as a PDF delivered to the loan origination system.

Closing needs the flood zone, the special flood hazard area answer, the NFIP community and the map panel. A yes on the hazard area question makes flood insurance a condition of the loan, and the lender tracks the coverage for its life.

Page 1 of a sample Flood Certification, with extracted values outlined
10,066Markdown characters
75parse blocks
40fields extracted
The problem

What makes flood certifications hard

The answer is a checkbox

Whether the building sits in a special flood hazard area is a YES or NO mark, alongside checkboxes for program type and insurance availability.

Short codes carry the answer

The flood zone, community number and map panel are short codes, such as zone AE, each beside a long printed caption.

A dense ruled form

Lettered sections and numbered boxes pack loan, community, map and determination details into one tightly ruled page of small type.

How it works

Parse, extract, verify

1

Parse

Parse turns the document into reading-order Markdown and a hierarchy of blocks (text, tables, figures), and grounds each block to its exact location on the page.

2

Extract

You define the fields in a JSON schema, and Extract returns their values in a consistent, structured format, each linked back to where it appears in the Markdown.

3

Verify

Each value links back to where it appears, down to the character range in the Markdown, and the page and bounding box in the source document, so every result can be verified.

Worked example

One flood certification, end to end

About this document: A completed FEMA Standard Flood Hazard Determination Form, prepared by a flood determination vendor for a residential mortgage. Three portrait pages: the determination form, a fee slip and the borrower notice with its applicable box checked. Page 1 is featured. Every borrower detail and identifier was replaced with stand-ins.

Processing objective: The objective is to read the determination itself. It names the community the property sits in, its flood zone, whether it lies in a special flood hazard area and when that was determined. Each value grounds to its own numbered box of the form.

Demonstration fields: NFIP community, NFIP community number, Flood zone, In special flood hazard area, Date of determination

The document

3 of 3 pages
  • Page 1 of the sample Flood CertificationPage 1shown below
  • Page 2 of the sample Flood CertificationPage 2
  • Page 3 of the sample Flood CertificationPage 3

Where each value came from

Page 1 of the sample Flood Certification, with every featured field outlined
NFIP communitynfip_community.community_name
JACKSON, TOWNSHIP OF
The region of the sample Flood Certification containing NFIP community, with the extracted value outlined
extraction_metadata["nfip_community.community_name"]
{
  "value": "JACKSON, TOWNSHIP OF",
  "page": 1,
  "range": {
    "end": 1189,
    "start": 1143
  },
  "box": {
    "xmin": 0.02851,
    "ymin": 0.30056,
    "xmax": 0.34153,
    "ymax": 0.3337
  }
}
NFIP community numbernfip_community.community_number
340375
The region of the sample Flood Certification containing NFIP community number, with the extracted value outlined
extraction_metadata["nfip_community.community_number"]
{
  "value": "340375",
  "page": 1,
  "range": {
    "end": 1294,
    "start": 1260
  },
  "box": {
    "xmin": 0.67765,
    "ymin": 0.3006,
    "xmax": 0.97095,
    "ymax": 0.33371
  }
}
Flood zonenfip_map.flood_zone
X
The region of the sample Flood Certification containing Flood zone, with the extracted value outlined
extraction_metadata["nfip_map.flood_zone"]
{
  "value": "X",
  "page": 1,
  "range": {
    "end": 1814,
    "start": 1434
  },
  "box": {
    "xmin": 0.02868,
    "ymin": 0.35639,
    "xmax": 0.9714,
    "ymax": 0.44144
  }
}
In special flood hazard areain_special_flood_hazard_area
NO
The region of the sample Flood Certification containing In special flood hazard area, with the extracted value outlined
extraction_metadata["in_special_flood_hazard_area"]
{
  "value": "NO",
  "page": 1,
  "range": {
    "end": 2757,
    "start": 2397
  },
  "box": {
    "xmin": 0.02914,
    "ymin": 0.57989,
    "xmax": 0.97074,
    "ymax": 0.63384
  }
}
Date of determinationdetermination_date
September 05, 2023
The region of the sample Flood Certification containing Date of determination, with the extracted value outlined
extraction_metadata["determination_date"]
{
  "value": "September 05, 2023",
  "page": 1,
  "range": {
    "end": 4084,
    "start": 4066
  },
  "box": {
    "xmin": 0.75401,
    "ymin": 0.89378,
    "xmax": 0.97062,
    "ymax": 0.91147
  }
}

How to try it yourself

Everything on this page is reproducible. The sample, its schema, and the Parse and Extract API outputs are published. You can repeat the same two calls from whichever surface you already build on.

  • Claude Skilldescribe the job; the agent writes it
  • CLIno code at all
  • MCPexpose ADE docs as an agent tool
  • REST APIany language
  • Pythonlandingai-ade
  • TypeScriptlandingai-ade
Why LandingAI?

Documents into data

Accurate

The best accuracy on the difficult documents other tools get wrong, such as messy scans, complicated tables, checkboxes and handwriting.

Auditable

Every answer cites its sources. Values come back with an audit trail (page, bounding box, character range) so a human can review them.

Agentic

Applies multi-step reasoning, and plans before it acts. Handles documents it has never seen before and adapts to variations.

API-first

Composable APIs that drop into any tech stack and can be called from anywhere. Easy to build on and embed in your pipelines and products.

Affordable

Cost-competitive rates with complete price transparency. Spend controls before you run, and every job reports its exact cost.

Enterprise-grade

Built for production and scale from day one. Fully observable and monitored, running securely in our cloud or yours.

Built for high-volume, high-throughput production

  • Zero data retention
  • Priority rate limits
  • Enhanced support
  • VPC and on-prem deployment

Available on Team and Enterprise plans.

Compare plans
Capabilities

Flood Certification processing highlights

Flood zone
Special flood hazard area answer
NFIP community name and number
Map panel and effective date
Insurance availability
Program type checkboxes
Letter of map change details
Determination date
Loan and order numbers
Borrower notice selection
No per-vendor templates
Bounding box for every value
FAQs

Questions, answered

Yes. Parsing writes every checkbox into the Markdown in one standard form, marked checked or unchecked beside its label. A field for the hazard area answer comes back as the box marked on the form.

Yes. Describe the community name, community number and map panel as fields in your schema. Each comes back from its own numbered box, grounded to the box that prints it.

No. A schema names the fields you want and describes them in plain language. Extraction reads the parsed form for meaning, so one schema covers each vendor's completed version of the FEMA form.

Every extracted value carries the character range it was quoted from in the parsed Markdown. The Ground API maps that range to a page and a bounding box, so a reviewer sees each value in the box that printed it.

Start extracting flood certification data

Reliable, structured outputs with full traceability in minutes