Build your own document intelligence pipeline

A self-serve API for developers to parse, extract, evaluate, correct, and deploy document AI applications.

IDP Forge

Build, Test and Document, Pipelines Without Writing Code

Studio is the no-code workspace for IDPForge. Design pipelines, bind schemas and taxonomies, test on real documents with per-stage output, publish a version, and watch your jobs, reviews, and costs in one place. Engineering only needs the endpoint.

Try Studio Now

Pipelines / Invoice Processing Draft Autosaved

Pipeline stages

1ParseLayout, OCR, language

2SplitSeparate document bundles

3ClassifyRoute by document type

4ExtractFields against a schema

Parse

Reads layout, text and language

Layout detectionAzure Document Intelligence · Layout

OCRAzure Document Intelligence · Read

Language detectionLLM

Extract

Reads values against a schema

SchemaFrom Library

Invoice schemav34 fields

Invoice NumberText

Vendor NameText

Invoice DateDate

Total AmountCurrency

Model

GPT-4o VisionFast$$

Confidence threshold0.65

sample-invoice.pdf Run against Draft Run TestRunning…

Globex Corporation 1200 Industrial Way Rotterdam, NL 3011 INVOICE Invoice no. INV-4471 Invoice date March 14, 2026 Bill to Acme Logistics Ltd. 88 Harbour Street Rotterdam, NL 3012

Description Qty Unit price Amount Hydraulic pump assembly 2 3,200.00 6,400.00

Pressure valve kit 4 800.00 3,200.00

Installation & calibration 1 1,900.00 1,900.00

Subtotal 11,500.00 Tax (8.5%) 977.50

Total due $12,477.50

Vendor Name

Invoice Number

Invoice Date

Total Amount

Stage outputDraft

ParseSplitClassifyExtract

Run a test to see each stage's output

Invoice NumberINV-44710.99

Vendor NameGlobex Corporation0.97

Invoice Date2026-03-140.96

Total Amount12,477.50 USD0.93

4 fields · all above the 0.85 threshold

Versions

Draftv3 DraftPublished Tested on sample-invoice.pdfJust now Publish versionPublishing…Compare

v2PublishedOct 28Compare

v1PublishedOct 21Compare

Published versions are immutable. Drafts never affect live pipelines.

API endpointReady

Pipeline IDpl_inv_7Kd29xQ

Versionv2

curl -X POST \
https://api.us.idpforge.cloud/v1/jobs \
-H "X-API-Key: $IDP_API_KEY" \
-F "pipeline_id=pl_inv_7Kd29xQ"

Pipeline PublishedVersion 3 is ready for API calls

Infrrd is Chosen and Trusted By

Studio Is Where Your Document Pipelines Come to Life

Document AI projects stall between the prototype and production. Configuration lives in code, testing is ad hoc, and business users cannot take part. Studio gives builders, operators, and developers one shared workspace. It is the no-code control plane for IDPForge, where pipelines, schemas, and taxonomies are designed and versioned, documents are tested, jobs are monitored, exceptions are reviewed, and keys, integrations, members, and billing are managed.

01 / FEATURED WORKFLOW PIPELINE CONNECTED

Design. Test.
Publish your workflow.

Start from a Predefined pipeline or a blank one, bind schemas and taxonomies from the Library, test on real documents with per-stage output, publish a version, then copy the endpoint into your code or the API Playground. Watch Jobs and Insights, and work exceptions in Reviews.

IDP FORGE / STUDIO PIPELINEWORKFLOW 01 / 01

01 / CONNECT INPUT

Build your workflow

▣Predefined or blankChoose a starting pipeline

⊞Library bindingsAttach schemas and taxonomies

▤Test documentsInspect per-stage outputs

02 / PROCESS

STUDIO WORKSPACE

Ready for workflow

03 / SEND RESULTS

Ship & monitor

✓Publish versionCreate a pipeline version

</>Use the endpointCode or API Playground

◉Monitor & reviewJobs, Insights and Reviews

CORE CAPABILITIES / STUDIO

Everything You Need to Take a Pipeline from Idea to Production

One workspace for building, testing, versioning, running and monitoring, with no code required.

Predefined Pipelines

Start from ready-made pipelines for Mortgage, Insurance, Accounts Payable and more, as parse only, split and classify only, extract only or full, then duplicate to edit.

Studio puts the whole pipeline lifecycle in one place, so teams ship document automation without waiting on engineering

Document Automation for Operations Teams

An operations lead at a lender or insurer duplicates a Predefined pipeline, adjusts the schema from a sample document, tests on last week's documents and publishes, all without engineering help.

A No-Code Setup with Google Drive

Connect a watched Google Drive folder your team already uses, switch on review with a response-time target, and collect results in an output folder as JSON plus an XLSX file.

Testing Models and Prompts Before You Publish

Change a model or an instruction on a draft, rerun the Test tab and compare the output of every stage, or run the same document against two versions.

Changing Live Pipelines Safely

Edit in drafts, test, publish and pin versions. If a change does not work out, roll back by cloning an earlier version.

Tracking Quality and Cost

Watch throughput, confidence, flagged fields, and credits by pipeline and stage in Insights, so you know what each pipeline delivers and what it costs.

One Workspace for Builders, Operators and Developers

Builders design in Pipelines and the Library, operators and supervisors work exceptions in Reviews, developers use the Playground, keys and webhooks, and admins manage billing, bring-your-own-key setup and the audit log.

Try Studio Now

Pick the Right Engine for Every Sub-Stage

Each sub-stage in Parse has its own on/off switch, engine, model and optional confidence threshold. Use the engine that is strongest for each one, and change it later without writing code.

Choose the model for each sub-stage. The picker filters by Vision, Reasoning and Fast, and shows a relative cost tier from $ to $$$.

Layout

Vision Fast

OCR

Fast Reasoning

$$$

Chunking

Fast Vision

Bring your own LLM keys. Use your own keys for the LLM-based sub-stages. Azure Document Intelligence usage is always billed in credits.

OpenAI key connected LLM stage

Claude key connected LLM stage

Azure Doc Intelligence credits

Billing note: Azure Document Intelligence is always billed in credits.

Built to recover. When a model call fails, the stage retries automatically (3 attempts with backoff) and rotates provider keys and deployments.

Model call failed

retry trigger

Try 1 Try 2 Try 3

Provider key rotated · deployment switched

auto recover

Stage completed successfully

recovered

STUDIO / PROCESS FLOW

How Studio Works

Built to Plug into Your Stack

Submit a file to a parse-only pipeline with one call:

curl -X POST \
  https://api.us.idpforge.cloud/v1/jobs \
  -H "X-API-Key: $IDP_API_KEY" \
  -F "files=@policy-handbook.pdf" \
  -F "pipeline_id=$PARSE_PIPELINE_ID"

Build Your Parse Pipeline Today!

Build document AI that learns, proves and improves

Get 15k credits for free

Frequently Asked Questions

Start Free

Does it handle scanned and handwritten documents?

Scans and photos, yes. OCR runs on page images. Handwriting quality depends on the engine you choose (Azure Document Intelligence or a vision LLM). There is no separate handwriting mode.

‍

Do I get Markdown or JSON?

Both. You get JSON with whole-document Markdown, per-page Markdown and typed blocks. Post Processing can also render CSV.

Are tables preserved?

Yes. Tables are detected as table regions and output as Markdown tables.

Can I get bounding boxes?

Yes. Every block has a bounding box, expressed as percentages of the page.

Can I chunk for my vector database?

Yes. Choose semantic, page or fixed-token chunking, with configurable size and overlap.

Which OCR engine is used?

Azure Document Intelligence by default. You can select a vision LLM per pipeline.

Is there a page limit?

There is no hard page limit. The file size limit is 100 MB.

Can I use my own LLM key?

Yes, for the LLM-based sub-stages. Azure Document Intelligence usage is billed in credits.

How long is my data kept?

Jobs, results and documents are kept for 24 hours after submission, then deleted.

Build your first document AI workflow in minutes.

Start building