Documents12 companies
12 companies, 12 swept. The median identity score is 84 of 100. Rows are ordered by readiness; rows not yet rated sit last.
12 companies · 12 swept · last sweep 2026-09-16
84/100
median
Ranked by readiness
- #1
Postman
postman.comDesigns, tests, and manages APIs with integrated documentation, mocking, monitoring, and workflow automation.
bots in✓ llms.txt100/100
#1 of 12 in Documents - #2
GitBook
gitbook.comHosts documentation with tools to detect stale content and verify accuracy against product changes.
- #3
Rossum
rossum.aiExtracts data from transactional documents, validates against master data, and routes to downstream systems.
bots in— llms.txt84/100
#3 of 12 in Documents - #4
Instabase
instabase.comExtracts and validates data from complex document packets using multi-model AI agents with cross-document understanding.
bots in— llms.txt78/100
#4 of 12 in Documents - #5
Dbt labs
getdbt.comTransforms raw data into tested, version-controlled SQL models for analytics and AI pipelines.
- #6
Mindee
mindee.comExtracts structured data from documents via API, supporting OCR, classification, splitting, and cropping across any format or language.
bots in✓ llms.txt69/100
#6 of 12 in Documents - #7
Nanonets
nanonets.comExtracts data from business documents and automates enterprise workflows like accounts payable, order management, and claims processing.
bots partly— llms.txt59/100
#7 of 12 in Documents - #8
Affinda
affinda.comExtracts and validates data from documents using AI, handling handwriting, tables, and multiple formats.
bots partly✓ llms.txt58/100
#8 of 12 in Documents - #9
Sensible
sensible.soExtracts structured data from documents using hybrid AI and rule-based methods, returning validated JSON.
bots in— llms.txt56/100
#9 of 12 in Documents - #10
DocuPanda
docupanda.ioExtracts structured data from documents of any layout, language, or format using machine learning.
bots in✓ llms.txt54/100
#10 of 12 in Documents - #11
Swimm
swimm.ioAnalyzes codebases to extract architecture, dependencies, and business logic for modernization and migration projects.
bots partly✓ llms.txt34/100
#11 of 12 in Documents - #12
Klarity (check domain)
klarity.comNo line written yet.
bots out— llms.txt8/100
#12 of 12 in Documents
How to read a row
- swept
- Read by a crawler: HTTP and parsing, no model call. Every row, every week.
- measured
- The full analyzer run, asked of four engines. Shown only where the company agreed to show it.
Can a retrieval engine find, resolve and quote this site? Four parts, each read by the sweep, each shown beside the total.
Entity 25 · Machine-readable 35 · Retrieval access 20 · Footprint 20
A part that was never read is left out and the total is rescaled to what was. It is never counted as zero.