Upload a certificate of insurance (COI) PDF and extract the insured, producer, holder, and every coverage line with its policy number, dates, and limits. Free.
The full guide: ACORD 25 certificate of insurance, limits and insurers
Need to scale? Create an API key, then run this from your own code or an agent.
Create an API keyFree account required
Upload a file or pick a sample, and see the fields come back.
No signup · nothing stored
The named insured and its address, the producer or broker that issued the certificate, the certificate holder and its address, the certificate number and issue date, the insurers affording coverage, and the description of operations — plus the full schedule of coverages.
Yes. The coverages return as a structured table with one row per coverage line and named columns for the fields on each line — the coverage type (such as Commercial General Liability, Commercial Auto, Workers Compensation, Umbrella/Excess, or Employers Liability), the insurer or carrier affording it, the policy number, the effective and expiration dates, and the limits of liability — so they export as CSV rows rather than one text blob.
Yes. It handles the US ACORD 25 Certificate of Liability Insurance layout with its lettered insurers and NAIC codes, and also EU and UK broker-issued certificates. Field synonyms cover German and French labels such as Versicherungsnehmer, Versicherer, Versicherungsverträge, and titulaire du certificat, and dates are read against EU formats like 01.01.2026 as well as US formats.
Yes. The limits of liability are captured per coverage line as written on the certificate — for example Each Occurrence and General Aggregate for general liability, the Combined Single Limit for auto, or the EL Each Accident and disease limits for workers compensation — so each row keeps the limits that belong to its own policy.
PDF only, up to 10MB and 100 pages. The certificate is processed via the Talonic API for extraction only, is not retained for training, and is not shared.
The tool reads a single document. The platform reads the whole estate once and keeps it queryable — the same engine, with a memory.
See document data extraction if you run this for underwriting and claims teams, or the extraction API if you are building it in.