Case study · AI automation agency

Document AI for an Irish life-insurance brokerage

An n8n pipeline reads each signed policy pack with OCR and GPT, checks it across documents, and puts it in front of ops staff for review before it goes to the insurer.

ClientA life-insurance brokerage in Ireland
EmployerPrevious company (an AI automation agency), as a contract AI engineer
My partBuilt the AI pipeline. Owned the React review dashboard (75% of its commits).
UsersThe brokerage's operations team, working with 47 advisors across 7 sales boards

Problem

When a client signs on DocuSign, the brokerage has a pack of documents to check before the policy can go to the insurer: the fact find, the application, the statement of suitability and the direct debit mandate. Someone had to read them, compare values across them, and check the premium against what the advisor recorded on the sales board. That manual pass took an estimated 20-30 minutes per policy.

Constraints

Architecture

  1. Signed envelopeDocuSign webhook
  2. Match and createFind the client and advisor on the sales boards, create the policy, drop duplicate envelopes
  3. OCRMistral OCR on every document
  4. Extraction agentGPT classifies each document and fills a structured schema through an n8n output parser
  5. Validation agentsCross-document checks for identity, underwriting risk and financial details, each issue with a severity
    Deterministic checksIBAN checksum (ISO 7064 mod-97), premium within 1 euro of the sales board, duplicate guards
  6. Supabase PostgresPolicies, extracted fields and flags
  7. Review dashboardOps staff confirm, work the flags and send documents out
  • LLM or OCR step
  • Plain code
  • Human decision
The model extracts and flags. Code decides anything with a single right answer, and a person approves the result.

What I did

I built the pipeline in n8n. Intake listens for signed DocuSign envelopes, matches each one to a client and advisor on the brokerage's sales boards, and creates the policy record. Each document then goes through Mistral OCR and a GPT extraction agent that works out which document it is looking at and returns the fields as structured output.

On top of extraction I designed the cross-document validation. Separate agents compare identity details, underwriting risk answers and financial figures across the documents in a pack. Within the first 7 months they raised 3,219 flags on 1,443 policies, including 100 critical age-band cases that would otherwise have reached an insurer.

I kept the checks that have one right answer in plain code. IBANs are validated locally with the ISO 7064 mod-97 checksum, which catches OCR slips in account numbers. Premiums must match the sales board to within 1 euro. Duplicate prevention runs at every stage, because envelopes can repeat and can carry more than one policy.

I also took over the React, TypeScript, Vite and Tailwind review dashboard from a teammate who started it, and wrote 75% of its commits. It's where ops staff see each policy, its extracted values and its flags. Database and infrastructure changes on my side cut its load time from about 15s to 2s.

Results

3,205
policies tracked in the first 7 months
74 to 719
monthly policy volume as the platform grew
3,219
validation flags across 1,443 policies
100
critical age-band cases caught before submission
20-30 min to about 4 min
manual work per policy (estimated)
15s to 2s
dashboard load time

Stack

Timeline

  1. Intake and extraction: DocuSign webhook, sales-board matching, OCR and the GPT extraction agent.
  2. Cross-document validation agents, with severities so staff could sort critical cases first.
  3. Hardening with deterministic checks for IBANs, premiums and duplicates.
  4. Took over the review dashboard and cut its load time from about 15s to 2s.
  5. Over the first 7 months, monthly volume grew from 74 to 719 policies.

The client is described by country and industry instead of by name.

Back to case studies