What I build

Software for insurance

Quote intake

Clients fill in one smart form; you get the details every carrier needs, without re-asking.

Client portal

Policies, documents, renewals and claims status in one secure place.

Renewal workflows

Renewals tracked from reminder to bind, so none slip past.

Claims tracking

Claims and their documents followed from notification to settlement.

Policy comparison

Coverage, exclusions and prices from several quotes side by side.

Commission and book reporting

Commissions, retention and book growth in one dashboard.

AI, right now

Where AI genuinely helps

Insurance agencies and brokers live in documents: applications, quotes, schedules and claims. 2026 guides point to AI document question-and-answer and structured extraction from dense PDFs as the biggest time savers, alongside automation across the policy lifecycle.

I haven’t built for an insurance agency yet, so I won’t pretend otherwise. What I bring is the same building blocks I’ve shipped for real clients, shown below.

  • Reading policies and schedules

    AI extracts limits, exclusions and dates from dense PDFs, linked to the page, for a broker to check.

  • Questions on documents

    Staff ask questions about a policy and get answers with the source shown.

  • Renewal preparation

    Changes since last year summarised before the renewal conversation.

  • First-line client questions

    Routine questions answered from your own information, with a hand-off to a broker.

Similar work

Data, security and access

  • Brokers make every recommendation and decision; AI extracts and summarises.
  • Client and policy data visible only to the roles that need it, with audit logs.
  • Every extracted figure links back to its source document.
  • Documents stored privately and shared through expiring links.

How a project runs

  1. Call

    A 30-minute call about what you need, who it is for, and what success looks like.

  2. Scope

    A written scope: features, architecture, timeline, price range and risks.

  3. Build

    Working increments you can click through, not a big reveal at the end.

  4. Ship

    Live on your domain and hosting, with a handover so you know how it runs.

More in how I work, or see rag and ai chatbots.

Questions

Common questions

Will it replace our agency management system?

Usually not. Custom tools fill gaps around it, like intake, portals or document AI, and connect through APIs where available.

Can AI read our policy documents reliably?

It does a fast first pass. With sources on every extraction and a person confirming, it's the same human-in-the-loop approach I built for PayRight.

Do you connect to carrier systems?

Where carriers offer APIs or structured feeds, yes. That's confirmed in the scope.

How much does it cost?

A focused first version is a fixed-price project, scoped and priced after a 30-minute call (MVPs start from $3,000). Ongoing work can run on a monthly retainer.

Spending hours on quotes and policy documents?

A 30-minute call is enough to tell whether it fits, what the first version should include, and how long it takes.

Book a 30-minute call