Construction and facilities In active development
A facility management platform that replaced spreadsheets and phone calls
Every request, inspection and cost for every building now lives in one place, with a clear owner and status.
Industries
Software and AI for insurance brokers and insurers
Insurance runs on forms, photos and policy wording. We build tools that read them quickly and route each case to the right person, with every decision left to your people.
Common challenges
What slows this industry down
Brokers, agencies and insurers handle a steady flow of documents: applications, policy schedules, claim forms, photos of damage, repair estimates and letters. Each has to be read, checked, filed and acted on. Much of the handling time goes to reading and retyping before any real assessment starts.
AI models that can read both text and images, known as multimodal models, are well suited to this first step. They can extract details from forms, describe what a photo shows and find the relevant section of a policy. They are not a substitute for an underwriter or a claims handler, and in insurance their output must be checked and explainable.
We build claims intake, document processing, policy search assistants and customer portals for insurance teams. Automation prepares the case, and people make every decision on cover, pricing and payment. Each step is logged, so you can show how a case was handled.
Claims arrive in pieces
Claim details, photos and estimates come by email, phone and portal, often incomplete.
Heavy document load
Applications, schedules and letters are read and retyped into policy systems.
Policy wording questions
Staff search long policy documents to answer what is and is not covered.
Photos and evidence
Damage photos and reports must be sorted and attached to the right claim.
Regulation and fairness
Decisions must be consistent, explainable and compliant with local rules.
What we build
What we build for this industry
The services insurance teams ask us for most often.
Document automation
Read invoices, forms, contracts and IDs, pull out the right fields and route them for review.
Computer vision
Software that reads photos and scans: damage checks, stock counts, document capture and quality control.
Customer portals
A secure place where your customers upload documents, check status, pay and message your team.
RAG knowledge assistants
Assistants that answer questions from your own documents and show where each answer came from.
Solutions that fit
Problems we solve here most often
AI document processing
Read forms, applications, IDs and statements, extract the fields you need and route each document for the right review.
Compliance tracking
Track filing deadlines, licenses and obligations in one place, with reminders and AI summaries of relevant rule changes.
Email triage
Sort a shared inbox by topic and urgency, pull out the key details and draft replies for a person to send.
Contract review assistant
Highlight unusual clauses, missing terms and deviations from your standard positions, so reviewers focus where it matters.
Similar work
Similar work from other industries
Finance and accounting In use
A payroll system that turned a monthly build into a monthly review
Payroll is calculated from recorded inputs, reviewed once and sent as payslips in a single batch, with every change logged.
SaaS and startups Design stage
Designing a goal tracker that measures effort, not streaks
A product design built around handwritten daily proof, locked plans and honest self-scoring. The build is in progress.
In practice
What it looks like in practice
An illustrative walk-through, not a client story.
A broker handles property claims for small business clients. A client reports water damage through the customer portal, uploads photos and a plumber's invoice, and answers a short set of questions. An AI model reads the invoice, describes what the photos show and checks the claim form for missing details.
The system prepares a claim summary with the policy number, dates, amounts and a list of attachments, and asks the client for one missing item. A claims handler reviews the summary, opens the policy section the assistant points to and decides the next step. The handler, not the model, decides what is covered. The whole case, including each automated step, is recorded for later review.
Over time, the team uses the logs to see which claims needed the most follow-up and which documents caused the most questions. That helps them improve forms and guidance for clients, which reduces the work on the next claim.
Where to start
Where most insurance teams start
Most insurance teams start with AI document processing for claims or applications, because the volume is high and the output is easy to check. Email triage on shared claims inboxes often comes in the same project.
The next steps are usually a policy knowledge assistant for staff, a customer portal for claims and documents, and compliance monitoring for rules and deadlines. Each step is small enough to test with real cases in a few weeks, and we measure the time saved before moving on.
Models and tools
MCP servers and AI models that matter here
These connect AI to the tools this industry already uses. We pick per project and test on real data first.
- Google DriveGoogle's own Drive MCP server lets AI search, read and create files in Google Drive, with your Google Workspace sign-in.
- AWS S3Amazon S3 is handled through the managed AWS MCP Server, which lets AI run scripted AWS actions, create presigned links and search AWS docs.
- SalesforceSalesforce's official DX MCP server lets AI query data with SOQL, manage orgs and metadata, run tests and assign permission sets.
- Gemini 3.1 ProGoogle's most advanced Gemini model for reasoning, software engineering and agent work, reading text, images, audio, video and PDFs. Available as a preview.
- Claude Sonnet 5Anthropic's balance of speed and intelligence: a strong everyday model for assistants, document work, tool calling and coding.
Keep exploring
More for insurance
Related services
View all related services- Document automation Read invoices, forms, contracts and IDs, pull out the right fields and route them for review.
- Computer vision Software that reads photos and scans: damage checks, stock counts, document capture and quality control.
- Customer portals A secure place where your customers upload documents, check status, pay and message your team.
- RAG knowledge assistants Assistants that answer questions from your own documents and show where each answer came from.
- AI workflows Step-by-step automations where AI handles the reading, sorting and drafting inside a process you control.
- Legacy modernization Replace an aging system step by step, with the business running normally while the new parts take over.
Solutions
View all solutions- AI document processing Read forms, applications, IDs and statements, extract the fields you need and route each document for the right review.
- Compliance tracking Track filing deadlines, licenses and obligations in one place, with reminders and AI summaries of relevant rule changes.
- Email triage Sort a shared inbox by topic and urgency, pull out the key details and draft replies for a person to send.
- Contract review assistant Highlight unusual clauses, missing terms and deviations from your standard positions, so reviewers focus where it matters.
- Invoice processing Read supplier invoices, match them to orders and push approved ones into accounting, with exceptions flagged for review.
- Receipt capture and matching Snap a receipt, and the details are read, categorized and matched to the card transaction and the right project.
Industries
View all industries- Tax and compliance services Client portals, document checklists, case queues and deadline tracking for tax preparers and compliance firms.
- Legal Contract review assistants, knowledge search, intake and document automation for law firms and in-house legal teams.
- Finance and accounting Client portals, document collection, invoice and receipt processing, and reporting for accounting firms and finance teams.
- Real estate Listing sites, lead handling, CRM automation and document workflows for agencies, brokers and developers.
- Healthcare Patient booking, intake forms, internal knowledge assistants and admin automation for clinics and care providers.
- Property management Tenant portals, maintenance tracking, owner statements and inbox automation for property managers.
Guides and articles
View all guides and articlesAI models
View all ai models- Gemini 3.1 Pro Google's most advanced Gemini model for reasoning, software engineering and agent work, reading text, images, audio, video and PDFs. Available as a preview.
- Claude Sonnet 5 Anthropic's balance of speed and intelligence: a strong everyday model for assistants, document work, tool calling and coding.
- Gemini 3.8 Flash Google's most capable Flash model, stable since September 2026, for agents, software engineering and enterprise workflows with full multimodal input.
- Gemini 3.5 Flash-Lite Google's lowest-cost current Gemini model for high-throughput work such as sub-agent tasks and document parsing.
- Mistral OCR 4.1 Mistral's document OCR model, turning pages into structured output with bounding boxes, block labels and confidence scores.
- Vision and multimodal Models that read images, scans, screenshots and sometimes audio or video alongside text.
MCP servers
View all mcp servers- Google Drive Google's own Drive MCP server lets AI search, read and create files in Google Drive, with your Google Workspace sign-in.
- AWS S3 Amazon S3 is handled through the managed AWS MCP Server, which lets AI run scripted AWS actions, create presigned links and search AWS docs.
- Salesforce Salesforce's official DX MCP server lets AI query data with SOQL, manage orgs and metadata, run tests and assign permission sets.
- Box Box's official MCP server lets AI search and read files, ask questions across documents with Box AI, extract data and upload files.
- Dropbox Dropbox's own MCP server lets AI list, search and read files, convert them to markdown and create, move, share and delete files. In beta.
- OneDrive Microsoft's OneDrive MCP server, part of its Work IQ preview, lets AI find, read, create, move, share and delete files in OneDrive.
Glossary terms
View all glossary terms- Multimodal model A multimodal model is an AI model that can take in more than one kind of input, such as text with images, audio or video.
- OCR OCR, or optical character recognition, is technology that turns text in images and scanned documents into machine-readable text.
- Structured output Structured output is when an AI model returns its answer in a fixed format, such as JSON matching a schema, so software can use it reliably.
- Context window A context window is the maximum amount of text, measured in tokens, that an AI model can consider at once, including the question, documents and its answer.
- Inference Inference is the step where a trained AI model is used to produce an output, such as an answer, a label or a prediction, from new input.
- Reasoning model A reasoning model is an AI model that works through a problem step by step before answering, trading speed and cost for better results on hard tasks.
FAQ
Questions from insurance teams
Have a question that is not here? Ask us directly.
We do not build systems that decide claims on their own. AI prepares and summarizes the case, and a claims handler makes the decision.
It can describe what a photo shows and sort photos by claim, which saves handling time. It does not replace an assessor. See computer vision.
Yes. A knowledge assistant finds the relevant section across your policy documents and shows it, so staff can answer with confidence. See knowledge base search.
We connect to Salesforce and to policy systems that offer an API or data export. See CRM integration.