Does Fabriq replace our claims or policy systems?

No. It drops in as a policy layer between your agents and the platforms you already run. Agents keep working in your claims and policy systems; Fabriq decides, per request, what they can read and which actions they can take there.

Can we choose what each adjuster’s or underwriter’s agent can do?

Yes — per user. The same agent can assemble files under a junior adjuster’s tight limits and act more broadly for a senior underwriter, because policy resolves from the person the agent works for. Denials, settlements, and coverage changes stay with humans by rule.

How do we keep sensitive details out of the wrong workflows?

Field-by-field limits. A workflow with no approved reason to see medical or behavioral data simply cannot retrieve it — the block is enforced on every request, not requested politely in a prompt.

Can payouts require sign-off?

Yes — an adjuster’s agent can read and draft freely while payments or coverage changes hold for approval, and the decision is part of the record.

What happens when staff change roles?

Grants resolve org → team → member, so authority follows the person — and revoking a session cuts their agents’ access immediately.

How do agents connect to our systems?

Through the hub — prebuilt connectors plus OpenAPI import for internal claims and policy APIs, with credentials held in the vault, not in bot configs.

Industry · Insurance

Safely automate decisions that affect coverage and claims

Govern agents across underwriting, claims, policy servicing, and sensitive customer records.

Get a demo

The landscape

Insurance agents work with personal, medical, financial, property, and behavioral data. They may summarize submissions, assess claims, recommend coverage, request documentation, or update policies.

The risk is not limited to data exposure. An agent may use information for an unapproved purpose, influence a regulated decision, or take action outside an adjuster’s or underwriter’s authority.

Live workflow

See a real workflow, governed

Every agent below carries its own identity and acts for a real user. Watch every tool call route through Fabriq — then edit the workflow yourself.

An agent summarizes each new claim, pulls the relevant policy documents, and routes it to the right adjuster queue.

agent: claims-bot-01

New claim filedclaims intake

Claims Triage Agentclaims-bot-01 · for: intake@northstarins.com

Agentic Fabriqidentity · policy · audit

Internal APIread claim intake

Document Vaultpull policy docs

Jiraroute to adjuster

Drag nodes, draw connections, add tools — every agent action routes through Fabriq. Try wiring the agent straight to a tool.

The stakes

Industry challenges

01Claims files mix medical, financial, and property data — and an agent that reads one can often read them all.
02The agent that summarizes a claim can drift into influencing the decision — a regulated act it was never approved for.
03An agent acting past an adjuster’s authority looks fine in the moment; it surfaces in the market-conduct exam.
04Rules like “don’t use health data for pricing” rarely survive translation into system permissions.

Capabilities

How Fabriq helps insurers

Restrict access by policyholder, claim, product, jurisdiction, and assigned team.Scope resolves from the case in front of the agent — one policyholder, one claim — not from the carrier’s whole book.

Separate data collection and recommendation from final decisions.Agents assemble and suggest; decisions that affect coverage or payout remain with adjusters and underwriters.

Require human review for denials, pricing changes, settlements, and coverage modifications.The decisions regulators scrutinize hardest always pass through a person with authority to make them.

Limit which sensitive details an agent may use in a workflow.Field-by-field limits keep medical, financial, or behavioral data out of workflows that have no approved reason to see it.

Control external communications and document sharing.Messages to policyholders, brokers, and third parties are checked and, where required, held for review before sending.

Record the inputs, authority, and approvals associated with each outcome.Every claim and policy outcome carries what informed it and who approved it — market-conduct evidence by default.

In practice

Featured workflows

logged

Claims intake

Intake agents summarize and route each new claim, limited to that claim’s policy and documents alone.

logged

Underwriting assistance

Assistants assemble submissions and flag risk factors; acceptance and pricing stay with the underwriter.

approval: human approval

Policy servicing

Routine changes apply automatically while coverage-affecting requests hold for authorized review.

scope: read-only

Fraud review

Review agents work assigned referrals read-only, preserving evidence and avoiding cross-case contamination.

approval: human approval

Broker support

Broker-facing agents answer from approved product and appointment data, without exposing other producers’ business.

logged

Document analysis

Analysis stays inside the case’s own documents, with sensitive details gated by purpose.

Core value

More efficient underwriting and claims operations with enforceable boundaries around data use and decision authority.

Questions

Safely automate decisions that affect coverage and claims

See a real workflow, governed

Industry challenges

How Fabriq helps insurers

Featured workflows

Common questions