Terms extracted once, verified, and flowed into every downstream document,governed out of the box, with client data never leaving your tenant.
Co-Analyst extracts structured terms from facility agreements, term sheets and credit approvals, then runs drafting, coverage structuring, approval orchestration, regulatory monitoring and issuance inside your own Azure or AWS tenant with a lineage record on every step. Your underwriters make the call, with the evidence attached, and nothing is exported or uploaded at any point.
governed by design · no client data leaves your tenant
90% of insurance leaders say work needs reinventing around AI. Around 25% have acted..
McKinsey, "The Future of AI in the Insurance Industry," 2026
P&C return on equity is forecast to fall from 15% in 2025 to 10% by 2027 as underwriting profitability weakens..
Swiss Re Institute, "US Property & Casualty Outlook," January 2025
The revised Solvency II framework bites on 30 January 2027..
EIOPA, Solvency II Review Updates, 2025
ORIGINATE / STRUCTURE
Terms extracted once, for every team that needs them
What the reader extracted, and what they missed, is recorded nowhere.
- The problem
- Inputs arrive as a facility agreement, a term sheet, and credit approvals, each written for a different purpose and none structured for underwriting. Someone reads all three and pulls out insurable risk and jurisdictional requirements by hand. That reading becomes the basis for everything downstream, so every later check validates the interpretation rather than the documents.
- What ProSyft does
- Co-Analyst ingests facility agreements, term sheets, and credit approvals, extracting insurable risk and jurisdictional requirements into a structured, policy-ready record with each term cited to its clause in the source, so a term read once at intake is available to drafting, approval and issuance without being re-read by each team.
- Outcome
- Extraction becomes an auditable artefact rather than an undocumented reading.
The problem: your annual compliance review is most wrong the day after it's signed off.
An annual review with external counsel is thorough, expensive, and accurate on the day it completes. Then it drifts, because obligations keep moving while the review does not. It is at its most accurate the moment before you rely on it, and at its least accurate when you need it: at audit, at renewal, or at a claim. A more rigorous review only buys more confidence in a picture that decays just as fast.
Two things are tightening at once. P&C premium growth is slowing from around 5.5% in 2025 to roughly 3% in 2026, (Deloitte, "2026 Insurance Industry Outlook," 2026) so cost per policy stops being a back-office concern. And the NAIC has made AI model governance a stated 2026 priority. (NAIC, "Leadership, Modernization, Resilience: NAIC 2026 Strategic Priorities," March 2026) Automation is not the hard part. Governing it is.
Does your data stay with you?
The usual assumption is that AI-assisted drafting means sending facility documents to a vendor.
Co-Analyst’s answer: it runs inside your own tenant, so no client, facility, or policy data leaves your environment at any point.
Can your solution show you its reasoning?
The usual assumption is that you trade explainability for speed.
Co-Analyst’s answer: every clause, exclusion, and decision carries lineage back to the facility document it came from. The record an examiner, an auditor, or a court asks for already exists.
Who is accountable when it is wrong?
The usual assumption is that automated wording means generic wording with no one standing behind it.
Co-Analyst’s answer: it drafts from the facility agreement, term sheet, and credit approvals in front of it, and anything that fails verification is routed to a named reviewer rather than passed through.
Can you control the cost?
The usual assumption is that reading every submission and every policy document means a bill that grows with the size of the book.
Co-Analyst’s answer: each step sees only the evidence it needs, so every run is bounded and underwriting cost stops tracking the size of the book.
How it Works
EVIE™, the orchestration engine inside Co-Analyst, deploys inside your own tenant and runs underwriting workflows end to end. Your team reviews governed outputs with the evidence attached, and anything that fails verification goes to a named reviewer.
Connect to your existing systems
Native connection to your policy admin system, document stores, pricing engines, sanctions screening, and Databricks, with no export and no upload.
Select and register the evidence
EVIE™ extracts insurable risk and jurisdictional requirements, checks clause alignment, and flags exclusions and coverage gaps before binding, recording which evidence each step used and why.
Generate verified, hallucination-contained outputs
Wording, schedules, approval trails, and gap analyses in your existing templates, with every clause checked line by line against the facility document it came from.
Review inside your perimeter
Your Azure tenant or on-premise, human-in-the-loop approval at every stage, a named reviewer for any exception, and audit logs retained locally for clause-level traceability.
Benefits
Sovereign
Client, facility, and policy data never leaves your tenant.
Verifiable
Every clause and exclusion is checked line by line against the facility document it came from.
Accountable
A live gap analysis and a named reviewer accountable for every approval trail on every policy.
Bounded
Each step sees only the evidence it needs, so the cost of every run is bounded and underwriting cost stops tracking deal flow.
Speed
Drafting cycles compress from underwriter days to minutes, with the first workflow live in weeks.
Scale
Underwriting throughput climbs on the same headcount.
Four ways to automate underwriting. Three cost you something you can't get back.
General-purpose AI assistants
Days to deploy, minimal governance, vendor-side data custody, unmanaged hallucination risk. For wording that has to hold at a claims event, that is not a governance model.
Consultants and custom agents
Eight to sixteen weeks, high cost, variable governance, shared data custody. Typically shelf-ware within six months.
Building it yourself
Six to twelve months to first policy, highest total cost, permanent maintenance obligation.
ProSyft Co-Analyst™
Deployed inside your own tenant with the first workflow live in weeks. Every claim traces to source, every output is verified line by line, a named reviewer stays accountable, and data custody never leaves you. The governance arrives with the software rather than being added afterwards.
The control of a self-build, the speed of off-the-shelf, governed out of the box, inside your own tenant.
Engagement built around your risk priorities
Deploy only the workflows you need now and scale on the same platform. You pay for outcomes, not licences or headcount.
Pay per workflow
Start with the one or two that matter most, then add more with no replatforming.
Ready to deploy
A library of proven workflows across the regulated risk lifecycle, live from day one.
Tailored
Where requirements are specific to your book, our architects design and build with you.
Underwriting and policy automation
Active pilot with a specialty and credit insurer, targeting significant time savings on policy drafting with the same underwriting headcount.
- 01
McKinsey, "The Future of AI in the Insurance Industry," 2026. Tier 1, major analyst firm.View source
- 02
Swiss Re Institute, "US Property & Casualty Outlook," January 2025. Tier 1, reinsurer research institute. Forecast, not outturn.View source
- 03
EIOPA, Solvency II Review Updates, 2025. Tier 1, primary EU regulator.View source
- 04
Deloitte, "2026 Insurance Industry Outlook." Tier 1, major analyst firm.View source
- 05
NAIC, "Leadership, Modernization, Resilience: NAIC 2026 Strategic Priorities," March 2026. Tier 1, primary US regulatory body.View source
Let’s map your highest cost compliance workflow and show you what governed AI looks like running inside your own environment, on your data.
- 01No data leaves your tenant.
- 02Every claim traces to source.
- 03A named reviewer stays accountable.
- 04Live in weeks.