AgentStatus × Federato
Independent, distributed assurance for production AI agents, alongside Federato's AI-native insurance platform.
Two jobs: reachability from residential networks (Monitoring now; Reliability over time), then outcome verification once reached - Scenario, Compositional, Safety, Stability (Consistency / Drift scores), not whether it reused the same words. We sit alongside your platform. We do not replace them.
What we understand about Federato
The AI-native platform that spans the full policy lifecycle.
Federato is the AI-native insurance platform built to prevent strategy drift. RiskOps brings precision to underwriting; Control Tower delivers real-time portfolio steering; Submission to Quote lets agentic AI deliver complete, on-strategy quotes for underwriter review within seconds; Product Studio, Producer Portal, Policyholder Portal, and Billing & Payments complete a single platform across the policy lifecycle.
Federato customers include Nationwide, QBE, Ascot, Mission, Ascendex, HDVI, Velocity Risk, and Wholesure. The platform is publicly cited for outcomes including a 3.7x lift in high-appetite bound policies, 89% reduction in time to quote, 90% reduction in systems used, and 30% lift in high-appetite premiums. Backed by a $100M Series D from Goldman Sachs, with the Nationwide CIO going on record: "Lots of people are talking about Agentic AI as the future, but Federato is doing it now."
What AgentStatus is
We measure whether users can reach the agent, then whether it did the job.
Reachability. Controlled validate traffic from 2,500+ residential devices across 70 countries measures whether users can open the agent the way they do — past CDN, WAF, and bot walls that treat datacenter synthetics differently. Monitoring asks if it is healthy right now; Reliability asks if it keeps working over time. Multi-geo is observer vantage for access and last-mile latency. It does not change agent tool egress or localize answers by probe IP.
Outcome verification. Once reachable, we verify outcomes: Scenario (did it finish the job?), Compositional (do the pieces hold together?), Safety (must-not-say / policy / attacks), Stability (same ask, same story?). Consistency and Drift track what changed. Job anchors and side-effects where they exist — not prose matching. Optional sample review is corroboration only; stably wrong still needs a domain expert.
User-side validation is two separate jobs
Reachability
Outcome
Can we talk to it?
Residential observers take the inbound path customers take — past CDN, WAF, and bot walls that treat datacenter synthetics differently. Monitoring asks: is it healthy right now? Reliability asks: does it keep working over time? “Up” means reachable from home networks, not from AWS.
Outcome verification
Outcome
Did it do the right thing?
Reachable and wrong is still broken. Scenario — did it finish the job? Compositional — do the pieces hold together? Safety — must-not-say, policy, attack probes. Stability — same ask, same story? Scores: Consistency and Drift. Not prose matching. Optional sample review is corroboration only.
Where we fit
We sit beside the platform. We do not replace it.
Strategy adherence vs continuous evidence
The Maturity Model gap
Global execution footprint
Partner-friendly integration posture
The split
How the work divides
Your platform
- • RiskOps & Control Tower
- • Agentic AI quote generation
- • Strategy-drift prevention
- • Maturity Model L1–L5
- • Random underwriter quality audits
Outcome
System of record
Dashboards, exports, lifecycle tools, and orchestration remain yours. We do not replace that surface.
AgentStatus
- • Continuous validate traffic
- • Gold libraries & drift detection
- • Multi-turn / multi-agent journeys
- • Real-network execution evidence
- • 2,500+ nodes across 70 countries
Outcome
User-side layer
Reachability (Monitoring / Reliability) from residential networks, then outcome verification once reached — Scenario, Compositional, Safety, Stability; Consistency and Drift scores. Not prose matching.
Proof of scale
Auditable scale metrics
In about two months, we have executed on the order of 18 million validate runs across the network. We also maintain on the order of 6,000 agent records in our system, meaning rows and configurations we track, including evaluation and pipeline agents, not "6,000 paying customers."
We have also caught node operators trying to game the network with datacenter VMs instead of real consumer egress. Detection of adversarial behaviour is built into the product. If helpful, we can share stricter production-only definitions under NDA.
What we are not claiming
We are an independent layer that runs alongside your stack.
We are not a replacement for RiskOps, Control Tower, the random underwriter audit process, or any of Federato's agentic AI workflows. We are an independent layer that can coexist with them, and where useful, help carriers, MGAs, and MGA aggregators correlate user-side validate outcomes with inside-out strategy adherence, so leaders moving toward Maturity Levels 4 and 5 have continuous evidence the deployed agent is still operating within the rules and guardrails the carrier has set.
What we'd like from this conversation
These three asks would move a pilot forward.
Validate the fit
As Federato's customers move up the Maturity Model toward Supervised and True Agentic AI Underwriting, where do they want independent assurance, and where does Federato prefer everything native to RiskOps?
A practical next step
A sandbox surface we can validate with gold prompts representative of an underwriting workflow (submission triage, agentic quote generation, strategy-drift checks), so Federato's agentic AI and AgentStatus drift detection tell one story together.
Partner path
If there is a partner path, we'd like to understand supported integration patterns for carriers, MGAs, and aggregators operating across multiple lines and geographies, particularly through Federato's relationships with Nationwide, QBE, and Ascot.
Federato × AgentStatus.
Federato helps carriers and MGAs build and operate AI-native underwriting that prevents strategy drift. AgentStatus helps those same teams prove, continuously, that the deployed agent behaves the way appetite, regulators, and capital providers require, globally, with evidence that holds up under scrutiny.
Contact·dulra@carmel.so·roman@carmel.so
Metrics are stated with explicit definitions: validate runs are scheduled executions over ~two months; agent records are database rows, not revenue customers. Public Federato references above reflect Federato's public product pages, customer disclosures, the 5-level AI Maturity Model, and the $100M Series D announcement (Goldman Sachs) as of the date of this note.