Research

Benchmarks before promises.

Relay is built inside agency workflows and measured in public. This is where we publish the runs, caveats, and field notes behind the product.

Latest benchmark

Carrier Portal Automation Benchmark

Relay scored head-to-head against leading general-purpose AI agents on real HO-3 carrier portal work.

The benchmark measures AI Quoting, which is in Research Preview. We publish the runs, including the limits, so nobody buys on a promise.

June 2026

HO-3 carrier portal run

Field accuracy, median time to quote, and output tokens, scored against ChatGPT Codex, Claude Code, and Gemini CLI.

91.9%

field accuracy on live portal work

3.6 min

median time to quote

1st

of 4 AI agents tested head-to-head

Read the benchmark

Field notes

The work behind the numbers.

01What Is a Quoting AI Agent? A Guide for P&C AgenciesA quoting AI agent automates carrier portal submissions. Learn how it works, how it differs from comparative raters, and what to ask before buying.7 min02Commercial Lines Quoting Automation: How Agencies WinCommercial lines quoting takes 30-45 min per portal. See how portal automation cuts a 3-hour workflow to under an hour for independent agencies.7 min03Comparative Rater vs. Portal Automation: What to KnowSee how comparative raters and portal automation differ. Find which approach saves your agency the most quoting time.6 min

Get started

Get on the Summer ’26 list.

Spring ’26 is full. Get on the Summer ’26 list and we will be in touch as spots open.

Explore the platform