# GEICO spent $1,000 to map legacy claims in a day

_GEICO ran a one-day, $1,000-token war room to map legacy claims code and ship agent APIs, using Anthropic's Fleet Kit and code-modernization plugin._

**Published:** 2026-10-21
**Source:** https://www.startuphub.ai/ai-news/artificial-intelligence/2026/geico-spent-1-000-to-map-legacy-claims-in-a-day

---

[AI Engineer](https://www.youtube.com/watch?v=DouK81O8R3o) featured Ford Prior, GEICO senior staff engineer in claims tech, detailing a one-day, $1,000-token war room that mapped a legacy claims domain end to end.

Prior said GEICO, a 300-engineer claims group inside Berkshire Hathaway, found engineers had 25 percent or less bandwidth for major V1-to-V2 work after patches, so it now routes minor work to agents to free them.

He ran the war room three times and Prior said the rentals uplift extended an API to save 8,500 calls per month, the damages transformation added new APIs, and the salvage reimagine produced a green-lit migration plan that also surfaced a prod bug he declined to detail.

The stack paired [Anthropic](https://www.startuphub.ai/ai-news/technology/2026/anthropic-disables-fable-5-and-mythos-5-after-us-export-control-order)'s harness, model and Fleet Kit plus a code-modernization plugin with GEICO's own context, tools, methods and judgment gates, and while Prior described Fleet Kit as markdown rules for the Claude harness, [Anthropic's v1.0.0 code-modernization plugin for Claude Code](https://gotburnout.io/en/news/anthropic-releases-code-modernization-v1-0-0-plugin-for-claude-4085) is publicly documented as built to modernize legacy codebases and manage technical debt.

The demo required local access to Prior's laptop as runtime, relied on Fable models where Sonnet and Opus-class systems did the heavy lifting, and burned budget fast when [Claude](https://www.startuphub.ai/ai-news/insights/2026/how-to-get-claude-pro-for-free-options-alternatives) running Fable set up crons that spawned sessions.

Prior said the next wins are stronger gate enforcement, better decision models and searchable context beyond markdown, but he left unanswered how the factory model scales beyond a hand-picked roster without losing the human judgment that approved every step.

---

Original analysis from [startuphub.ai](https://www.startuphub.ai), the #1 AI startup directory.

© StartupHub.ai. All rights reserved. You may not republish this article in full without a license. Search engines and AI research tools may crawl and summarize for reference. Bulk reproduction or model training on this content requires a license. See https://www.startuphub.ai/terms.