# One Day, $1,000 in Tokens: An AI War Room for Legacy Code — Ford Prior, GEICO

## Executive summary

This talk details how GEICO addressed the 'outer loop' bottleneck in their Software Development Lifecycle (SDLC)—the slow processes of decision-making, sign-offs, and context gathering—which historically limited the speed of coding (the 'inner loop'). They implemented a multiplayer, AI-native war room that uses agent fleets, structured rules (FleetKit), and human collaboration to accelerate major code modernization missions. The goal was to map a complex legacy claims domain end-to-end and deliver a functional change (like an agent-callable API) within one day and a limited token budget. The system successfully ran three modernization missions across rentals, damages, and salvage domains, producing fully vetted migration plans and design artifacts.

## Key takeaways

- The Outer Loop Bottleneck: In non-tech companies like GEICO, the SDLC is often limited by the 'outer loop' (decision-making, governance, context gathering), even if the 'inner loop' (coding) is fast. The solution requires automating the decision and intelligence layers.
- AI-Native War Room Architecture: The war room is a collaborative system comprising key decision-makers, a 'driver,' and an AI-native productivity suite. It is wired into code repositories, workflows, agent skills, and enterprise MCPs to handle heavy lifting, fact-checking, and synthesis.
- FleetKit: The Orchestration Layer: FleetKit is a structured collection of rules, protocols, and instructions written in markdown, optimized for guiding agent fleets (specifically for the Claude harness). It acts as a 'fleet manager,' taking a goal, breaking it down, dispatching research leaders, and managing the process through a human-in-the-loop queue.
- Modernization Missions: The team ran three missions: 1) Uplift (rentals domain, extending an existing API to save costs); 2) Transformation (damages domain, building new agent-callable APIs); and 3) Reimagination (salvage domain, producing a fully vetted migration plan with API specs and design mock-ups).

## Technical details

- Agent Architecture: The system uses two types of agents: 'code dives' (for code crunching and graphing over legacy domain-specific languages in the cloud) and local agents (with access to local MCPs and enterprise-specific, highly optimized code).
- Core Components: The architecture relies on a combination of vendor tools (e.g., Anthropic's code modernization plugin, the Claude harness) and internal GEICO assets (knowledge base, software standards, decision archaeology, and methods/skills).
- Artifact Generation: The war room generates high-quality, structured artifacts, including HTML worksheets (using cloud artifacts), design documents (e.g., Draw.io or Figma visualizations), and complex visualizations of the architecture, which are crucial for human sign-off.
- Model Selection: Benchmarks showed that models like Fable or Sonnet 5.5 performed comparably to, or better than, the previous generation of models when writing complex legacy code.

## Practical implications

- The concept of the 'AI-native war room' provides a blueprint for automating governance and decision-making processes in highly regulated, legacy environments.
- Structured rule sets (like FleetKit) are critical for steering complex agent behavior, moving beyond simple system prompting.
- The process demonstrates that AI agents can be used not just for coding, but for generating high-quality, actionable design and business artifacts, significantly reducing the manual effort in the outer loop.
- Organizations should focus on optimizing context retrieval (e.g., moving beyond simple markdown files) and incorporating non-text data sources like audio transcripts into agent workflows.

## Topics

AI Agents, Software Development Lifecycle (SDLC), Legacy Code Modernization, Workflow Automation, Enterprise Architecture, Ford Prior, GEICO, AIE CODE summit

Source: https://www.youtube.com/watch?v=DouK81O8R3o