← back
To the moon! Navigating deep context in legacy code with Augment Agent — Forrest Brazeal, Matt Ball
Takeaway
Augment Agent positions its proprietary context engine as the real differentiator for AI on legacy codebases — model quality matters less than what you feed it.
Summary
- Augment Agent's value proposition: a proprietary context engine for legacy codebases that lifts the right knowledge into the model — IDE plugin (IntelliJ-friendly) with enterprise security (customer-managed keys, ISO 42001).
- Live demo on the Apollo 11 Guidance Computer source code (assembly): chat mode explains the 1202/1201 program alarms (executive system out of core sets) by combining repo reading with web context.
- Auto mode in agent mode lets it close the laptop and run long tasks remotely in parallel; chat mode is for tight back-and-forth.
- Use cases include code modernization (P65 'full automatic' lunar landing routine) on a 1960s assembly codebase.
coding-agentslegacy-codeaugment
Original description
Shortened presentation-only version of our Apollo 11 workshop! About Forrest Brazeal Forrest Brazeal is an author, tech educator, cartoonist, and Pwnie Award-winning songwriter. He left Google in 2024 to found the technical media company Freeman & Forrest. His community initiative, the Cloud Resume Challenge, has helped thousands of nontraditional learners take their first steps toward a career in tech. About Matt Ball Matt is passionate about empowering developers. At Postman, Matt was the first Solutions Architect where he helped build the go-to-market strategy. Matt previously led Professional Services Engineering at Qubit. Recorded at the AI Engineer World's Fair in San Francisco. Stay up to date on our upcoming events and content by joining our newsletter here: https://www.ai.engineer/newsletter