Augment Code

Mentoring the Machine — Eric Hou, Augment Code

Jul 24, 2025 · 19:06

Eric Hou, member of technical staff at Augment Code, argues that AI agents work best when treated as perpetually junior engineers requiring mentoring and context, not just prompts. He recounts a chaotic Tuesday where he parallelized three urgent tasks—a design system component, a staging emergency involving a gRPC library upgrade touching 12 services and 20,000 lines of code, and mentoring a new hire—using Augment's agent and Slack bot, completing in half a day what normally takes weeks. Hou quantifies industry inefficiencies: each interruption costs 23 minutes recovery, two-thirds of time spent maintaining code, totaling $300 billion annually. He prescribes a three-step organizational adoption: knowledge gathering (mapping Notion, Google Docs, GitHub; using meeting intelligence tools like Granola), gaining tool familiarity, and leaning in by sharing successful agent memories across teams. He demonstrates live creation of an agent personality during the talk, and concludes that solving knowledge infrastructure allows parallel exploration of prototypes, turning software development into a more scientific, data-driven process.

To the moon! Navigating deep context in legacy code with Augment Agent — Forrest Brazeal, Matt Ball

Jun 27, 2025 · 15:24

Forrest Brazeal and Matt Ball demonstrate how Augment Agent helps developers navigate and modernize legacy codebases using the Apollo 11 guidance computer as an example. They show that Augment's chat mode can instantly explain the 1202 program alarm—indicating the computer was overloaded but could continue—by reading assembly code and web context. Then, using agent mode, they prompt the tool to write a Python implementation of the P65 vertical descent algorithm from the original assembly, run a simulator, and land the lunar module within expected parameters. The episode argues a three-step strategy for any legacy codebase: use chat to understand, write tests via agent, and then modernize modularly—proving AI agents can turn toil like Java 8-to-17 migrations into automated tasks.

Self Coding Agents — Colin Flaherty, Augment Code

Apr 21, 2025 · 17:23

Colin Flaherty, founding researcher at Augment Code, describes how the company built an AI coding agent that wrote over 90% of its own 20,000-line codebase with human supervision. The agent autonomously added third-party integrations like Google Search and Linear by searching its own codebase and even used its own Google Search tool to look up Linear API docs. It profiled and optimized itself, replacing synchronous file hashing with a process pool after adding print statements and running sub-copies. Flaherty argues that agent capabilities improve with better context engines, code execution environments, and test harnesses—adding test-driven iteration boosted a bug-fixing benchmark by 20% versus 4% from just upgrading the foundation model. He cautions that agents are general-purpose, not category-specific, and have different strengths than humans, making knowledge bases crucial for onboarding. With code becoming cheap, the focus shifts to product insights and design, while better tests enable greater autonomy and accelerate agent self-improvement.

Frontier Feud: Anthropic, Google DeepMind, Meta FAIR, Thinking Machines — Barr Yaron, Amplify

Apr 19, 2025 · 22:26

Teams from Anthropic, Google DeepMind, Meta FAIR, and Thinking Machines compete in a Frontier Feud game hosted by Barr Yaron at the AI Engineer Summit 2025. Surveyed AI engineers name Ilya Sutskever as the most influential AI researcher, with Andrej Karpathy, Jeff Hinton, and Yann LeCun also on the board. Cost is the top consideration when choosing a model, followed by latency, eval scores, and open vs. closed source. The buzzword everyone is tired of hearing is AGI, with RAG and prompt engineering trailing. In the fast money round, Cursor tops favorite AI tools, 'Attention Is All You Need' wins most influential paper, and hardware failure is the biggest 2 a.m. nightmare. The winning team, Rocco's Basilisk, takes home a massive llama and other prizes.