From AI-Assisted to AI-Native: Building a Frontier Development Team — Clare Liguori, AWS
Source
youtube.com
Author
AI Engineer
Date
Context
An Amazon account of 50 development teams suggests that adopting a coding assistant leaves substantial workflow problems to solve. According to the talk's published description, 90% used the same assistant, yet improvements in deployment velocity varied widely. The proposed explanation centers on how teams prepared work: documenting intent before generation, maintaining useful project context windowThe maximum amount of text a model can consider at once — its working memory for the current conversation or task.Full definition → and providing fast local tests so agents can correct errors. Those practices give an AI agentAn AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.Full definition → both a clearer target and a shorter feedback loop. The comparison is observational and measures deployment velocity, so it cannot isolate a productivity gain caused by any single practice.
Terms in this piece · Glossary
context window — The maximum amount of text a model can consider at once — its working memory for the current conversation or task.
AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
video1,000 Agent Tasks in a Sandbox: What Breaks When LLMs Run Code — Kevin Orellana, AWS
videoHow Inference Keeps Up with Our Insatiable Need for Tokens — Cerebras & Gimlet Labs
videoAuth for Agents: Let AI Sign Up for Your Product with auth.md — Michael Grinich, WorkOS
videoDecoupling the Brain from the Hands: Claude Managed Agents (Part 1 of 4) — Anthropic
