Uber Burned 6x Its AI Budget in Four Months
Learn how to manage the exploding costs of AI agents. Experts discuss cache-aware routing, open-weight models, and why only $18 of every $100 spent on AI actually ships to users.
Read articleTopic
AI DevCon NYC 2026
All digests tagged AI DevCon NYC 2026
Suggested route
Topic journey
Move from earlier context through the available material to the newest signals. This route is a reading aid, not a difficulty ranking.
Start here
Anthropic, OpenAI & Thoughtworks on Context Engineering Context engineering is now the main lever on what a coding agent can actually do. The three remaining constraints are human time, attention, and the context window.Build context
Cisco & Stanford on Why Skills Are the New Code Skills are transforming software development from revolving around code to intent. Experts argue that managing skill sprawl requires treating skills as code, focusing on context engineering over model size. GitHub Next & Tessl on the Self-Merging Repo The shift from CI/CD to Continuous AI is explored, detailing how agents can auto-merge PRs and how fixing the system, not the code, drives efficiency. NVIDIA, Docker & Hud on Agents in Production Running AI agents in production requires shifting focus from root cause analysis to context. Key insights cover using combined data sources (Elastic logs + ServiceNow) for diagnosis, optimizing GPU usage during tool calls, and building AI-powered tracing frameworks.Recent signals
Uber Burned 6x Its AI Budget in Four Months Learn how to manage the exploding costs of AI agents. Experts discuss cache-aware routing, open-weight models, and why only $18 of every $100 spent on AI actually ships to users. Meta's VR Codebase Nobody Wanted to Touch — Until This Learn how to modernize legacy codebases by treating them like functioning cities, not 'balls of mud.' Discover how to decouple AI workflows from single providers using specialized servers and parallel agent processing. Meta, Stanford & Odevo on Agentic Coding at Scale Scaling agentic coding requires fixing fundamentals first: CI/CD, platform stability, and testing. The 2025 DORA report warns that agents make weak delivery worse.
Meta's VR Codebase Nobody Wanted to Touch — Until This
Learn how to modernize legacy codebases by treating them like functioning cities, not 'balls of mud.' Discover how to decouple AI workflows from single providers using specialized servers and parallel agent processing.
Read article
Meta, Stanford & Odevo on Agentic Coding at Scale
Scaling agentic coding requires fixing fundamentals first: CI/CD, platform stability, and testing. The 2025 DORA report warns that agents make weak delivery worse.
Read article
NVIDIA, Docker & Hud on Agents in Production
Running AI agents in production requires shifting focus from root cause analysis to context. Key insights cover using combined data sources (Elastic logs + ServiceNow) for diagnosis, optimizing GPU usage during tool calls, and building AI-powered tracing frameworks.
Read article
GitHub Next & Tessl on the Self-Merging Repo
The shift from CI/CD to Continuous AI is explored, detailing how agents can auto-merge PRs and how fixing the system, not the code, drives efficiency.
Read article
Cisco & Stanford on Why Skills Are the New Code
Skills are transforming software development from revolving around code to intent. Experts argue that managing skill sprawl requires treating skills as code, focusing on context engineering over model size.
Read article
Anthropic, OpenAI & Thoughtworks on Context Engineering
Context engineering is now the main lever on what a coding agent can actually do. The three remaining constraints are human time, attention, and the context window.
Read article