視点
AI の未来について、開発者やリーダーたちが語るアイデアや展望をお届けします。
注目のリソース 1 / 5：Product development in the agentic era
62 件中 11 件を表示
Building agents: When to fold subagents into your main agent loop
When building agents in Claude Platform, using fewer subagents in favor of progressively disclosed context and tools can improve quality while reducing cost and latency. Here’s when and how to migrate.
Building secure agents for knowledge work
Katelyn Lesse sat down with Dan Shipper and Willie William at Every to talk about the AI coworker they built.
DRI-ing Your Career
Your career is yours. It always was - but when the market was hot, it didn't seem like you needed to think about it.
Uber の CISO が語る、AI 向け内部脅威対策プログラムの構築
Uber の CISO、Philip Martin 氏が、AI エージェントの監視と可観測性の重要性、そして Uber のオープンソースツールと Enterprise Frontier Safeguards がどのように連携するかを語ります。
AI as an Engineering Leadership Multiplier
Most conversations about AI in engineering focus on how the IC role is changing, but the engineering leadership role is adapting…
How Block orchestrates Claude Fable across thousands of pull requests
Bradley Axen, Head of AI Capabilities at Block, on how his team evaluates new large language models, how Claude Fable 5 orchestrates company-wide code migrations, and why safeguards are a critical part of deploying frontier intelligence responsibly, at scale.
How Comcast and Booz Allen use Claude Mythos to find exploit chains and secure their codebases
Security teams at Comcast and Booz Allen used Claude Mythos-class models through Project Glasswing to find, validate, and fix vulnerabilities their existing scanners missed.
Agents you can coach: how Asana builds human-agent teams with Claude
Arnab Bose, Chief Product Officer at Asana, on how Asana runs AI agents as teammates with scoped roles, shared memory, and work that everyone can see.
Automating eval design and hillclimbing with Claude
Principles for designing evals and hillclimbing against them without fooling yourself, and how the claude-api skill's build-eval and hillclimb commands put them to work.
Using Claude Code: Spending your effort
What effort really is and when to use which level in Claude Code, from my own tests of three builds and a deep dive into Terminal-Bench 3.0 on Opus 5.5 and Fable 5.1.
Coding sessions are longer and use more context. Claude Opus 5.5 is built with that in mind.
Our latest Opus model is priced and trained to optimize costs for how developers code now.