Tag: Claude

Anthropic's Managed Agents now expose session budgets, advisors, inference geography, repository skills, and inference hooks as runtime controls; this article maps their value and remaining boundaries.

Anthropic removed over 80% of Claude Code's system prompt for Claude Opus 5 and Claude Fable 5 without losing benchmark performance. Explore the paradigm shift from rigid instruction constraints to progressive disclosure, auto-memory, and rich reference harness engineering.

Anthropic has released Claude Tag, designed specifically for team collaboration. By tagging @Claude in Slack, AI becomes a virtual teammate that proactively participates in discussions, executes asynchronous tasks, and continuously learns. This article details its core features, usage, target audience, and billing model.

Anthropic releases a privacy-preserving analysis of 400,000 Claude Code interactions. The research reveals the true division of labor for AI coding agents: humans decide 'what to do', while AI decides 'how to do it'. More importantly, success depends not on 'coding ability', but on 'domain expertise'. This has profound implications for the future of knowledge work.

The starting point for the Harness Engineering section on this site: concepts, a full series article index, and reading paths based on roles and scenarios.

A deep dive into Nicholas Carlini's experiment: nearly 2,000 sessions, about $20,000 in API costs, and a 100,000-line Rust compiler capable of compiling Linux 6.9—exploring task locking, test harnesses, GCC oracle, multi-role specialization, and capability boundaries.

In-depth read of HumanLayer's long article: Failure is often a configuration issue, not a model one. Clarifying AGENTS.md, MCP, Skills, Sub-agents, Hooks, and back-pressure, and responding to ETH research and post-training overfitting debates.

Standing at the startup scene in 2026, we are witnessing an unprecedented paradigm shift. In the AI-native era, development costs and time are extremely compressed, and the bottleneck for startups is no longer 'building capability,' but 'selection capability.' This article reveals the most disruptive core insights in the AI-driven startup ecosystem.

A source-grounded analysis of Anthropic's initializer, progress artifacts, feature inventory, Git checkpoints, and end-to-end verification pattern for work spanning context windows.

Adapted from Anthropic's 'Building Effective AI Agents': From single agents to multi-agent collaboration, common architectural patterns, workflow design, and how to choose the right architecture based on control requirements, problem complexity, and resources.