Agentic coding and persistent returns to expertise
… It appears that coding agents are making a coding background less relevant to successful programming. At the same time, successful sessions are more likely to exhibit domain expertise. …
Search
Demystifying evals for AI agents
… For example, the code review startup Qodo was initially unimpressed by Opus 4.5 because their one-shot coding evals didn’t capture the gains on longer, more complex tasks. In response, they developed a new agentic eval framework, providing a much clearer picture of progress. …
Quantifying infrastructure noise in agentic coding evals
Engineering at Anthropic Quantifying infrastructure noise in agentic coding evals Agentic coding benchmarks like SWE-bench and Terminal-Bench are commonly used to compare the software engineering capabilities of frontier models—with top spots on leaderboards often separated by just a few percentage… …
Long-running Claude for scientific computing
Science Long-running Claude for scientific computing Mar 23, 2026 In this post, Siddharth Mishra-Sharma , a researcher on the Discovery team, explains how to apply multi-day agentic coding workflows—test oracles, persistent memory, and orchestration patterns—to scientific computing tasks even outsi… …
Building Effective AI Agents
… Summary Success in the LLM space isn't about building the most sophisticated system. It's about building the right system for your needs. Start with simple prompts, optimize them with comprehensive evaluation, and add multi-step agentic systems only when simpler solutions fall short. …
AI agents find smart contract exploits
… Related content Agentic coding and persistent returns to expertise Paving the way for agents in biology Measuring LLMs’ impact on N-day exploits In cybersecurity, a large fraction of real-world harm comes from N-days: vulnerabilities that have already been publicly disclosed, but only patched on so… …
Eval awareness in Claude Opus 4.6’s BrowseComp performance
… Failed attempts The two successful attempts were not the only examples of Opus trying to decrypt BrowseComp’s answers. …
Patterns and problems in multiagent systems
… Other failure modes of agentic coordination, however, look very different. …
Measuring AI agent autonomy in practice
… Next, we developed a collection of metrics that draw on data from both agentic uses of our public API and Claude Code , our own coding agent. These offer a tradeoff between breadth and depth: Our public API gives us broad visibility into agentic deployments across thousands of different customers. …
Equipping agents for the real world with Agent Skills
… Iterate with Claude: As you work on a task with Claude, ask Claude to capture its successful approaches and common mistakes into reusable context and code within a skill. …