Anthropic Engineering
Articles about AI Agents, Prompt Engineering, Claude Code.27 articles · Last updated: 27/05/2026
Articles
How we contain Claude across products
explanation · 27/05/2026 · AI, Technology
Engineering
explanation · 07/05/2026 · ai-agents, code-quality, software-engineering
An update on recent Claude Code quality reports
explanation · 24/04/2026 · AI, Technology
Scaling Managed Agents: Decoupling the brain from the hands
explanation · 09/04/2026 · AI, Technology
Claude Code auto mode: a safer way to skip permissions
explanation · 26/03/2026 · Software Development Practices, User Experience Design, Machine Learning Models
Harness design for long-running application development
explanation · 25/03/2026 · AI in Software Development, Generative Adversarial Networks, Autonomous Coding
Eval awareness in Claude Opus 4.6’s BrowseComp performance
explanation · 08/03/2026 · Eval Awareness, AI Benchmarking, Model Contamination
The "think" tool: Enabling Claude to stop and think in complex tool use situations
how-to · 21/02/2026 · AI, Technology
Claude Code overview
reference · 21/02/2026 · Prompt Engineering, AI Agents, Claude Code
Introducing Contextual Retrieval
explanation · 21/02/2026 · Prompt Engineering, AI Agents, RAG
Raising the bar on SWE-bench Verified with Claude 3.5 Sonnet
explanation · 21/02/2026 · Prompt Engineering, AI Agents, Claude Code
Engineering
explanation · 20/02/2026 · ai-agents, coding-evaluations, technical-evaluations
Building a C compiler with a team of parallel Claudes
explanation · 12/02/2026 · AI Agents, Agent-Native Architecture, Claude Code
Quantifying infrastructure noise in agentic coding evals
explanation · 12/02/2026 · Agent-Native Architecture, AI Agents, Software Engineering Benchmarks
Designing AI-resistant technical evaluations
explanation · 02/02/2026 · Technical Hiring, Performance Engineering, AI Agents
Demystifying evals for AI agents
explanation · 02/02/2026 · Agent-Native Architecture, Evaluation Harness, AI Agents
Desktop Extensions: One-click MCP server installation for Claude Desktop
how-to · 02/02/2026 · Anthropic API, Prompt Engineering, Software Development
Introducing advanced tool use on the Claude Developer Platform
explanation · 02/02/2026 · Anthropic API, AI Agents, Prompt Engineering
Beyond permission prompts: making Claude Code more secure and autonomous
explanation · 02/02/2026 · AI Agents, Claude Code, Open Source
Effective context engineering for AI agents
explanation · 02/02/2026 · Context Engineering, AI Agents, Transformer Architecture
A postmortem of three recent issues
explanation · 02/02/2026 · API Performance, Infrastructure Bugs, Claude Code
Effective harnesses for long-running agents
how-to · 01/02/2026 · AI Development, Incremental Development, Task Management for AI Agents
Code execution with MCP: Building more efficient agents
explanation · 31/01/2026 · Software Development, Efficiency in Computing, Protocol Standards
How we built our multi-agent research system
explanation · 31/01/2026 · Multi-agent systems, Token efficiency in AI models, System architecture and design
Equipping agents for the real world with Agent Skills
explanation · 29/01/2026 · Agent-Native Architecture, Claude Code, AI Agents
Building agents with the Claude Agent SDK
tutorial · 29/01/2026 · Agent-Native Architecture, Claude Code, AI Agents
Writing effective tools for agents — with agents
how-to · 29/01/2026 · Prompt Engineering, Agent-Native Architecture, Anthropic API