Anthropic Engineering Blog & Tech Articles
AI research and safety company building reliable, interpretable AI systems like Claude
19 engineering articles, tutorials, and technical insights from Anthropic's engineering team
Latest Articles
Filter:
This article from Anthropic's engineering team quantifies how infrastructure configuration—specifically resource allocation and enforcement methodology—introduces significant noise into agentic cod...
9 min read
Includes Code
Has Summary
--
Nicholas Carlini from Anthropic's Safeguards team describes how he built a 100,000-line Rust-based C compiler using 16 parallel Claude agent instances working autonomously on a shared codebase.
The article discusses the importance of evaluations (evals) for AI agents, emphasizing how they help teams identify and resolve issues before they reach production.
The article discusses the challenges and solutions for developing long-running AI agents, particularly focusing on the Claude Agent SDK.
The article introduces advanced tool use features on the Claude Developer Platform, focusing on enabling AI agents to utilize tools more efficiently.
The article discusses the Model Context Protocol (MCP), an open standard for connecting AI agents to external systems, and how code execution can enhance the efficiency of these agents.
11 min read
Includes Code
Has Summary
--
The article discusses enhancements in Claude Code, focusing on new sandboxing features that improve security and autonomy for developers.
6 min read
Includes Code
Has Summary
--
The article discusses the development of Agent Skills, which are organized folders of instructions, scripts, and resources that enhance the capabilities of general-purpose agents like Claude.
The article discusses the emerging concept of context engineering for AI agents, emphasizing the importance of optimizing the context provided to large language models (LLMs) to achieve desired beh...
The article discusses the Claude Agent SDK, a tool designed to enable developers to build versatile agents capable of performing coding and non-coding tasks.
11 min read
Includes Code
Has Summary
--
The article provides a detailed postmortem of three infrastructure bugs that affected the response quality of Claude between August and early September.
10 min read
Includes Code
Has Summary
--
The article discusses the Model Context Protocol (MCP) and its role in enhancing the effectiveness of LLM agents through the development of tools.
The article introduces Desktop Extensions, a new packaging format for Model Context Protocol (MCP) servers that simplifies installation for Claude Desktop users.
13 min read
Includes Code
Has Summary
--
The article discusses the development of a multi-agent research system, detailing its architecture, benefits, and the lessons learned during its transition from prototype to production.
18 min read
Has Summary
--
Claude Code is a command line tool designed for agentic coding, allowing for flexible integration of AI into coding workflows.
The article discusses the implementation and benefits of the 'think' tool for Claude, enhancing its problem-solving capabilities in complex scenarios.
11 min read
Includes Code
Has Summary
--
The article discusses the upgraded Claude 3. 5 Sonnet model, which achieved a score of 49% on the SWE-bench Verified benchmark, surpassing the previous state-of-the-art model's score of 45%.
15 min read
Includes Code
Has Summary
--
The article discusses the development of effective agents using large language models (LLMs), emphasizing the importance of simplicity and composability in their design.
15 min read
Has Summary
--
The article introduces Contextual Retrieval, a method that enhances Retrieval-Augmented Generation (RAG) by improving the retrieval step through Contextual Embeddings and Contextual BM25.
You've reached the end! All 19 articles loaded.