Claude Programming Tutorials & Engineering Articles

The article discusses the limitations of the SWE-bench Verified benchmark in measuring frontier coding capabilities, highlighting issues of contamination and recommending the use of SWE-bench Pro f...

The article introduces Code Mode, a technique that allows AI agents to interact with the entire Cloudflare API using only 1,000 tokens, significantly reducing context window usage.

This article delves into the development and implementation of minions, Stripe's unattended coding agents, which autonomously produce pull requests without human-written code.

The article introduces Markdown for Agents, a feature by Cloudflare that allows AI systems to request web content in Markdown format instead of HTML.

Cursor has significantly increased usage limits for their Auto and Composer 1. 5 models across all individual plans by introducing two separate usage pools.

Stripe built homegrown unattended coding agents called Minions that one-shot entire tasks from Slack message to merged pull request.

This article from Anthropic's engineering team quantifies how infrastructure configuration—specifically resource allocation and enforcement methodology—introduces significant noise into agentic cod...

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 provides practical security guidance for sandboxing agentic workflows, emphasizing the importance of managing execution risk associated with AI coding agents.

Cloudflare introduces Moltworker, an open-source middleware that enables running the Moltbot self-hosted AI agent on Cloudflare's Developer Platform instead of dedicated hardware like Mac minis.

This article details the engineering challenges behind building an animated ASCII banner for GitHub Copilot CLI, revealing how a seemingly simple 3-second animation required over 6,000 lines of Typ...

This article explains the design and implementation of Sprites, Fly. io's new product offering instant-creation Linux VMs with 100GB durable storage backed by object storage.

Fly. io introduces 'Sprites' — durable, persistent cloud computers designed as an alternative to ephemeral sandboxes for AI coding agents.

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 evaluation of chain-of-thought monitorability in AI systems, emphasizing its importance for understanding decision-making processes in models like GPT-5 Thinking.

The article discusses FrontierScience, a new benchmark designed to evaluate AI's capabilities in expert-level scientific reasoning across physics, chemistry, and biology.

This article discusses Spotify's advancements in background coding agents, focusing on the implementation of strong feedback loops to ensure reliable software maintenance.

The article discusses the development of small orchestration agents, specifically the ToolOrchestra method, which automates the selection and management of models and tools for task-solving in AI s...

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.

This article discusses the development and optimization of background coding agents at Spotify, focusing on context engineering to enhance their functionality in code migration tasks.

Google Antigravity is a new agentic development platform designed to enhance software development by allowing users to orchestrate complex tasks through AI-powered agents.

Replicate, a leading platform for running AI models, is joining Cloudflare to enhance the development and deployment of AI applications.

FishDB is a generic retrieval engine developed by LinkedIn to replace the legacy FollowFeed system, enhancing scalability and performance for their feed infrastructure.

This article details the transformation of ClickHouse's internal data warehouse from a traditional BI-first approach to an AI-first model, significantly enhancing user accessibility to analytics.

The article discusses the benchmarking of AI coding assistants in writing efficient CUDA code using the ComputeEval framework.

Thomas Ptacek argues that every developer should build an LLM agent to truly understand the technology, demonstrating through progressive Python code examples that a functional agent with tool use ...

Netflix introduces Spin, a new feature in Metaflow 2.

The article discusses how weather data can be derived from airplane telemetry using ADS-B data.

The article discusses enhancements in Claude Code, focusing on new sandboxing features that improve security and autonomy for developers.

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 dual role of AI-enabled developer tools, highlighting both their potential to accelerate coding and the security vulnerabilities they introduce.

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.

The article introduces GDPval, a new evaluation framework designed to measure AI model performance on economically valuable, real-world tasks across 44 occupations.

The article discusses the rising costs associated with observability in software engineering and proposes a shift towards open, cost-efficient architectures.

The article discusses the detection and mitigation of scheming behaviors in AI models, particularly focusing on how these models can appear aligned while pursuing hidden agendas.

The article provides a detailed postmortem of three infrastructure bugs that affected the response quality of Claude between August and early September.

The article discusses the integration of Google’s Agent Development Kit (ADK) for Java with the LangChain4j LLM framework, enabling developers to utilize a variety of Large Language Models (LLMs) f...

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 announces the release of Genkit Go 1. 0, a stable, production-ready open-source AI development framework for the Go ecosystem.

AI Week 2025 focused on how to harness the power of AI while maintaining control and security.

The article discusses the complexities of troubleshooting network connectivity and performance issues in corporate environments, particularly with the introduction of Cloudflare's AI-powered tools:...

The article discusses the evolving landscape of web crawling, particularly the impact of AI bots on referral traffic to content creators.

The article discusses the advancements in building real-time voice AI applications on Cloudflare's global network.

The article discusses how to enhance website interactivity by implementing conversational search capabilities using NLWeb and AutoRAG.

The article discusses best practices for securing Generative AI in organizations using Secure Access Service Edge (SASE) architecture.

The article discusses Cloudflare's integration of its Cloud Access Security Broker (CASB) with generative AI tools like ChatGPT, Claude, and Gemini, enabling organizations to assess security postur...

The article discusses the importance of securing generative AI applications within organizations, highlighting the risks of data exposure when employees use these tools.

The article explores the potential of Large Language Models (LLMs) to replace Site Reliability Engineers (SREs) in performing root cause analysis (RCA) for production issues.