Anthropic uses Claude Code for 100% of pull requests

// 2h agoNEWS

Anthropic uses Claude Code for 100% of pull requests

A creator of Claude Code revealed that Anthropic heavily dogfoods its own AI coding assistant, using it to run all of their internal pull requests and the vast majority of their code reviews. This highlights the tool's advanced capabilities and Anthropic's confidence in using it for critical software engineering tasks.

// ANALYSIS

Anthropic aggressively dogfooding Claude Code proves its viability for enterprise-grade engineering.

–Relying on an AI tool for 100% of PRs is a massive milestone for AI-assisted development.
–It shows that terminal-based AI agents can handle complex, multi-step workflows like code reviews.
–This high adoption rate internally suggests the tool is highly effective and reliable.

// TAGS

anthropicclaude-codeai-coding-assistantcode-reviewsoftware-engineeringai-coding

DISCOVERED

2h ago

2026-06-15

PUBLISHED

3h ago

2026-06-15

RELEVANCE

8/ 10

AUTHOR

Av1dlive

// KEEP READING

More AI developer news from the feed

EXPLORE FULL FEED

OPEN SOURCE30m ago

SmallHarness launches version 1.0 with model routing, followed by a hotfix introducing active effort routing to control reasoning depth for local and cloud LLMs.

SmallHarness, a terminal-based developer tool for running agentic LLMs on local hardware and cloud APIs, has officially released version 1.0.0, followed by a quick 1.0.1 update introducing active effort routing. The tool supports multiple backends—including Ollama, LM Studio, MLX, llama.cpp, and OpenRouter—and features safe execution of filesystem/shell commands via interactive approval gates and diff previews. The new active effort routing allows the system to analyze task complexity and automatically set reasoning effort levels (from minimal to max) sent to providers like OpenRouter and OpenAI, offering a highly customizable framework that optimizes performance, cost, and latency.

MODEL31m ago

User pans Kimi K2.7-Code in early testing

Early testing of Moonshot AI's Kimi K2.7-Code reveals rapid usage limit exhaustion and broken game generation. The user reports the model struggles with complex tasks, positioning competitor GLM 5.2 as a stronger alternative.

NEWS43m ago

A leak of the Claude Fable 5 system prompt allows users to replicate its frontier capabilities on Claude Opus 4.8 with high accuracy.

A social media post by CodeWithImanshu reveals that the system prompt for Anthropic's frontier Claude Fable 5 model has been leaked. When this extensive system prompt is run on Claude Opus 4.8, it reportedly achieves roughly 90% of the performance of the native Fable 5 model. This highlights how heavily Anthropic relies on prompt-level instruction tuning to define its new Mythos-class agentic behaviors.

Anthropic uses Claude Code for 100% of pull requests