July Dosu Drop: Public Spaces enter the chat
Introducing Public Spaces, now in beta, which are free public knowledge bases for open source projects.
Devin Stein
Author • 12 posts
Browse by Author
Articles by Devin Stein
AI Is Better at Maintaining Docs Than Humans
People have dreamed of living documentation–documentation that evolves as fast as your code–for decades but human bandwidth to review and update documentation has always been the bottleneck. Now with AI, we have a way to couple written knowledge to code and get the best of both worlds: easy to understand documentation that evolves with your code.
Building the future of knowledge management - June Dosu Drop
June Dosu Drop: One-click documentation, @ mentions, improved code reasoning, and the new fact-based reasoning agent now GA. Building the future of automated knowledge management.
Dosu's new fact-based reasoning agent is generally available
Dosu's new fact-based reasoning agent is now generally available, featuring smarter problem-solving, customizable behavior controls, and improved knowledge management for development teams.
May 2025 Dosu Drop - New Agent, Self-Serve Pricing, Fresh Look
Introducing Dosu's new fact-based reasoning agent, self-serve pricing, and a fresh new look in our May 2025 update.
April 2025 Newsletter - Dosu Does Docs
April 2025 updates from Dosu - focusing on documentation automation and improvements.
March 2025 Newsletter - Dosu Knows
March 2025 updates from Dosu - introducing new features and community insights.
February 2025 Newsletter - Introducing Spaces
February 2025 updates: Introducing Spaces - share data sources across channels, plus new preview generation and inbox features for better team collaboration with Dosu.
Open Source Labeling Best Practices
Best practices for labeling issues and pull requests in open source projects.
How Dosu Used LangSmith to Achieve a 30% Accuracy Improvement with No Prompt Engineering
There are many techniques for “teaching” LLMs to improve their performance on specific tasks. The most common are:
Iterating Towards LLM Reliability with Evaluation Driven Development
How to improve LLM reliability through evaluation-driven development practices.
Reliable Data Orchestration for AI Applications
How to build reliable data orchestration systems for AI applications.