It's Dosu Drop day! 🎉 We have an MCP Server preview (your coding agents can access Dosu's knowledge), an improved diff UI, and we're searching for design partners to test Notion/Confluence/GitHub sync. Let us know if you're interested in taking a look! dosu.dev/blog/january-2026-dosu-drop

a little gift before the holidays! checkout the Dosu's new year resolution for what's to come in 2026

thankful we don't need to write changelogs anymore 🦃

Come for the updates, stay for Michael Mangus' storytelling. The newsletter content will not disappoint!

make your docs age like wine, not milk, with Dosu :)

feels like magic to see documentation you wrote months ago automatically reflect the latest business logic changes when a PR is merged

we are building out free public living knowledge bases for every OSS project what features would you like to see? what projects do you want us to create a knowledge base for?

Honored to be featured in @github.com's first "Awesome Continous AI" list. Read all about it! 👇 go.dosu.dev/74utNAE

human jobs vs ai jobs for documentation, a human job is deeply understanding your audience and what content is important to them an AI job is maintaining that content as your code and product changes

It's hard enough to remember to document learnings, but it's near impossible to remember to keep that documentation up-to-date. Let AI do it for you!

the team had a ton of fun rebuilding Dosu's agent architecture based on what we've learned over the past year. we have technical blog posts in the works, but an early user's reaction of "first time AI has genuinely impressed me." does a good job of summing it up the results :)

Most companies say docs matter, but @mplacona.com 🧮 crunched the numbers. Good docs = -$22k/year wasted per dev just hunting for answers -$1.25M/year in onboarding drag for a 100-dev org -$50k+ in support costs you could deflect with self-service 👇 Full breakdown (with data)👇 go.dosu.dev/HcW2dLS

Ai documentation is the best i got; parsing though complex code, making clear and searchable human readable tutorials for software that updates so often that human made documentation not only becomes out of date quickly.. it actively acts as a decoy to actually finding out what you need to know.