Fern

In case you didn’t know already, Fern is awesome. They just added something new to make it easier to test their Ask AI functionality because I asked them to 💖 👏 For some upcoming work, I wanted to run a small eval project to see what information users would get in response to questions using the Ask AI widget in our Fern-hosted docs. They expose a Post Chat Completion endpoint that gives you programmatic access to the tool, but I noticed two things: - The widget scopes retrieval to pages under a product path, but the endpoint didn’t expose the ability to scope the retrieval similarly - When I was hitting the endpoint, my queries were showing up alongside user data in the tool analytics, potentially skewing the “real” user queries. There was no way to say “I’m just testing, don’t count this in analytics” I raised both to Ryan Amirthan Stephen and now Fern has shipped 2 new params to help! Big thank you to all involved. Related, if you’ve got docs on Fern, did you know you can programmatically test and run evals to see if your users are getting the answers you expect? It’s a great way to learn about gaps or conflicting info in your docs. (It does get billed toward your usage, though, so use it strategically.)

Introducing Fern Agent Automations. Schedule recurring documentation and analysis tasks to run automatically. Here's how it works:  • One prompt + cron equates to an agent run. Each run is a normal Fern Agent conversation with your prompt as the message.  • It acts as you, not as a bot. A one-time OAuth consent means every edit and PR carries exactly your permissions.  • Doc edits run as durable background jobs that wake the agent when they land; it reports the PR, then you get the email/Slack DM. Built by Cade Sarkin

We launched Fern Agent earlier this week. Now, Clay Tondreau and Mathieu Legault explain how and why we built it the way we did. → One toolset for our agent and yours. Our MCP server reads the same registry, so your Claude Code gets the same tools Fern Agent uses. → Fern Agent edits docs with a specialist subagent that already knows Fern configuration and components.  → Fern Agent acts as you, never as itself. Every request carries your own auth token. Everything it reads from the outside world is screened for prompt injection

“Fern has been such a great partner. It’s one of the best vendor relationships I’ve ever had. They know what we need because they ask us.” - CT S., Director of Documentation at Payabli

Introducing Fern Agent. Use it to complete any docs task wherever you want to work: start a chat in the Fern Dashboard, @Fern in Slack, or use MCP in your favorite coding agent. - “Look at user feedback for the past 7 days and create a PR for improvements” - “Tell me how to improve the SEO of my site” - “Reorganize my navigation based on how readers are using my site” Built by Mathieu and Clay

We're proud to power ElevenLab's CLI. Build your own CLI with Fern: https://lnkd.in/gU3G5CdX

We’re excited to have Fern sponsoring Write the Docs Berlin 2026! Fern helps teams deliver SDKs and API docs they're proud to share. Start with an API spec, and generate SDKs in multiple languages and interactive API documentation tailored to your brand. 💡 Stop by and chat with them at WTD Berlin, Sep 6-8 Tickets: https://lnkd.in/effyVHiy

We’re excited to have Fern sponsoring Write the Docs Berlin 2026! Fern helps teams deliver SDKs and API docs they're proud to share. Start with an API spec, and generate SDKs in multiple languages and interactive API documentation tailored to your brand. 💡 Stop by and chat with them at WTD Berlin, Sep 6-8 Tickets: https://lnkd.in/effyVHiy

Payabli's APIs change daily. Their docs keep up because code examples live in one place: their spec. Using Fern's built-in request/response examples, Payabli defines named examples with realistic data once in their API definition and references them into the docs. They now save 200+ hours a year on example maintenance.