We're hosting a happy hour with Reducto on what it's like building for agents as the primary user. Join us for food, drinks, and a fireside chat after the AI Engineer World’s Fair. June 29th, 6PM PDT, San Francisco
About us
Knowledge infrastructure for AI. Mintlify powers docs for 20,000+ companies, reaching 100M+ developers a year. When humans or agents need to understand your product, they start with your docs. We make sure they find the right answers. We're hiring in SF at mintlify.com/careers.
- Website
-
https://mintlify.link/li
External link for Mintlify
- Industry
- Software Development
- Company size
- 51-200 employees
- Headquarters
- San Francisco, California
- Type
- Privately Held
- Founded
- 2022
Products
Locations
-
Primary
Get directions
San Francisco, California, US
-
Get directions
1 Post St
San Francisco, California 94104, US
Employees at Mintlify
Updates
-
Companies are pulling back on AI spend for the first time. We ran a controlled experiment to answer one question: Does structured documentation actually make coding agents better? We worked with a company running Claude Code on million-line monorepos daily, with a full team dedicated to one thing: making their agents more efficient. We tested their environment against two conditions: 1. No docs, just the codebase 2. Docs + the codebase When you provide agents with structured information, you get → 64% more precise answers → 39% better discoverability → ~50% fewer tokens per task → 1.5x faster completion Better models don't address the issues on cost or efficiency. Working from raw code, they still relearn the whole codebase every session, burning context just to orient themselves.
-
-
Your users can now help improve your site. When visitors can't find what they need, every person asking the same question hits the same wall. Now when someone queries your site, Mintlify detects frequent question patterns, flags the gap, and auto-drafts a fix. One question improves the knowledge for everyone after.
-
Mintlify reposted this
Let's be honest, nobody likes maintaining docs. And now, not only are humans reading docs but so are agents. When agents read incorrect quickstarts, they will fail silently and immediately choose an alternative. The cost of outdated content just got a lot higher. Manually updating info will never keep up with how fast agents move. We found a solution ↓
-
Mintlify reposted this
Companies like Granola, Lovable, and Box are using Mintlify to build their support centers. Mintlify's help center starter kit comes fully equipped with: → an AI assistant that updates your support center based on user questions → a web editor simple enough for anyone on your team to use → a Slack agent that turns support conversations into help articles