How Espressif deploys Kapa across its docs, products, and internal teams
"We tried building our own AI agent for our technical documentation. It never gained much traction. Kapa did, fast. Now our users get instant, cited answers on their own, no waiting for us."
Krzyzstof B.
Customer Education Leader, Espressif
Challenge
A self-serve community of millions asks technical questions around the clock, across dozens of chips and ESP-IDF versions, and an in-house AI agent never gained traction.
Solution
Deploy Kapa across the docs, the website, and a public MCP server, all grounded in one corpus spanning documentation, GitHub code, datasheets, PDFs, OpenAPI specs, and YouTube.
Results
Thousands of customer queries addressed daily across four surfaces
Over 82% of users found answers helpful
Over 60% of queries answered in Chinese
Over 100,000+ hours saved in support hours
Documentation Agent
Answers scoped to ESP32 variant and IDF version
A chat agent embedded on your docs site that answers natural-language questions with citations back to source. On documentation.espressif.com it pins answers to the exact ESP32 variant and ESP-IDF version, instead of making developers scan five documents.
Play video
Website Agent
Product-fit questions answered on espressif.com
The same agent embedded on your marketing site with one script tag, answering from the docs wherever visitors ask. Espressif runs it on espressif.com, so visitors confirm feature and protocol support directly on the product page.
Play video
MCP Server
ESP-IDF context via mcp.espressif.com
A hosted MCP server connected to your knowledge base, shareable as a single link for Cursor, Claude Code, or ChatGPT. Espressif hosts it publicly at mcp.espressif.com, grounding any developer's coding agent in ESP-IDF and chip specifics.
Play video
Why Kapa
Every deployment runs on the same corpus and answer engine, so an answer on the website, in the docs, inside an Espressif-built experience, through the Retrieval API, or in a coding agent stays consistent and traceable to source.
Espressif adds a surface without rebuilding its knowledge base, and updates reach every agent at once as chips and SDKs evolve, which is how a lean documentation team keeps pace with a community of millions.
