AI shouldn't write your tech docs, it should enforce the standards

Maintaining tech docs has been a chore for developers. Naturally, it led to explore Gen AI to solve this boring and often complex task. Only to end up more burned out and making it even harder and slower for potential users to use their product.

In this talk, Pradeep shares his experiences doing the same as a Developer Relations Specialist. He shares his initial failures and the insights that led to dramatic improvements in tech docs. By the end of the talk, you'll learn the process which helped protecting the human aspect of tech docs while complimenting the weaknesses of humans maintaining the tech docs using LLM agents.

The first part of the talk will cover how to think about the documentation to avoid creating convoluting tech docs structure. Primarily by organizing docs into four categories - Tutorial, Reference, How To Guides, Explanation.

The second part will cover the effective automation using AI in the real-world that led to improved technical accuracy and comprehensiveness. This section of the talk will break the common falsehood that AI usage will lead to degraded docs quality. Pradeep will share the Open Source code for the automation that helped fix technical mistakes in the docs before they frustrate more users.

• Finding the right balance between autonomy and oversight for your AI agent

• Diataxis is a decent framework to improve tech docs comprehensiveness

• Effectively using and improving AI agents for tech documentation