Building AI Assistants:
Lessons from production


How to evaluate LLMs: Full LLM evaluation guide
How to evaluate LLMs: Full LLM evaluation guide
This post is a practical guide to making LLMs more reliable, based on a talk I recently gave at PyData London. I’ll walk you through a framework we use at ParsLabs to go from experiments to production.
This post is a practical guide to making LLMs more reliable, based on a talk I recently gave at PyData London. I’ll walk you through a framework we use at ParsLabs to go from experiments to production.
May 20, 2025
May 20, 2025
Read more ->


Best practices from 7 years of building AI Assistants
Best practices from 7 years of building AI Assistants
In this post, you'll find practical advice on everything from problem definition and user research to advanced AI model training and continuous improvement. We'll explore why these often-overlooked aspects are crucial for success and how you can implement them in your own AI projects.
In this post, you'll find practical advice on everything from problem definition and user research to advanced AI model training and continuous improvement. We'll explore why these often-overlooked aspects are crucial for success and how you can implement them in your own AI projects.
Nov 5, 2024
Nov 5, 2024
Read more ->


How to effectively test AI Assistants
How to effectively test AI Assistants
In this post, I’ll share my approach to testing AI Assistants, drawing from both 7 of experience working in Conversational AI space and insights from industry experts.
In this post, I’ll share my approach to testing AI Assistants, drawing from both 7 of experience working in Conversational AI space and insights from industry experts.
Aug 22, 2024
Aug 22, 2024
Read more ->