Tagged: evaluation

LLMOps analyst: conversation designer's next career step

How conversation designers are evolving into LLMOps analysts, and why linguists are uniquely suited for monitoring, evaluating, and improving GenAI systems in production.

ALCPE: A Practitioner's Guide â R. Verity Vabolis

Claude Code: what's new for the garden

Five short experiments validating new Claude features (March 2026 release) on the digital garden. Practical demos for conversation designers.

Experiment 1: scheduled garden health check

Testing Claude Code's new scheduled tasks feature by automating weekly garden health checks.

The issue with LLM hallucinations: knowledge as a missing fundamental

Will we ever solve hallucinations in LLMs?

Fingers crossed is a figure of speech, DALL-E!

DALL-E 3 is still digitally challenged.

2 years and 700 members: insights from Convoclub

The top 5 challenges that conversation designers face, based on 300 real answers.

Putting the design in prompt design

Blind prompting vs. prompt engineering, and what it means for conversation designers.

An evening with YouChat and Chatsonic, with a bit of a twist

Both can access the internet and retrieve recent information. Let's take them for a test drive.

How to create your own content quality audit

5 checks to keep your content on track, and your clients happy.