AI Analysis

Running AI-assisted analysis, tools, tactics and more

4 hours of analysis + documentation in 14 minutes with zero uploads 👉 Claude Code for customer research.

The October 2025 Edition

Oct 31, 2025

•

9 min read

Testing an AI-embedded browser for research uses, a 4-month roadmap to adopt AI meaningfully, and more...

The September 2025 Edition

Sep 30, 2025

•

10 min read

The GPT-5 Issue | What’s better, what’s not, what to do with Agent Mode + a study on context windows.

The August 2025 Edition

Aug 29, 2025

•

8 min read

Transcription evaluations head-to-head, and NotebookLM's "hidden" transcripts - are they any good? Plus a speedy test protocol...

The July 2025 Edition

Jul 31, 2025

•

6 min read

Preventing AI's basic math errors, fast data cleaning, a viral study, a meta-prompting addition worth thinking about, and more...

The June 2025 Edition

Jun 30, 2025

•

12 min read

A Claude 4 vs 3.7 reasoning test, new Claude system prompts, and "MCP" explained...

The May 2025 Edition

May 31, 2025

•

10 min read

My new favorite LLM for customer research, what we can use AI benchmark tests for, and scientists may have found the most efficient way to prompt...

The April 2025 Edition

Apr 30, 2025

•

12 min read

AI designs: From insights to test-ready prototype views faster (a workflow), the options on the market, and data privacy issues -

The March 2025 Edition

Mar 31, 2025

•

10 min read

My framework for evaluating AI tools systematically, checking AI privacy policies, and a shiny new model...

The February 2025 Edition

Feb 28, 2025

•

13 min read

Generate your own data for unlimited experiments, a study on sentiment analysis, DeepSeek data privacy issues, and more...

The January 2025 Edition

Jan 31, 2025

•

10 min read

The results are in: I ran a study with AI Moderators and 70+ real participants. This is what I found -

The December 2024 Edition

Dec 19, 2024

•

16 min read

Make more impact with insights personalized for stakeholders, faster usability test planning, an "agentic" process for following up feedback, and more...

The November 2024 Edition

Nov 30, 2024

•

8 min read

The Upside of Bias in AI Research and "Does ChatGPT Treat Us All the Same?" Plus faster surveys, data anonymization, and more...

The October 2024 Edition

Oct 31, 2024

•

11 min read

Should we let AI do our Quantitative Analysis? Can AI recognize emotions like humans can? Plus OpenAI's new model, and more...

The September 2024 Edition

Sep 30, 2024

•

17 min read

Build a Custom GPT, 6 Low-risk Data Sources for AI testing, and more

The August 2024 Edition

Aug 30, 2024

•

9 min read

AI for Analysis, the big LLMs' privacy policies, and a tool for comparing LLMs yourself

The July 2024 Edition

Jul 31, 2024

•

8 min read

AI for note-taking, a prompting use case and an intro to “RAG”

The June 2024 Edition

Jun 29, 2024

•

9 min read

Comparing new ChatGPT-4o vs. 4 for research tasks, questions for teams pre-AI integration, and Anthropic thinks they know how LLM "brains" work

The May 2024 Edition

May 31, 2024

•

12 min read

Miro vs. Figma AI's for synthesis, creating your team's prompt library, and a replacement for LLM prompting skills. Plus: How well can we trust AI text summaries?

The April 2024 Edition

Apr 26, 2024

•

9 min read

AI Analysis

4 hours of analysis + documentation in 14 minutes with zero uploads 👉 Claude Code for customer research.

Testing an AI-embedded browser for research uses, a 4-month roadmap to adopt AI meaningfully, and more...

The GPT-5 Issue | What’s better, what’s not, what to do with Agent Mode + a study on context windows.

Transcription evaluations head-to-head, and NotebookLM's "hidden" transcripts - are they any good? Plus a speedy test protocol...

Preventing AI's basic math errors, fast data cleaning, a viral study, a meta-prompting addition worth thinking about, and more...

A Claude 4 vs 3.7 reasoning test, new Claude system prompts, and "MCP" explained...

My new favorite LLM for customer research, what we can use AI benchmark tests for, and scientists may have found the most efficient way to prompt...

AI designs: From insights to test-ready prototype views faster (a workflow), the options on the market, and data privacy issues -

My framework for evaluating AI tools systematically, checking AI privacy policies, and a shiny new model...

Generate your own data for unlimited experiments, a study on sentiment analysis, DeepSeek data privacy issues, and more...

The results are in: I ran a study with AI Moderators and 70+ real participants. This is what I found -

Make more impact with insights personalized for stakeholders, faster usability test planning, an "agentic" process for following up feedback, and more...

The Upside of Bias in AI Research and "Does ChatGPT Treat Us All the Same?" Plus faster surveys, data anonymization, and more...

Should we let AI do our Quantitative Analysis? Can AI recognize emotions like humans can? Plus OpenAI's new model, and more...

Build a Custom GPT, 6 Low-risk Data Sources for AI testing, and more

AI for Analysis, the big LLMs' privacy policies, and a tool for comparing LLMs yourself

AI for note-taking, a prompting use case and an intro to “RAG”

Comparing new ChatGPT-4o vs. 4 for research tasks, questions for teams pre-AI integration, and Anthropic thinks they know how LLM "brains" work

Miro vs. Figma AI's for synthesis, creating your team's prompt library, and a replacement for LLM prompting skills. Plus: How well can we trust AI text summaries?

The only newsletter keeping you updated on AI for Customer Research