<?xml version="1.0" encoding="utf-8"?>
<feed xml:lang="en-us" xmlns="http://www.w3.org/2005/Atom"><title>Simon Willison's Weblog: userresearch</title><link href="http://simonwillison.net/" rel="alternate"/><link href="http://simonwillison.net/tags/userresearch.atom" rel="self"/><id>http://simonwillison.net/</id><updated>2023-11-23T17:37:04+00:00</updated><author><name>Simon Willison</name></author><entry><title>The 6 Types of Conversations with Generative AI</title><link href="https://simonwillison.net/2023/Nov/23/6-types-of-conversations-with-generative-ai/#atom-tag" rel="alternate"/><published>2023-11-23T17:37:04+00:00</published><updated>2023-11-23T17:37:04+00:00</updated><id>https://simonwillison.net/2023/Nov/23/6-types-of-conversations-with-generative-ai/#atom-tag</id><summary type="html">
    
&lt;p&gt;&lt;strong&gt;&lt;a href="https://www.nngroup.com/articles/AI-conversation-types/"&gt;The 6 Types of Conversations with Generative AI&lt;/a&gt;&lt;/strong&gt;&lt;/p&gt;
I’ve hoping to see more user research on how users interact with LLMs for a while. Here’s a study from Nielsen Norman Group, who conducted a 2-week diary study involving 18 participants, then interviewed 14 of them.&lt;/p&gt;

&lt;p&gt;They identified six categories of conversation, and made some resulting design recommendations.&lt;/p&gt;

&lt;p&gt;A key observation is that “search style” queries (just a few keywords) often indicate users who are new to LLMs, and should be identified as a sign that the user needs more inline education on how to best harness the tool.&lt;/p&gt;

&lt;p&gt;Suggested follow-up prompts are valuable for most of the types of conversation identified.


    &lt;p&gt;Tags: &lt;a href="https://simonwillison.net/tags/usability"&gt;usability&lt;/a&gt;, &lt;a href="https://simonwillison.net/tags/ux"&gt;ux&lt;/a&gt;, &lt;a href="https://simonwillison.net/tags/userresearch"&gt;userresearch&lt;/a&gt;, &lt;a href="https://simonwillison.net/tags/ai"&gt;ai&lt;/a&gt;, &lt;a href="https://simonwillison.net/tags/generative-ai"&gt;generative-ai&lt;/a&gt;, &lt;a href="https://simonwillison.net/tags/llms"&gt;llms&lt;/a&gt;&lt;/p&gt;



</summary><category term="usability"/><category term="ux"/><category term="userresearch"/><category term="ai"/><category term="generative-ai"/><category term="llms"/></entry><entry><title>Do I need to change something on my LIVE website to do Remote usability testing? Am I needed to create a duplicate copy of my website?</title><link href="https://simonwillison.net/2013/Jul/29/do-i-need-to/#atom-tag" rel="alternate"/><published>2013-07-29T18:31:00+00:00</published><updated>2013-07-29T18:31:00+00:00</updated><id>https://simonwillison.net/2013/Jul/29/do-i-need-to/#atom-tag</id><summary type="html">
    &lt;p&gt;&lt;em&gt;My answer to &lt;a href="https://www.quora.com/Do-I-need-to-change-something-on-my-LIVE-website-to-do-Remote-usability-testing-Am-I-needed-to-create-a-duplicate-copy-of-my-website/answer/Simon-Willison"&gt;Do I need to change something on my LIVE website to do Remote usability testing? Am I needed to create a duplicate copy of my website?&lt;/a&gt; on Quora&lt;/em&gt;&lt;/p&gt;

&lt;p&gt;You should be able to run a working copy (potentially with fake data or a subset of your production data) on your laptop, for development purposes. You can use the same setup for usability testing new features.&lt;/p&gt;

&lt;p&gt;If you or your team can't do this I'd suggest fixing that as soon as possible. Not having an effective development environment is a huge productivity disadvantage.&lt;/p&gt;
    
        &lt;p&gt;Tags: &lt;a href="https://simonwillison.net/tags/usability"&gt;usability&lt;/a&gt;, &lt;a href="https://simonwillison.net/tags/web-development"&gt;web-development&lt;/a&gt;, &lt;a href="https://simonwillison.net/tags/quora"&gt;quora&lt;/a&gt;, &lt;a href="https://simonwillison.net/tags/userresearch"&gt;userresearch&lt;/a&gt;&lt;/p&gt;
    

</summary><category term="usability"/><category term="web-development"/><category term="quora"/><category term="userresearch"/></entry><entry><title>What activities, games or examples have you used to persuade developers that they are different from 'real' users?</title><link href="https://simonwillison.net/2012/Feb/22/what-activities-games-or/#atom-tag" rel="alternate"/><published>2012-02-22T13:52:00+00:00</published><updated>2012-02-22T13:52:00+00:00</updated><id>https://simonwillison.net/2012/Feb/22/what-activities-games-or/#atom-tag</id><summary type="html">
    &lt;p&gt;&lt;em&gt;My answer to &lt;a href="https://www.quora.com/What-activities-games-or-examples-have-you-used-to-persuade-developers-that-they-are-different-from-real-users/answer/Simon-Willison"&gt;What activities, games or examples have you used to persuade developers that they are different from &amp;#39;real&amp;#39; users?&lt;/a&gt; on Quora&lt;/em&gt;&lt;/p&gt;

&lt;p&gt;I doubt there's anything as effective as getting them to watch a well-run usability test - either a video, a fancy one-way glass setup or just having them quietly observe a zero-budget testing session in a coffee shop.&lt;/p&gt;
    
        &lt;p&gt;Tags: &lt;a href="https://simonwillison.net/tags/ui"&gt;ui&lt;/a&gt;, &lt;a href="https://simonwillison.net/tags/usability"&gt;usability&lt;/a&gt;, &lt;a href="https://simonwillison.net/tags/quora"&gt;quora&lt;/a&gt;, &lt;a href="https://simonwillison.net/tags/ux"&gt;ux&lt;/a&gt;, &lt;a href="https://simonwillison.net/tags/userresearch"&gt;userresearch&lt;/a&gt;&lt;/p&gt;
    

</summary><category term="ui"/><category term="usability"/><category term="quora"/><category term="ux"/><category term="userresearch"/></entry></feed>