Who this is for
Designers, PMs, and UX researchers who need to capture raw user behavior before confirmation bias rewrites it.
The moment this saves you
An hour after a user test my brain has quietly rewritten the session into the result I wanted, so the genuinely surprising thing the user did, the part I needed to hear, gets sanded down into agreement with my own assumptions.
See it work
Messy spoken thought in. A clean, structured artifact out.
User research note from the session I just ran. The user was trying to create their first project. Big observation, they completely missed the create button, it's top right and they kept looking in the center and the left sidebar, took them like 90 seconds to find it, that's a real problem. They also said out loud quote I don't know what a workspace is versus a project, so our terminology is confusing them. The thing that surprised me, they loved the templates, lit up and said oh this is helpful, I didn't expect that to be the highlight. One quote to keep, they said this feels like it's built for people who already know what they're doing. Ouch but useful.
User research observation, June 5, 2026
- Task: Create their first project
- Key friction: Missed the "create" button (top-right) entirely, kept looking center and left sidebar, ~90 seconds to find it
- Terminology confusion: Said "I don't know what a workspace is versus a project"
- Surprise (positive): Loved the templates, "oh this is helpful," unexpectedly the highlight
- Quote to keep: "This feels like it's built for people who already know what they're doing."
The workflow
Record a voice note
Hit the hotkey and talk, no formatting, no typing.
Tag it with this context
Contextli shapes your words into the structured output above.
Find it later
Everything's searchable and organised by context.
Pull it into Claude or ChatGPT
Bring your contexts straight into your AI tools with the Contextli MCP.
Your raw recording and transcription stay on your device, so you can always go back to the original.
The prompt behind this context
I'm going to recount a user research or usability session I just ran. Turn it into a research observation: a bold "User research observation, [today's date]" heading, then labeled lines: Task (what the user was trying to do), Key friction (where they struggled, with specifics and timings), Terminology confusion (only if relevant), Surprise (anything unexpected, positive or negative), and Quote to keep (verbatim user quotes, in quotation marks). Preserve exact user quotes and behaviors, do NOT interpret them into conclusions or recommendations. Don't invent quotes or behaviors. Output only the observation.
Make it your own. This is a starting point. Once it's in Contextli, tweak the instructions so the output comes out exactly how you like it.
Use this context
One click copies it and shows you exactly how to drop it into Contextli.
Next, open Contextli, go to the Contexts page, click Import, choose From JSON, paste, then Import Context. It is ready to use.
Make it your own. This is a starting point. Once it's in Contextli, tweak the instructions so the output comes out exactly how you like it.
Your raw recording and transcription stay on your device, so you can always go back to the original.
Related contexts
Product Demo Feedback
You watch a user try your product and see exactly where it breaks down, then the meeting moves on and the insight gets diluted. Speak what you observed right after. You keep the raw signal, the confusion, the workaround, the delight, so the team fixes the real thing.
Design Critique Note
You can feel exactly what's off about a design but writing the feedback so it's clear and not crushing takes ages. Talk through what works and what doesn't and why. You get structured critique, organized and constructive, ready to hand over without bruising anyone.
Feature Request
A customer asks for something and it lands in your head as a vague 'they want X.' Say what they actually asked and the problem underneath. You get a brief with the real user problem, not just the feature, so the backlog reflects needs instead of demands.
Questions people ask
Questions designers ask about User Research Observation
What is the best way for a designer to capture research observations without missing what the candidate is saying?
Stay fully present during the interview, then speak a structured debrief immediately afterward. The User Research Observation context converts your spoken observations into a research observation covering the competencies assessed, key quotes, and your recommendation. You take better notes because you listened better.
What should a research observation include?
It should include the date, the candidate name and role, the competencies or areas assessed, the key observations and quotes, your overall impression, and your recommendation with reasoning. The User Research Observation context structures your spoken debrief to cover these areas consistently across all candidates.
How do I take research observations quickly between back-to-back interviews?
Dictate a 60 to 90 second spoken debrief into Contextli using the User Research Observation context right after each interview. The context produces a structured research observation in under two minutes. Because the format is consistent, you can compare candidates directly at the end of the day.
How do I share research observations with a hiring panel after an interview?
Copy the structured research observation that Contextli produces and paste it into your ATS, a shared document, or the hiring channel. Because the output is consistently formatted, panel members can read and compare notes across candidates without reformatting.
How do I add this context to Contextli?
Copy the context on this page, then open Contextli and go to the Contexts page. Click Import, choose From JSON, paste it into the Import from Clipboard window, and click Import Context. It is ready to use in under 30 seconds. If you do not have Contextli yet, you can download it for free first.
Is my voice recording private? Does Contextli send it anywhere?
Your voice recording and the transcription are stored on your device only. Contextli processes your audio locally and does not send your recordings or transcription text to any server. The structured output it produces is text you control, and you decide where it goes.
Can I change what the output looks like?
Yes. Every context in Contextli is a starting point you can edit. Open the context in the app, change the instructions to adjust the structure, tone, or fields, and save. The next time you use it, the output reflects your changes. You are not locked into the default format.
Do I need to install an app to use this context?
Yes. Contextli is a free app. Download it, then copy this context and paste it into the Import from Clipboard window on the Contexts page. The whole process takes about 30 seconds.