Cracking the Code: How to Streamline Your UX Research Processes with No-Code Tools.
About
There’s just never enough time, especially when you work in UX Research. We will share how we efficiently conduct research by automating mundane tasks such as requests, recruitment, scheduling, and incentive sending. Using an automation tool Make, we have successfully streamlined the busywork of UX, giving us more time for the creative aspects of our roles. Learn that automations aren’t scary or difficult. We have very practical and simple examples that anyone can use to get started.
Watch the full talk
Watch this WaysConf session, then continue with related talks or explore the current programme.
Talk in brief
At WaysConf 2024, Make.com product designer Eva Cizmarikova and UX researcher Michaela Hrackova Pysnakova demonstrate how non-technical user experience professionals can streamline research workflows using no-code automation and generative AI. Addressing common research operations bottlenecks like request tracking, participant recruiting, interview summarization, and survey analysis, the speakers showcase practical Make.com scenarios integrated with everyday tools such as Zoom, Google Workspace, and Slack. They explain how breaking complex research tasks into granular, step-by-step logic enables automated intake forms, personalized bulk recruiting emails, real-time interview summaries, and AI-assisted qualitative survey coding. While AI significantly accelerates routine synthesis, Cizmarikova and Hrackova Pysnakova emphasize its limitations in high-level strategic reasoning, such as building user personas, framing AI as an intern that requires human verification, precise prompt engineering, and structural controls.
Key takeaways
- 01
Deconstruct Workflows into Granular Steps
Automating non-technical research workflows requires decomposing complex stories into precise, sequential baby steps. Breaking down intake and recruiting tasks allows non-coders to create manageable Make scenarios with predictable outcomes.
Watch from 12:00 - 02
Streamline Participant Outreach with Dynamic Templates
Using spreadsheets integrated with email modules allows teams to send bulk recruitment messages while retaining personalization. Dynamic variables populate participant names and session details, ensuring outreach remains targeted and tracked.
Watch from 11:38 - 03
Treat Generative AI as a Supervised Intern
Large language models provide speed but lack deep product context and can generate hallucinations. UX researchers must act as domain experts, reviewing AI outputs and refining prompts to ensure reliable analysis.
Watch from 26:25 - 04
Structure AI Prompts with Specific Rules and JSON
To turn messy interview transcripts or survey text into usable tabular data, prompts must include explicit formatting rules and structural constraints. Leveraging JSON formatting forces AI to output structured data that can be programmatically re-injected into spreadsheets.
Watch from 23:51 - 05
Recognize the Limits of AI in High-Level Strategy
While AI excels at summarizing raw transcripts and tagging survey responses, it struggles with strategic synthesis like persona development. Complex insights require human UX judgment to properly interpret organizational context and high-level patterns.
Watch from 28:25
Read edited transcript highlights
These concise notes were edited from automatic captions and checked against the talk structure. They are not a verbatim transcript.
Managing Intake Chaos with Automated Briefs
When Michaela Hrackova Pysnakova joined Make.com as the sole UX researcher, rapidly growing internal demand created operational tracking challenges. Stakeholders frequently pitched study requests informally, making prioritization and overlapping schedules difficult to manage. Rather than viewing this surge as a problem, she designed two connected Make.com scenarios. The first automation collects structured intake details through a Google Form and writes them into a spreadsheet and project brief template. Upon approval in Slack, the second automation instantly notifies stakeholders with ready-to-go documentation, eliminating manual back-and-forth communication.
Watch from 5:22Scaling Participant Recruitment Without Research Ops
Lacking a dedicated research operations team meant handling participant recruitment and incentives manually, consuming hours of administrative time. To resolve this, Michaela Hrackova Pysnakova built a lightweight scenario connecting Google Sheets with Gmail. The automation filters participant lists based on study criteria and updates contact logs automatically to avoid over-contacting users. By embedding dynamic tokens into email modules—such as individual names, subscription plans, and session dates—the system sends tailored recruitment messages at scale while maintaining a personalized touch.
Watch from 10:01Instant Slack Summaries from Zoom Transcripts
Taking comprehensive notes while moderating user interviews is challenging, and relying on colleagues for note-taking often yields inconsistent results. Eva Cizmarikova experimented with automating session synthesis by pulling Zoom transcripts directly into Make.com after meetings. The transcript passes to an AI model configured with strict prompting parameters, generating structured summaries delivered straight to Slack. By automating note-taking and immediate summary distribution, team members receive real-time visibility into user research without waiting months for a final report.
Watch from 13:58Two-Step Qualitative Survey Analysis via JSON
Analyzing thousands of qualitative survey responses manually is tedious and time-consuming. Michaela Hrackova Pysnakova initially attempted a single AI prompt to categorize survey responses, but received hallucinated quotes and unstructured output. She restructured the workflow into two distinct scenarios. The first prompt generates fifteen representative category tags alongside descriptions and examples, converting unstructured data into clean JSON format. Once a researcher reviews and approves the proposed categories, the second scenario automatically maps those labels back to the raw spreadsheet responses.
Watch from 22:03Strategic Research Limits and the Persona Experiment
When Eva Cizmarikova attempted to generate target user personas from ten summarized interview documents, the AI tool struggled with strategic context. Despite receiving accurate underlying summaries, the model hallucinated details not present in the transcripts and failed to identify crucial higher-level patterns, such as variations across business sizes. This experiment demonstrated that while generative AI excels at administrative synthesis and text tagging, complex strategic analysis still requires human domain expertise and contextual product understanding.
Watch from 27:11