Optimal Blog
Articles and Podcasts on Customer Service, AI and Automation, Product, and more
.webp)
Great research has never been about speed alone. It’s about asking the right questions, understanding the context behind them, and uncovering insights that help teams make better decisions.
Optimal's AI Interviewer is designed to support that process. It’s designed to work alongside researchers and teams, so you can move faster without losing the depth and human nuance that makes research valuable.
Shaped by discovery
Before building AI Interviewer, we spoke with and surveyed researchers, designers, and product teams to how they approach interviews today and where AI could genuinely help.
What we heard was consistent:
- Interviews are powerful, but time-intensive
- Scaling across time zones is challenging
- Synthesising conversations can take longer than running them
- And most importantly, context matters
AI isn’t useful if it ignores how your team works. So instead of building a generic interviewer, we focused on building an AI Interviewer that fits into your current workflows and keeps researchers and teams in the driver's seat.
Here’s what we learned and how we brought it to life with Optimal’s AI Interviewer.
Context matters
The best interviews start with a clear understanding of what you’re trying to uncover. With the AI Interviewer, you can add your research goals, audience details, company and product context, and additional context you want the AI to consider. This means the AI doesn’t just ask questions; it understands what you’re trying to learn and helps guide conversations in the right direction.
The same context also powers AI insights, helping ensure summaries, key themes, and citations are relevant, accurate, and aligned with what you're trying to learn.
Control the conversation
One of the concerns with AI-led interviews is not having enough control. We’ve designed the AI Interviewer with this in mind.
For each question, you can choose how deeply you would like the AI Interviewer to probe and follow-up. You decide when deeper exploration is valuable, how the conversation flows, and the AI can then carry this out on your behalf.
Scale your research without losing depth
AI Interviewer helps remove some of the barriers that make qualitative research difficult to scale. Use it to:
- Scale research without hiring additional moderators
- Run interviews across different geographies and time zones
- Keep research moving, even when your team is offline
- Encourage more honest, candid feedback with an AI interviewer that participants may find easier to open up to
This isn’t about replacing researchers. It’s about removing operational work so you can focus on higher-value work, like synthesis, storytelling, and decision-making.
Richer insights, backed by evidence
Every session comes with recordings, key summaries, and AI-generated insights with clear detailed evidence. Instead of reviewing hours of footage, you can quickly find what matters and confidently back it up. Review insights across your full study, or dive deeper into individual sessions and specific questions.
On the roadmap: Once your interviews are complete, you can use AI Chat to go further with your data and explore patterns across sessions, ask follow-up questions, and validate assumptions with real evidence.
Humans in the loop, by design
Let’s address the elephant in the room. AI-led interviews aren’t something everyone is immediately comfortable with, and that’s fair. There are real limitations.
Some research scenarios require human sensitivity and judgment. Nuance, emotion, and edge cases still benefit from a human touch. Vulnerable populations and complex topics should always be handled with care. Optimal values a human-in-the-loop approach and know an AI Interviewer isn’t always suitable. With that in mind, we made sure that:
- You define the context
- You control the structure
- You decide when and how to use it
The AI Interviewer supports your work. It doesn’t replace your expertise.
Early access: help shape what comes next
AI Interviewer is now available in early access, and we’re continuing to learn from the teams using it. If you’re looking to scale your research without scaling your workload, run interviews across time zones, and spend less time on logistics and more time on insights, we’d love for you to try it.
👉 Book a demo to see how it fits into your workflow.
Already with Optimal? Register your interest for early access.
Topics
Research Methods
Popular
All topics
Latest
.webp)
Understanding AI Interviewers and AI Moderation in User Research
AI moderation is often framed as a question of replacement: can an AI interviewer do what a human moderator does, and if so, when should teams use one instead of the other? That framing misses the nuances and context of a study.
AI interviewers introduce another way to conduct research, one that sits somewhere between the scale of unmoderated research and the adaptability of a semi-structured moderated session. An AI interviewer can lead a research conversation on its own, asking questions, following up in real time, and adapting to what a participant says, without a human moderator present. Where that approach fits depends on the research question, the participants, the subject matter, and the stage of the product or idea.
To understand how people who do research are actually thinking about and using AI moderation, and what they see as its value and limitations, we surveyed 80 researchers and product managers across the US, Europe, the UK, and Canada.
What you'll learn
- How teams are actually splitting moderated vs. unmoderated work today
- Which research methods are most common, and where AI moderation shows up in that mix
- What teams expect from an AI interviewer in terms of oversight and control
- Where AI moderation isn't the right fit and where it starts to behave like its own hybrid method
What research teams are actually running in 2026
Before asking where AI interviewers fit, it's worth looking at what teams are running in 2026. Among the teams we surveyed:
- 90% Interviews
- 85% Usability testing
- 75% Surveys
- 71.3% Concept testing
- 40% Card sorting / tree testing
- 31.3% Diary studies
Interviews and usability testing are the most common methods in our data. Both allow you to understand not just what participants do, but the reasoning and context behind their behavior. Choosing a research approach means connecting the question you want to answer with the kind of data you need to answer it, and understanding how that data will lead you to the answer. It also depends on the time and resources you have.
The tradeoff between depth and scale
Half of the teams we surveyed lean to moderated research, while 38.8% run an approximately 50/50 split between moderated and unmoderated research. Notably, zero participants said they run fully unmoderated research. A live moderator gives you the ability to respond, ask why, probe deeper when a participant says something unexpected or interesting, describe a problem you didn't anticipate, and spend more time on an answer that deserves further exploration. But it also comes with practical constraints. You need to recruit participants, coordinate calendars, manage time zones, attend sessions, and find time to review them afterward. The number of sessions a team can conduct is ultimately limited by the team’s availability and capacity.
Unmoderated research removes much of that friction. A study can scale. Teams can reach more participants and run studies in parallel. AI moderation sits between these approaches. It introduces the ability to respond to participants without requiring a researcher to be present for every conversation.
A new approach for gathering qualitative data: AI-moderated research
AI-moderated research uses an AI interviewer to conduct a research conversation without a human moderator present. Instead of presenting participants with a fixed set of questions, the AI can ask a question, interpret the response, and decide what to ask next based on the participant's answer and the goals you set. For instance, you want to understand how users solve a particular problem. One participant might use a third-party tool, another might have developed a manual workaround, while someone else might have a different workflow altogether. The AI can conduct a semi-structured interview, following up differently with each participant, exploring what they do, why they do it, and what they're trying to accomplish so you can really grasp their motivations and behaviors based on your research goals.
60% of participants said they see AI interviewers as a way to conduct significantly more research. That doesn't mean replacing human moderators with an AI interviewer for every study. It means making more sessions possible with the right people in situations where a researcher wouldn't otherwise have the time or resources to moderate every conversation.
Beyond scale, AI interviewers also reduce researcher bias by providing a more consistent interviewing experience. In a pilot study of Optimal’s AI Interviewer, participants also noted the AI interview is easier to talk to than a traditional interview and the on-screen text was helpful for accessibility. Curious what we learned? Read the full study write-up.
Setting parameters and control while using an AI Interviewer
AI interviewers don't automatically add value to a study or help your team gather meaningful insights on their own. The quality of those conversations depends on how well you configure the AI interviewer, the context they provide, and the goals they define.
To get the most out of an AI interviewer, you should begin by providing clear context about the study, the company, its participants, and the product being researched. You can define specific goals at different levels, including the overall study, individual sections, and specific questions. These goals guide the AI in determining which follow-up questions to ask and where to probe more deeply. You can also adjust how actively the AI interviewer probes participants, allowing them to control the depth of follow-up questions when responses are unexpected, unclear, or lack detail.
Limitations of AI Interviewers
Even with thoughtful setup and clear parameters, AI interviewers aren't the right fit for every study. Human moderators will always play an essential role, especially in cases like:
- Sensitive topics or research with vulnerable populations which requires trauma-informed training
- Trust-building conversations and client engagement where the value of the conversation extends beyond data collection and insights
- Early exploratory research, where you don't yet know what you're looking for (AI moderation works best when the research team can provide clear goals and context).
AI interviewers are best understood as an expansion of researchers' capabilities and a new approach to gathering qualitative insight, not a universal replacement for existing methods and approaches.
Insight doesn’t come from AI alone
One of the clearest themes from our research is that people who do research want visibility into how AI-generated research is produced. Teams want to scrutinize the data themselves. They want access to conversations, raw recordings, transcripts, and the ability to sense-check findings against what participants actually said. That matters because AI moderation changes the role of the researcher. Instead of being present for every conversation, researchers can focus on identifying the right people to talk to, developing research questions, organizing priorities, engaging with and aligning cross-functional teams, weighing insights and seeing what requires further exploration, and crafting the bigger story.
AI can conduct more conversations and accelerate the time to insight.
Research teams still need to determine what those insights mean within the context of the market, the business, and everything that surrounds a decision.
AI moderation makes more possible
AI interviewer changes the tradeoff between depth, scale, speed, and the team involved. It is still an emerging approach, and teams are figuring out where it belongs. Its value comes from what it makes possible like more opportunities to ask, follow up, and understand.
More than any single feature, what we're building toward with Optimal Intelligence is a research experience that uplifts human expertise. Technology can accelerate the work. It can't weigh nuanced risk, define ethics, or build relationships. That's still on us.
AI moderation is a new methodology, not a replacement for the ones that came before it. It earns its place in your workflow because of what it makes possible. Discover what our AI Interviewer taught us about conversational AI.
.jpeg)
Best User Research Platforms for 2026
Your research platform shouldn't be the slowest part of your sprint
Your team ships every two weeks. Your research platform takes three weeks to get a study live, recruited and analysed. By the time insights land, the roadmap has already moved on.
Speed is only half of it. A fast study with the wrong participants can be worse than no study at all. Screener gaming, ineligible respondents and AI-written answers are now regular complaints in platform reviews. When your data is skewed, the product decisions built on it are too. Your team pays for that later, in rework, missed adoption targets and a harder conversation with stakeholders.
In 2026 teams are asking more of their tools. They want studies live in minutes, participants they can trust, and pricing that doesn't punish them for doing more research. They want one place to run the methods they rely on, with no stitching together a recruitment tool, a testing tool and a repository.
We've compared seven of the most widely used user research platforms against Optimal on the things that decide whether research shapes what ships. Here's what we found, including where other platforms are the better fit.
How we evaluated each platform
Feature lists all start to look the same. So we judged each platform on five questions that we believe matters to setting up and running a successful research program from the get go:
- Speed to insights. How quickly can you go from a research question to a study in field and results you can share? Approval queues, setup steps and analysis time all count.
- Participant quality and reach. How big is the panel, how many countries does it cover, and how much can you trust the people in it? We also looked at whether you can bring your own participants.
- Ease of setup. Can a designer or PM run a study on their own, or does every study need a specialist?
- Price transparency. Can you see what you'll pay before you talk to sales? Are seats capped, and are core methods locked behind higher tiers?
- Design tool workflow. How well does the platform fit the way your team designs, including Figma prototypes and early concepts?
We used public product pages, help docs, pricing pages and third-party review sites, current as of November 2026. Platforms change quickly, so check current plans before you buy.
The 2026 comparison at a glance
Optimal is the only platform here that combines instant launch, a 20M+ verified panel across 150+ countries, unlimited seats on every plan and core UX research and IA methods with no tier gating.
| Platform | Best for | Participant panel | Setup and launch | Pricing |
|---|---|---|---|---|
| Optimal | Enterprise teams that want every research method and recruitment in one platform |
20M+ · 150+ countries Bring your own free |
Launch instantly, no approval queue Guided setup for designers and PMs |
Quote only Unlimited seats and studies on enterprise plan |
| UserTesting (Auros) | Large enterprises running video-led usability tests on native mobile apps |
2M+ own · 7.6M with User Interviews 40+ countries |
Fast for unmoderated video Moderated sessions use 3-5x more credits |
Quote only Seats plus credits |
| Maze | Product teams validating Figma prototypes inside sprints |
6M+ · 130+ countries Billed separately |
Fast for unmoderated prototype tests Quick to start with free plan |
Free plan Paid tiers and Enterprise on quote |
| Great Question | Research ops teams wanting a participant CRM and repository |
6M+ · 150+ countries Via User Interviews integration |
Fast with your own panel External recruitment through partner |
Free trial Self-serve capped at 5 paid seats |
| Lyssna | Quick design checks like five-second and preference tests |
690K+ · 120+ countries |
Very quick for short tests Simple and self-serve |
Free plan Published tiers with seat caps on lower tiers |
| Dscout | In-context diary studies and mobile-first qualitative research |
530K+ own · 3M+ partner |
Dscout reviews screeners before launch Can add days |
Quote only |
| UXtweak | Smaller teams running usability tests on a tight budget |
Partner panels · 130+ countries |
Quick for single tests Study types can't be combined in one link |
Free plan Published lower tiers, Enterprise on request |
Sources: vendor product, help and pricing pages, plus G2 reviews, as of November 2026.
Platform by platform
Every platform here does something well. The question is whether it does what your team needs, at the pace you work.
Optimal
Optimal is a user insights platform and research repository built by research, product, and design leaders over 19+ years. It covers surveys, card sorting, tree testing, first-click testing, prototype testing, live site testing, native mobile app testing, AI Interviewer, and qualitative insights, all in one place.
- Strengths: Studies go live the moment you're ready, with no review queue. You can recruit from 20M+ verified participants in 150+ countries, or bring your own for free. AI insights, summaries and an AI interviewer help you get from raw data to a shareable finding in minutes. Every plan includes unlimited seats, and the platform holds SOC 2, their management systems and infrastructure is ISO/IEC 27001 and ISO/IEC 27701 certified.
- Limitations: There are no dedicated diary study or five-second test blocks. Teams running long-form diary research may want a specialist tool alongside.
- Best for: Teams that want one platform for evaluative research, IA and recruitment, with room for the whole org to take part.
UserTesting
UserTesting is the long-standing name in remote video research. After merging with UserZoom and acquiring User Interviews, it now sits under the Auros brand.
- Strengths: It covers a broad set of methods, including diary studies and native mobile app testing. Enterprise support and services are deep, and its MCP server connects to AI tools and Figma Make.
- Limitations: Pricing is quote-only and credit-based, and reviewers report yearly price rises. Joining three platforms has left parts of the experience feeling disjointed, and some reviewers flag participant quality and fulfilment delays.
- Best for: Large enterprises with a dedicated research budget and a heavy focus on video usability sessions.
Maze
Maze is built for rapid prototype validation inside design sprints.
- Strengths: It has a well-loved Figma prototype testing flow, a free plan to get started, and a broad AI feature set.
- Limitations: Card sorting, tree testing and its AI Moderator sit on the Enterprise tier. Reviewers report bugs with large prototypes and heatmaps, and first-click tests allow multiple clicks. Panel credits are billed separately.
- Best for: Design teams whose research is mostly quick prototype checks.
Great Question
Great Question combines participant recruitment, a research CRM, mixed-method studies and an AI repository.
- Strengths: Its participant CRM, API and MCP tooling are strong. Observer seats are unlimited, so stakeholders can follow along.
- Limitations: Self-serve plans cap paid seats at five. Card sorting and tree testing sit on Enterprise. External recruitment runs through a User Interviews integration rather than an in-house panel, and some reviewers report lag on large datasets.
- Best for: Research ops teams managing their own customer panel.
Lyssna
Lyssna, formerly UsabilityHub, is a simple, self-serve platform known for five-second and preference testing.
- Strengths: It's quick to learn, has a free plan, and publishes its self-serve pricing. It recently added mobile testing and observer rooms.
- Limitations: Its 690K+ panel has no managed recruitment, and reviewers say niche audiences can be hard to reach. AI analysis is lighter, and does not yet hold enterprise-grade security certifications.
- Best for: Smaller teams running fast design checks.
Dscout
Dscout specialises in in-context, mobile-first qualitative research.
- Strengths: Diary studies are its flagship, and recent AI moderation and insight features are a real investment.
- Limitations: A Dscout advisor reviews screeners before launch, which can add days. Participants download an app, survey logic is limited, and there's no first-click testing.
- Best for: Teams running longitudinal, in-the-moment qual research.
UXtweak
UXtweak is a researcher-founded platform with a broad toolkit, from card sorting to session recordings.
- Strengths: It offers a free plan and published lower tiers, native mobile app testing without an SDK, and testing for AI-generated prototypes.
- Limitations: AI insight is minimal. You can't combine study types in a single link, and reviewers call the setup interface dated. It's a small team, which can limit enterprise support.
- Best for: Budget-conscious teams that want breadth without enterprise requirements.
Why Optimal wins in 2026
If your team runs one kind of study, a specialist tool may be all you need. Most enterprise teams don't work that way. Some weeks you're testing a prototype, other weeks you're restructuring navigation or checking a concept with a hard-to-reach audience. Your team needs a platform that keeps up with all of it.
We've spent 19+ years listening to researchers describe the same frustrations: waiting on approvals, chasing recruits, rationing seats and defending data quality to stakeholders. Optimal is built to remove that friction.
- Insights in minutes. Launch the moment your study is ready, with no review queue, and let AI summaries turn results into findings you can share the same day.
- Participants you can trust. Recruit from 20M+ verified participants across 150+ countries, or bring your own for free. Our recruitment team can help with niche and international audiences.
- Simple enough for everyone. Designers, PMs and researchers run studies with guided setup and templates. Unlimited seats mean the whole team can join in without a budget conversation.
- Optimal Intelligence. Optimal's growing AI and automation capabilities help you refine studies, uncover key themes, summaries, and insights, and dive deeper with AI chat and MCP.
- Clear pricing. You pay one platform fee, sized to your research plan. Card sorting, tree testing and first-click testing come included, with no extra tier to unlock them.
- Built into how you design. Test Figma prototypes or images alongside the IA methods that tell you whether people can find what you've built.
- Enterprise ready. SOC 2, ISO/IEC 27001 and ISO/IEC 27701, with dedicated onboarding and a Customer Success Manager.
Netflix, Nike, Toyota, Apple, LEGO and Workday already trust Optimal with their research. Book a demo and we'll walk through your research plan with you.

Optimal and World Usability Day partner to advance world usability education and responsible AI innovation
Every year on the second Thursday of November, communities around the world come together for World Usability Day to celebrate the practice of designing products for the people they serve. This year, on November 12, 2026, the theme is Designing a Sustainable Future with Ethical AI, exploring how human creativity and intelligent technology can work together to create a better world. It’s a theme that holds particular significance for us, reflecting a shared vision of what’s possible when people and technology come together with purpose.
Shaping a better future, together
Responsible innovation is the process of creating products that deliver value while minimizing unintended consequences and potential harm. This means understanding the broader impact of our decisions on people and our planet, mitigating social and ethical risks, and taking responsibility for what we create.
This work is happening across our industry every day. Researchers, designers, and practitioners are co-designing with users, testing ideas, challenging assumptions, and working to turn what they learn into meaningful improvements. It's an ongoing process of questioning, learning, and advocating, and its impact reaches millions of people through the products and experiences we design. Progress depends on a community that leads with kindness, empathy, and respect; one that shares openly, listens thoughtfully, and lifts others up along the way.
A partnership built on decades of shared purpose
For nearly two decades, we've celebrated the work World Usability Day brings into focus: the vital role of user research in shaping technology that makes a meaningful difference in our world and the power of thoughtful design to shape our everyday experiences. This year, we're excited to take that relationship a step further as a Research Sponsor.
As AI and emerging technologies reshape what's possible, we're also faced with new questions about the choices we make, the responsibilities we hold and the future we're creating. Through this partnership, five conversations are taking shape:
- Ethical and Responsible AI: How do we share responsibility for the decisions and impacts of AI as it becomes part of our everyday lives?
- AI and Sustainability: How can we harness the potential of AI and emerging technologies to support a more sustainable future?
- Keeping Humans in the Loop: How can human judgment, creativity, and expertise complement AI to shape better outcomes?
- Inclusion and Digital Equity: How do we design and deliver products and services that are accessible, inclusive, and equitable for everyone?
- From Creating to Evaluating: How do we embed standards and meaningfully evaluate AI outputs?
We are proud to support World Usability Day and the World Usability Initiative, and to contribute to a broader body of work that advances our understanding of how technology should be designed, developed and evaluated as AI transforms our industry.
To follow our latest updates, reports, and insights, subscribe to our blog.

What Our AI Interviewer Taught Us About Conversational AI
AI-moderated interviews are moving from experiment to everyday workflow. But for anyone who cares about user experience, the real question isn’t whether an AI can ask good questions. It’s whether the person on the other side wants to answer them. And that comes down to the design more than the model.
People are more comfortable talking to AI than you might expect. In an Adobe Express survey of 1,005 US consumers, 61% said they were comfortable having conversations with AI-powered systems. A COPC study across six countries found people who knew they were talking to AI reported 34% higher satisfaction than those who weren’t told.
But a quick chat with a bot isn’t a research interview. So we put it to the test. We ran a study using Optimal’s AI Interviewer with participants at different levels of AI and UX experience, including some who were skeptical going in (and rightfully so!). Because if an AI interview only works for people who already love AI, it doesn’t really work.
What participants told us
Most participants described the experience as seamless, smooth, natural and even fun, including several who had reservations going in. Three things stood out.
1. It felt like a conversation, not a script
Participants noticed that follow-ups were built on what they had just said. One put it simply:
“I really felt like I was talking to a real person.”
Another appreciated that the AI summarised their points before moving on, instead of asking the same question in different ways. That was a frustration they’d had with other AI interview tools.
2. Less pressure made it easier to open up
Several participants found the AI easier to talk to than a live interviewer. Without a person across the table, there was less pressure to perform.
“I have no problems speaking freely.”
On-screen text alongside the spoken conversation also mattered. One participant with auditory processing difficulties called it out as a genuinely useful accessibility feature.
Not everyone was fully won over. One participant felt a human would better grasp the emotion behind their answers, though they still rated the experience positively.
3. Choice built confidence
Participants could pick how the conversation flowed. One chose “submit response” mode, deciding when each answer was finished. After a good first experience, they said they’d be happy to try “free form” mode next, where the AI responds naturally once they stop speaking.
Want to hear it from participants directly?
Watch the highlight reels in our full study write-up →
What designers can take from this
The takeaway reaches well beyond research tools: whether an AI conversation works depends less on the model and more on the experience designed around it. If you’re designing any conversational AI, these are worth stealing.
- Prove you’re listening. Responses that reference the user’s own words build trust faster than clever phrasing. A short summary before moving on signals “I heard you.”
- Don’t make people repeat themselves. Rephrasing the same question feels robotic. Move the conversation forward instead.
- Lower the stakes. Removing social pressure can make people more candid. Clear instructions and a predictable flow help them settle in.
- Offer more than one channel. Pairing voice with on-screen text supports people who process information differently, and makes the experience easier for everyone.
- Give users control over pacing. Letting people choose when to submit, or when to go free form, turns uncertainty into confidence.
- Be honest about limits. Some people will still prefer a human for emotionally nuanced topics. Design AI as an option, not the only path.
See how Optimal’s AI Interviewer works
We built these lessons into Optimal’s AI Interviewer, an AI-moderated research tool designed to work with you, not instead of you. It helps teams run more interviews without losing the depth that makes qualitative research valuable.
- Add your context. Research goals, audience details and supporting material guide every follow-up.
- Build your discussion guide. Set sections, questions, goals and how deeply the AI should probe.
- Let it run the interview. The AI listens, adapts and explores relevant threads while staying on your goals.
- Get cited insights. An AI-generated summary and key themes, with citations at study, section and question level, plus highlight reels that jump to the moment behind each insight.
Take this two-minute interactive tour to see it for yourself.
The bottom line
AI interviews aren’t about replacing the human side of research. They give teams another way to listen, at a scale that used to need a lot more people and time. And when the experience is designed well, participants are happy to talk.
Optimal’s AI Interviewer is now in Early Access, book a demo to learn more.

When to use MCP vs. AI Chat
Optimal gives you two ways to use AI to ask questions about your research and explore your findings: AI Chat in Optimal Interviews and Optimal MCP.
Both let you ask questions in natural language, but they’re designed for different types of research exploration.
The simple difference: Use AI Chat to explore interview data in depth. Use MCP to explore individual studies, connect research from different studies, connect to other tools, automate existing or new workflows
AI Chat vs. MCP: Which should I use?
Use AI Chat when you want to:
- Explore a specific interview topic
- Find supporting evidence in interview sessions
- Find new video clips
- Generate new highlight reels
- Investigate participant reactions in more detail
- Follow evidence back to timestamped interview sessions
Use MCP when you want to:
- Search across multiple studies
- Compare findings across studies or time periods
- Identify recurring themes and trends
- Combine research from different methods
- Explore individual studies using participant results, study setup and metadata
- Analyse transcripts, task results, user paths and other available research data
- Connect Optimal research to ChatGPT, Claude, Gemini, Cursor or other MCP-compatible tools
- Bring research into broader AI-powered workflows and automate research tasks
In short
Go deeper into interviews → AI Chat
Use AI Chat when your question is focused on what participants said, how they reacted, or finding evidence within interview sessions.
Go broader across research → MCP
Use MCP when your question spans multiple studies, research methods, time periods or data sources, or when you want to bring Optimal research into another AI workflow.
What is AI Chat in Optimal?
AI Chat is an AI-powered research assistant built into Optimal Interviews. It helps you explore interview data using natural-language questions.
Use AI Chat to find what participants said, investigate specific topics, discover supporting evidence and explore interview findings in more depth.
For example, you can ask:
- “What frustrations did participants mention about checkout?”
- “Show me quotes about trust in the product.”
- “What did participants find confusing about onboarding?”
- “Find examples of participants struggling with the navigation.”
You can ask follow-up questions to refine your search or investigate a finding further. AI Chat can also surface participant quotes, video clips and highlight reels, with citations that take you back to the supporting evidence in your interviews. Learn more about AI Chat.
What is Optimal MCP?
Optimal MCP connects your Optimal research to MCP-compatible AI assistants and tools, including ChatGPT, Claude, Gemini and Cursor.
MCP is designed for broader research exploration. It lets you work with research data across individual studies or your wider Workspace, making it useful for research synthesis, cross-study analysis and AI-powered research workflows.
For example, you can ask:
- “What usability issues have appeared across our research this year?”
- “Compare our findings from March and June.”
- “What themes are recurring across our recent studies?”
- “Which studies included feedback about onboarding?”
- “Create a Notion page outline summarising these research findings.”
Depending on the data available to you, MCP can help you explore study information, participant results, supported survey results, transcripts, task results, user paths, study metadata and AI-generated insights. Learn more about Optimal MCP.
AI Chat vs. MCP example
Imagine you want to understand problems with onboarding.
Use AI Chat
Ask: “What did participants say was confusing about onboarding? Show me examples.”
Use MCP
Ask: “What onboarding issues have appeared across our research over the past six months?”
What research data can AI Chat and MCP access?
AI Chat focuses on your Interviews data, helping you explore interview responses and supporting evidence such as quotes and highlight reels.
MCP provides read-only access to research data available to you in Optimal, including study information, participant results, supported survey results, and AI insights.
Best practices for using AI Chat and MCP
Whichever tool you use, you’ll get more useful results by giving the AI enough context.
- Ask specific questions. Include the product, feature, audience, study or timeframe where relevant.
- Start broad, then dig deeper. Use follow-up questions to explore interesting findings.
- Ask for evidence. Request quotes, examples, citations or the studies supporting a finding.
- Specify the format. Ask for a summary, presentation-ready bullets, or another format that suits your needs. With MCP, you further specify formats, such as charts, tables, or interactive deliverables.
- Check important findings. Use AI to accelerate analysis, but review the underlying research before making important decisions.
Find out more in our AI Chat best practices.
Already using AI Chat or MCP? We’d love to hear how you’re using AI to explore your research. Share your use case, workflow or favorite way to work with AI with our team.
Not using Optimal yet? See how Optimal can help you bring AI into your research workflow.
Book a demo.
.webp)
Optimal MCP + Figma Agent: Turning User Research Into Better Designs
What if you could turn real user feedback into your next design iteration with a single prompt?
With Optimal MCP and Figma Agent, you can turn user research to design updates in minutes. Pull insights from your Optimal studies into Figma, then let its AI design agent update multiple frames and screens based on real participant feedback. As you gather more feedback, you can keep refining your designs, testing updated prototypes with real users and using what you learn to shape the next iteration.
Together, Optimal MCP and Figma Agent help close the loop between research and design, helping you turn real user feedback into better designs with every iteration.
How does the Optimal MCP & Figma Agent work?
Optimal MCP and Figma Agent help you connect the dots between research and design. Connect Optimal to Figma and draw on findings from one or multiple studies, including participant feedback, usability insights, transcripts and prototype task results. Figma’s AI design agent can use these insights to update existing designs or generate new ones based on your prompts.
Then, bring your updated prototypes back into Optimal to test them with real participants and see how your changes perform.
So what does this look like in practice? Imagine you've run a usability study and discovered that participants are struggling to find an important action in your product. Here’s how to put this research design loop into action.

From research insight to your next breakthrough
1. Turn user insights into new design possibilities
Reference Optimal MCP and one or more Optimal studies in Figma’s agent chat. Ask the agent to explore solutions to the usability issues your research revealed and generate design changes to address them.
Example prompt: "Connect to Optimal Workshop MCP, look at study "Mobile banking app", read the feedback and update the prototype based on the participants' feedback. Add these updated prototype screens to a new page in this file, side-by-side with the original artboard."
2. Explore further. Iterate faster.
Use AI to explore alternatives, challenge your first approach and move through design possibilities faster. Then bring your expertise to the process. Evaluate the trade-offs, review the prototype flows, refine the details and decide which ideas best serve your users.
As more participant feedback to your Optimal studies comes through, ask the agent to pull feedback from those new participants to bring those fresh insights into your Figma iterations.
3. Put your changes to the test
Here's where the loop gets even more exciting.
Put your newly updated prototype to the test with a new Optimal study. Have you made that important action easier to find? Does the new design solve the original problem? What could be even better?
You can test multiple prototypes or combine multiple methods in one study, whether you're working with a prototype, live website or web app, or AI prototype with Optimal’s Usability Testing tool or keep it focused on one prototype with Optimal’s Prototype Testing tool.
Every round of testing gives you more to work with. Every new insight creates another opportunity to improve.
Ready to bring user research into your next design iteration?
AI is changing how quickly we can move from an idea to a design. Make the most of your research by connecting Optimal to Figma’s AI Design Agent with Optimal MCP to build experiences and products people love.
Get started with the Optimal MCP setup guide or check out the interactive demo.
