- Platform
- Web App
- Duration
- 12 weeks
- Industry
- Marketing Tech
- Read time
- 5 min read
RaftLabs built Perceptional, a conversational AI interview platform for product managers, that delivers 4x deeper insights than static surveys by running AI-led user interviews that adapt questions in real time based on participant responses. The system uses Anthropic Claude via AWS Bedrock for context-aware conversation management, generates structured insight summaries within 48 hours of interview completion, and runs on AWS Lambda to handle thousands of simultaneous interviews without infrastructure management. Built in 12 weeks for Canadian founder Amer Abu Khajil, who previously worked at Amazon.
Amer Abu Khajil spent years at Amazon, one of the most customer-obsessed companies in the world, and still couldn't get real feedback from his own users. Not because the tools didn't exist. Because every tool gave him the same shallow answers.
A static survey asks the same questions in the same order to every respondent. If someone says they find a feature confusing, the survey moves on. There is no follow-up. No "what specifically was confusing?" No "how did you try to work around it?" Product managers end up with data that confirms what they already suspected but never surfaces what they actually needed to know.
Amer came to us with a prototype idea. We built Perceptional: an AI platform that interviews users the way a researcher would. It adapts its questions in real time based on what each user says, maintains full context across the entire conversation, and generates a structured summary within 48 hours of the interview completing.
We delivered the platform in 12 weeks. It produces 4x deeper insights than traditional static surveys.
before & after
What changed
- Static surveys asked every user the same questions regardless of what they said
- No follow-up questions when a user gave a signal worth exploring
- Analysis took days of reading unstructured responses across spreadsheets
- Survey tools could not handle real load at scale without breaking
- Product managers were making decisions on surface-level data they knew was incomplete
- AI conversations adapt in real time to each user's specific responses
- Relevant follow-up questions surface automatically when the AI detects an important signal
- Structured summaries generated within 48 hours of interview completion, with no manual analysis
- Serverless infrastructure handles thousands of simultaneous interviews without any ops overhead
- Product managers get insight depth that previously required live researcher interviews
What we had to solve
- 01
Keeping a multi-turn conversation coherent from first question to last
A real interview has a thread. The researcher remembers what was said in question two when they ask question eight. Standard AI implementations lose this context as conversations grow longer, treating each exchange as near-isolated rather than as part of a continuous session. We needed Perceptional to hold the entire conversation in working memory, reference earlier answers when deciding what to ask next, and never repeat a question the user already answered. Claude's extended context window made this possible. Smaller models would have broken interview coherence mid-session.
- 02
Turning unstructured conversations into structured summaries a PM can act on
A conversation with 15 exchanges produces a lot of text. Product managers need the signal, not the transcript. We had to design a summarisation layer that could read the full conversation, identify the themes and patterns that appeared across responses, and format them into a structured summary a PM could use in a sprint planning meeting. The summary had to be accurate enough to reference specific user language but concise enough to read in five minutes. Getting this right required iteration on the prompt engineering and the output format with Amer's team until the summaries were genuinely useful.
outcomes
What we achieved
The founder had a clear vision but no working product. Just static survey tools that couldn't adapt to what users were actually saying.
Static surveys returned surface-level answers. Product managers spent days reading unstructured feedback trying to find the signal, and still made decisions on incomplete data.
Manual analysis of a single survey round took days. By which time the team had already moved on to the next sprint and the insight had lost its relevance.
What clients say
Most clients stay.
Some say so on camera.
Three-year average engagement. Founders and operators describing the work in their own words. No marketing varnish.
CanadaI found RaftLabs to be the perfect partner for Perceptional, with their expertise in helping startup founders build MVPs, a free consultation, a prototype that matched my vision, and their unwavering support.
Building a product without clear signals from your users?
the build
What we built
Before writing a line of code, we built a working prototype in under a week so Amer could see the conversation flow in action. Everything after that was two-week Agile sprints, daily Slack updates, and Asana for task tracking.
Every interview follows the user's actual answers, not a fixed script
The AI reads each response and decides what to ask next based on what the user actually said, not a fixed script. If a user mentions confusion with a specific feature, the platform follows up on that confusion. If they express enthusiasm, it probes what drove it. Each interview takes a different path because each user's answers are different.
Product managers answer stakeholder questions before the next sprint, no transcript reading required
After each interview session closes, the platform analyses the full conversation thread and generates a structured summary with themes, specific user language, and concrete findings. No manual reading of transcripts. The summary is ready before the next working day.
5,000-user campaign launches without an infrastructure team watching it
Built on AWS Lambda, Perceptional runs thousands of simultaneous interviews without infrastructure management. A product manager can launch a campaign to 5,000 users and the platform handles the load automatically. The beta and enterprise workloads run on the same architecture.
Themes that appear in 40% of interviews surface differently than ones that appeared once
The platform analyses entire conversation threads for context, not just individual answers, and surfaces patterns that repeat across multiple users. A theme that appears in 40% of interviews is surfaced differently than one that appeared once. Product managers see where the signal is strong and where it is noise.
Engagement
How we worked together
- 01Weeks 1–2
Discovery and scoping
We map the problem before writing code. Two weeks of technical audit, stakeholder interviews, and prototype — so both teams align on scope and risk before sprint one.
- 02Ongoing
Two-week Agile sprints
Each sprint ends with working software, not a status update. You review a real build, request changes, and approve before we move forward. No surprises at handover.
- 03Ongoing
Daily async updates
Slack for daily progress, Asana for task visibility, weekly video calls for decisions. You have full visibility without needing to attend every meeting.
- 04Final
Handover and warranty
Full code handover with deployment runbooks and documentation. Thirty-day warranty period for production issues at no extra cost.
stack
Why we chose this stack
- 01Amer was building alone. Lambda means Perceptional handles 10,000 simultaneous interviews without an infrastructure team. No servers to provision, no idle capacity to pay for between interview campaigns.AWS Lambda
- 02Claude's extended context window keeps the full conversation in memory. The AI remembers what was said in the first exchange when asking the tenth question, which is what makes follow-ups feel like a real interview rather than a disconnected form.Claude (Anthropic)
- 03Bedrock gives a single control plane for model management and versioning. When Anthropic ships a better model, we update Perceptional without touching application code. The platform stays current without a re-architecture.AWS Bedrock
Still curious?
Survey tools are built for scale, not depth. They ask the same question to every user regardless of what the previous answer was. A custom AI interview platform adapts in real time, so you get the follow-up questions a researcher would ask, not a form that ignores what was just said. The difference shows in what you learn, not just how you collected it.
We delivered a working prototype within the first week so the founder could validate the conversation flow before any production code was written. The full platform (conversation engine, summary generation, admin dashboard, and infrastructure) was live in 12 weeks.
Yes. The platform runs on AWS Lambda, which scales automatically to match demand. There are no servers to provision. A campaign to 1,000 users and a campaign to 50,000 users use the same infrastructure. The platform expands to meet the load and contracts when it is done.
Product managers configure interview goals through the web interface, generate a shareable link, and distribute it to users via whatever channel they use today: email, in-app prompt, or Slack message. No dev work is required to run a campaign. Structured summaries appear in the dashboard when interviews complete.
Start with the research problem you are trying to solve: what decisions are you making, and what information would change those decisions? We can design and build an AI research platform around your specific users, workflows, and output format. Contact us for a free diagnostic call.
Related work
More work like this
AI phone agents automate global feedback loops through voice interviews
We transformed a text-based AI interview platform into a voice-first system that conducts automated phone interviews globally, eliminating user friction and delivering richer insights through natural conversations.
Read case study
An AI OCR loyalty platform drove 1,000+ sign-ups for a major supermarket chain
We built an AI loyalty platform for Musgrave's SuperValu and Centra that automates receipt validation with 99.9% accuracy, acquiring 1,062 users in 4 weeks.
Read case study
LoyaltyPass delivers wallet-native loyalty cards with 60% higher enrollment than app-based programs
LoyaltyPass runs loyalty programs inside Apple Wallet and Google Wallet. Customers earn and redeem without a separate app download, and businesses get real engagement data without the friction of a native app.
Read case study