AI can generate insights in seconds.
The harder problem is knowing whether they’re worth acting on.
In product discussions, teams rarely questioned what the AI concluded. They questioned how it got there. Without evidence, even accurate insights were hard to defend, and important decisions still meant reopening interviews and documents by hand. The challenge was never generating better summaries. It was designing an interface that made AI reasoning inspectable.
TraceFox is a product-discovery platform. I joined as the UX/UI designer, shaping its interface, flows and interaction logic. This is the investigation behind it — the questions, the rejected directions, and the decisions that stuck.
“I got as far as the part where you set up the workspace and I just closed the tab, it wanted a bunch of decisions I wasn’t ready to make yet. I never went back.”
Finding information stopped being the bottleneck.
Product teams have more research than ever — interviews, support conversations, analytics, product feedback, internal docs. The bottleneck moved. It’s no longer finding the information. It’s turning it into decisions everyone trusts.
Existing tools failed for opposite reasons.
Polished summaries, but little confidence. Impressive to read — impossible to defend in a review.
Evidence preserved, but only through constant manual upkeep — so the knowledge quietly dies.
The opportunity was to combine both: answers andthe context behind them — because an insight that can’t be defended in a roadmap review rarely changes the roadmap.
The model wasn't the problem. The interaction model was.
My first instinct was to improve the AI’s outputs. But after mapping how teams actually worked, something became clear: users couldn’t inspect how conclusions were formed. Without that visibility, every AI-generated insight was just another opinion. Trust wasn’t going to come from a higher score — it would come from showing the work.
One pattern the whole product repeats.
Four principles set the rules the whole product had to obey — and one interaction enforces them everywhere. Instead of turning AI output straight into documentation, every claim passes through human review. The same four steps happen everywhere, so the mental model never changes.
Users can always trace an insight back to its original source.
Generated knowledge stays a draft until someone reviews the evidence.
Confidence is shown, not hidden. Conflicting evidence is surfaced, not ignored.
The repository grows as teams do their everyday work — no extra upkeep.
AI proposes, a person reviews the evidence and approves, and only then does the shared repository update — the system never quietly decides on its own.
Every insight is connected to its origin.
A claim is assembled in four layers, each grounded in the one below. Selecting any claim reveals the participant quote, interview metadata, supporting observations, confidence, and related evidence. Step it up one layer at a time.
A real sentence from a real interview. Nothing is inferred yet — this is the ground truth every layer above must point back to.
“I got as far as the workspace setup and I just closed the tab, too many decisions I wasn’t ready to make. I never went back.”
Rather than asking users to trust the AI, the interface lets them judge it — any reader can open a claim and land on the exact sentence a real person said.
Research rarely produces one clear answer.
Participants disagree and evidence changes. Instead of hiding these inconsistencies, the product treats them as signals: when new evidence conflicts with a claim, confidence drops automatically and the contradictory sources are surfaced for review.
Onboarding drop-off is concentrated at workspace setup.
The claim remains, but its score falls and the conflicting source is named — nothing gets quietly overwritten.
AI positioned as a reasoning partner, not an answer engine.
The clearest signal came from how discussions changed. Conversations stopped stalling on where an AI answer came from and moved to whether the evidence behind it was strong enough.
- A claim is defended by opening its source, not re-reading the transcript.
- Contradictions surface on their own instead of being missed.
- The repository builds itself instead of needing upkeep.
- Shared briefs stay checkable — every reader can trace the reasoning.
AI products don’t become trustworthy by making fewer mistakes. They become trustworthy when people can see where a conclusion came from.
The biggest lesson wasn't about AI. It was about information architecture.
I used to think trust was mostly a function of model quality. Users rarely know how accurate a model actually is — they judge whether they can independently verify its conclusions. So designing that verification layer mattered more than designing the summaries themselves. Explainability wasn’t a machine-learning problem; it was an information-architecture one.
TraceFox is in active development, heading toward launch from Munich in 2026. This case describes the product as designed and the thinking behind it, rather than adoption to date.