An AI tool that turns scattered, conflicting design feedback — from Figma, Slack, docs and meetings — into one clear, evidence-backed plan, while the designer stays in control.
A hi-fi prototype that ingests 32 scattered comments from Figma, Slack, docs and meetings, and organizes them into five ranked themes with cited research. Click around, or scroll to the full-size version at the end.
See the full flow ↓An AI that organizes feedback only helps if people actually trust it. These four goals held that tension throughout.
Turn the busywork of collecting and reconciling feedback into the work of deciding.
Every claim should be visible and sourced — never a black box.
The AI proposes with evidence; the designer always makes the call.
One predictable model across tools and teammates — design-system thinking for AI output.
After a review, feedback lands everywhere at once — and the real work, deciding what to change, gets buried under the busywork of gathering it. Three frustrations show up every time.
One design review · 32 comments · 4 tools
4 tools, 32 comments, none talking to each other.
"Bigger" (Figma) clashes with "smaller" (Slack) — no flag until too late.
Volume beats the weight of evidence.
Maya leads two product areas and runs the weekly design review with PMs, engineers and a researcher. She wants to ship confident decisions fast — but loses her mornings reconciling feedback before she can act on any of it.
Mapping Maya's current flow showed exactly where a tool could help — her emotion bottoms out right at “make sense” and “decide.”
Three questions that opened up the design space.
Synthread connects your tools, does the synthesis, and leaves the decision to you.
Connect Figma, Slack, docs, meetings once.
Group comments by meaning, not keywords.
Flag contradictions and show both sides.
Highlight where people already agree.
Rank by impact, frequency, stakeholder weight.
Ground recommendations in real UX research.
All six visible in the live prototype below.
See it work ↓The AI proposes with evidence.
The human decides.
Because the AI gives direction, it has to prove it. Two mechanisms carry the whole trust story.
Theme 04 · CTA hierarchy
Reduce visual weight of primary CTA.
Trust. Every claim is traceable.
“The hierarchy feels off, we should rethink it.”
Graceful failure. When unsure, it asks.
A restrained, cool “tech” palette with one electric accent — and semantic colors that mean the same thing everywhere.
Connect sources, see feedback pinned on the design, watch chaos become ranked themes, resolve a conflict with cited research, and leave with a prioritized plan. Tap around — it's live.
It starts on the synthesis view — 32 scattered comments organized into five ranked themes — and lets you explore every part of the product from the sidebar.