Nicheloom

Market intelligence for builders — see what's gaining traction before it's crowded.

Figr

AI that thinks through product problems before designing

Details

External ID
46724567
Source
HN
Company
—
Product
Figr
Website domain
figr.design
Launched
Jan. 22, 2026
Cohort
—
Upvotes
10
Upvotes percentile
0.5006587615283268
Tags
—
Fetched at
Sept. 7, 2026, 9:25 p.m.
Updated at
Sept. 7, 2026, 9:25 p.m.

Description

Built Figr AI because I got tired of AI builder tools market themselves as design tools and end up skipping the hard part.Every tool I tried would jump straight to screens. But that's not how product design actually works. You don't just design screens. You think through the problem first. The flows, the edge cases, the user journey, where people will get stuck. Then the design comes finally.Figr does that thinking layer first. It parses your existing product via a chrome extension or takes in screen-records, then works through the problem with you before designing. Surfaces edge cases, maps flows, generates specs, reviews UX. The design comes after the thinking.It is able to do so because we trained it on over 200k+ real UX patterns and UX principles. Our major focus is on helping in building the right UX by understanding the product.The difference from Lovable/Bolt/V0: I think those are interface builders. They are good when you know exactly what you want to build but they don't truly help in finding the right solution to the problem. Our aim with Figr is to be more like an AI PM that happens to also design.Some difficult UX problems we've worked through with it: https://figr.design/galleryWould love feedback, especially from folks who've hit the same wall with other AI builder/design tools.

Enrichment

Theme
3D modeling and visual design tools
Vertical
—
Function
Agent / copilot
Audience
B2B
AI stance
AI-native
Project type
Commercial product
Normalized one-liner
ai design assistant for product thinking
Manually corrected
False

Could you build this?

No Building an AI design agent that analyzes complex multi-step user flows, scrapes existing applications, integrates bidirectional Figma APIs, and enforces design system tokens is a massive frontier AI product.

What it would actually take: A real version requires headless browser infrastructure (Playwright/Puppeteer cluster) to crawl apps, complex multi-modal LLM reasoning graphs (LangGraph or custom state engines) to model UX flows, and deep integration with Figma's Plugin and REST APIs to dynamically generate native vector components and styles. It demands senior UX engineering expertise alongside sophisticated prompt engineering and evaluation pipelines.

Discussion

5 comments analyzed.

Concerns raised: Credit-based pricing is unclear - users don't know how many questions or workflows a credit amount enables, Pattern bias from 200k UX corpus could override product-specific needs and constraints, Data integration complexity and maintenance burden for enterprise customers, Difficulty translating between AI suggestions and actionable product decisions

Feature requests: Show decision logs with reasoning - what was considered, rejected, and why, Surface AI suggestions tied to product's own data (analytics, funnels, support tickets) with tunable opinionation level, Guide users through discovery questions before jumping to solutions, Real-time collaboration capability for discovery and customer success meetings, Support for non-UI design contexts like hardware and other domains

Competitors

Other products that read as similar to this one — 109 launches clear the similarity bar, closest 8 shown.

Attention rank: #59 of 110 (itself plus its competitors, highest first — normalized so YC and Product Hunt are compared fairly).

Launched 84 days after the earliest competitor.

Other launches for this product