[HN Gopher] Show HN: Figr - AI that thinks through product probl...
___________________________________________________________________
Show HN: Figr - AI that thinks through product problems before
designing
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/gallery Would love
feedback, especially from folks who've hit the same wall with other
AI builder/design tools.
Author : Mokshgarg003
Score : 4 points
Date : 2026-01-22 20:12 UTC (2 hours ago)
(HTM) web link (figr.design)
(TXT) w3m dump (figr.design)
| pedalpete wrote:
| I like the way you've framed the problem, and it's actually an
| issue I bring up with designers that I work with, not that they
| go directly to screens, but that they go from problem to ideation
| too quickly.
|
| We work in hardware, so we don't have UI to work with. UX isn't
| just UI, which I'm sure you know. I'd like to see something like
| your product to help guide people through the right questions,
| rather than finding the solution.
|
| One of the challenges I have with many AI subscriptions is that
| when you price in credits, I have no idea how many questions, or
| what kind of workflow that gives me. 10 credits. That could be 3
| questions.
|
| This was actually the business model issue we had with our last
| business, where we had to pay for map tiles, and we loaded
| thousands of them. For our B2B customers, we came up with a
| pricing model which said "per 1000 scenes" and they knew what a
| scene was. We still had no idea how big their scene was going to
| be, but we priced so that they could understand what they'd get,
| and they could verify, yes we opened 40,000 scenes.
|
| For our B2C customers, we had a simple monthly subscription
| because they would only likely use so much. We barely made any
| money on the consumers, but it helped offset the costs.
|
| This isn't just a you problem. But it is what prevents me from
| using a lot of, what may be, very good tools.
| midlander wrote:
| I like that you're positioning this as an "AI PM that happens to
| design" instead of yet another screen generator. Most tools are
| great at producing artifacts and terrible at preserving the
| reasoning behind them. If Figr could reliably spit out a tight
| decision log/constraints list from each session (what we
| considered, what we rejected, and why), that alone would replace
| a lot of hand-wavy product docs.
|
| The 200k UX pattern corpus sounds powerful, but that's also the
| scary part: pattern bias overpowering the specifics of a product.
| The more you can show "this suggestion came from your own data"
| (analytics, funnels, support tickets) and let teams tune how
| opinionated the pattern-matching is, the easier it is to trust it
| for things like onboarding and billing flows rather than just
| happy-path demos.
___________________________________________________________________
(page generated 2026-01-22 23:01 UTC)