$FIG just launched the Figma Design Agent, a dedicated agent that works alongside users in Figma.
The agent lives directly on the canvas, so you can prompt from any design layer, iterate and edit alongside the agent, and hand it boring tasks that would have otherwise taken up a lot of your time.
$FIG CEO @zoink came on the show today to discuss the launch. Here's our full conversation.
01:18 โ Clocking AI-generated designs
03:31 โ Figmaโs new Design Agent
05:40 โ AI code bloat and slop
09:09 โ Using AI to augment creativity and branding
15:08 โ Why Figma should be the front door to building apps in the AI era
18:53 โ How design becomes more important as code commoditizes
๐จ๐ช๐ธ GOAL | Barcelona 1-0 Real Madrid | Pedri
WHAT A FANTASTIC GOAL FROM PEDRI !!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!
https://t.co/oKoXpKpEbB
@InterviewsChat For sure! Cool stuff youโre building, I built https://t.co/8tYeIdF3Tt a few months ago. Might take another stab with this new functionality
This is awesome โ feels like a big unlock for more dynamic turn-based conversational experiences (e.g. coding interview agents). Will definitely be playing around with this model!
Today weโre launching our first homegrown AI model: an open source turn detection model for building voice agents.
Instead of relying solely on voice activity detection (VAD), which only considers when a user is speaking, our model also considers what has and is being said in the context of a conversation and predicts when a user is finished expressing their thoughts before the agent responds.
Conversations with AI voice agents using this new model flow much more naturally without constant interruptions from the AIโ check it out (more videos, details, and code in the thread):
Can't be a full-stack engineer without a personal website: https://t.co/gG7RYZ25tf ๐ซก
Any recommendations for cool features / website elements? Could be anything from slick animations, fun projects, dark mode (implemented yesterday), etc.
@_alexshaq Cool demo! Love the use of voice as well.
As a FE developer though, adding download buttons/modals is somewhat trivial. I'd love to see a demo of how to scaffold larger features with Cursor projects; I've seen other examples with more flushed-out prompts.
Who are we?
Weโre @therealak914, @the_chet2an, and @aachang97 - a team of YC / Stanford alum who sold our last company to Coinbase. Weโre gearing up for Act II and canโt wait to push the frontier of voice intelligence ๐
Why are we excited about voice AI?
As @deepgramscott said in our YC community, โsomething hugeโ is happening in the world of audio. This past year has seen an incredible shift in voice infrastructure, and weโre betting that there will be intelligent voice interactions everywhere. If you havenโt used @elevenlabs , @play_ht , or any of the recent TTS / STT tools in the last 6 months, go check them out - special things are on the horizon ๐ฏ
Whatโs next?
Weโre cooking up some pretty cool products - stay tuned and follow for updates! Weโll tweet out observations from using the latest tech along the way ๐