

✓AI agents for concierge customer experiences


The bar for good product is competitive and continuously getting higher. It's a privilege to build and have a front seat to frontier application layer AI product Sharing my observations about what wins, and what the industry is demanding of its vendors

For the first time, you can try our voice agent right on our website. Give it a call and hear the difference for yourself: decagon.ai/product/voice#dem…

So excited to announce Alto, our newest voice model. Alto is fast, natural and smart. It responds in under 700ms and can guide users through the most complex workflows. Customers can no longer distinguish Alto from human agents. Shoutout to the team at Decagon Labs.

Give it a call and hear the difference: decagon.ai/product/voice#dem…

Introducing Alto, our new voice model from Decagon Labs. Alto powers our duplex architecture which lets agents listen, speak, and act at once. It delivers a 5+ percentage point lift in resolution with ~700ms responses on live calls.

I'm excited to share that I'll be speaking at #SGLangSummit this week! I'll be sharing our work on speculative decoding at @DecagonAI, including when to choose EAGLE vs. DFlash, the latency-throughput tradeoffs, and where we're headed next. See you there!

Devin can do more than ship PRs. @DecagonAI used it to run an inference research lab. One Devin orchestrates, subagents chase competing hypotheses in parallel, and every idea is tested against replayed production traffic on @modal GPUs. The result was up to 2.5× more throughput per GPU.



I'm hosting a voice/audio research night with @DecagonAI and @Accel on Nov 9. @nishnik from Meta Superintelligence Labs, @chongz from Cartesia, and I are each giving a quick talk then it’s just hanging out with other speech people if you work on voice in SF come through! luma.com/j3ddfdsw


Next up on First Pass: A conversation with @EveraertDante, a voice AI researcher at @DecagonAI on Duplex Models LLMs are turn based. Duplex Models are constantly "listening" streaming audio in and out simultaneously.

Had a blast talking with @jaminball and @palak_go on First Pass about why transcription shouldn’t be on the critical path for voice agents, and what it actually takes to go audio-native. Thanks for having me!

marketing team advised that I shitpost less and try to provide some real value to the world, so here's what I've been working on recently!

Read more here: decagon.ai/blog/experiment-h…