Oliver Iida

engineering @ telli (YC F24)

[Oliver Iida @oliveriida]

@ArtemKislukhin @proactivepath @Daniel_Almi {} —> {{}}

[telli @tellicom]

🚀 Day 5/5 of telli Launch Week

Introducing Browser Use: your voice agents can now use software like humans.

Show telli how to complete a task, and your agent can navigate pages, fill out forms, and get things done, even without a direct integration.

[telli @tellicom]

🚀 Day 1/5 of telli Launch Week

Introducing Simulations: automated testing for voice agents.

Hours of test calls, replaced by one prompt.

Tell Charlie what your agent must get right.

It creates the tests, runs them in parallel, and helps fix what fails.

[seb selassie @sebselassie]

our voice agents can use the browser now...

[Oliver Iida @oliveriida]

@proactivepath @nullfellows {}

[Oliver Iida @oliveriida]

if a product doesn’t have dark mode, i’m not using it

[Oliver Iida @oliveriida]

Working with 6 Sol feels like playing whack-a-mole.

[telli @tellicom]

Today we are launching telli Duo agents.

Over the past years, the industry standard for voice AI has been the cascading architecture.

Meaning when a human speaks to an agent, the voice gets transcribed by an STT (speech-to-text) model, goes into an LLM, and is transcribed back with a TTS (text-to-speech) model.

This worked well and kicked off the era of Voice agents. But it came with fundamental flaws: It's impossible for an agent to listen and speak at the same time.

A good conversation has a rhythm. We pause, interrupt, and respond before the other person has finished their sentence. It happens so naturally that we rarely think about it. Building this into an agent was impossible.

A couple of months ago we got early access to @OpenAI's GPT-live model. It made us rethink our entire Voice AI infrastructure and rework it to bet on full-duplex speech-to-speech models. The result was the new telli Duo agent.

We went deeper into how we did that in our blog post: https://t.co/hASQc0TV6b

PS: We know we over-exaggerate the difference in the video. The comparison is more with a traditional IVR bot. But it's still much better now, just harder to show in a demo than when you experience it yourself. Just give yourself a call on https://t.co/KsqwnodO7Y.

[seb selassie @sebselassie]

This ad cost $14 and took 8 minutes to make.

[Y Combinator @ycombinator]

Congrats to @tellicom on their $15M seed!

They're building AI agents for B2C customer operations, handling the calls, lead qualification, appointment booking, and follow-ups that companies currently run through a maze of CRMs, call centers, and manual work.

Their agents already handle millions of conversations for customers including Sky, Enpal, and Vaillant.

https://t.co/5BVzdDCWS9

[Oliver Iida @oliveriida]

@jmetrikat Letss goooooo!!!🚀