telli

A world where every interaction is worth having.

[telli @tellicom]

We just raised $15M to build AI for customer-facing operations.

And today, we’re launching Charlie: the first AI coworker for customer-facing teams.

Charlie is the best way to build and improve Voice AI agents.

It can analyze conversations, create workflows, connect to your tool stack, generate performance reports, and even help your team improve business outcomes over time.

The round was led by @redalpine, with participation from @CherryVentures, @ycombinator, strategic investors, and angels.

[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 4/5 of telli Launch Week

Introducing improved Workflows: automate what happens before and after calls, all within telli.

And with the new Code Node, enterprise integrations are faster and more flexible.

So agents have the context they need, and customers get the follow-up they deserve.

[telli @tellicom]

🚀 Day 3/5 of telli Launch Week

Introducing Analytics: track your agents' performance and identify areas for improvement.

Start with a template, build your own dashboard, or ask Charlie to create one for you.

Then share your insights across the company with interactive reports.

[telli @tellicom]

🚀 Day 2/5 of telli Launch Week

Introducing Web Calls: test your voice agent directly in telli, without picking up the phone.

Talk to your agent and follow the transcript as it happens.

And when real customers call, you can listen in and follow those conversations live, too.

[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...

[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.

[jannis metrikat @jmetrikat]

sunday afternoon, driving back home, quickly checking slack - 13 min from bug reported to fix deployed. only at @tellicom

[seb selassie @sebselassie]

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

[telli @tellicom]

@thenickpattison 🤝

[telli @tellicom]

I love my new logo 😌

[Nick Pattison @thenickpattison]

Love this logo we did for Telli, a platform that handles agentic phone calls.

The whole identity is about human + agent collaboration, with two sides coming together

[telli @tellicom]

RT @sebselassie: small easter egg on new website - https://t.co/H2dsqyIpFh

[telli @tellicom]

If you want to experience it for yourself try it out at https://t.co/TXphnUMVmG

[telli @tellicom]

We just raised $15M to build AI for customer-facing operations.

And today, we’re launching Charlie: the first AI coworker for customer-facing teams.

Charlie is the best way to build and improve Voice AI agents.

It can analyze conversations, create workflows, connect to your tool stack, generate performance reports, and even help your team improve business outcomes over time.

The round was led by @redalpine, with participation from @CherryVentures, @ycombinator, strategic investors, and angels.

[telli @tellicom]

Read the full story here → https://t.co/z73fAPzFOj

[ai-coustics @ai_coustics]

☎️@tellicom built their voice agent stack on @livekit - and integrated ai-coustics to make sure audio never became the bottleneck at enterprise scale.

The result: agents that handle real-world calls reliably, at volume. 🎯

Read the full case study → https://t.co/qXMm9DG0V5

[telli @tellicom]

The exact playbook from the video - Jannis demos it with a car dealership, but it maps to any business with a lead form:

1️⃣ Connect telli to your form
Use a webhook or a native CRM integration (Salesforce, HubSpot). Set the workflow's start trigger to "contact created" - every new form submission now enters the pipeline automatically.

2️⃣ Let telli do the filtering
Add an If/else node and run pre-qualification on whatever criteria your form already captures. In the dealership demo, three boolean conditions:
→ willing to pick up the car = true
→ located in Germany = true
→ driver's license = true

3️⃣ Branch the response
If false → send a polite SMS or email: "unfortunately we can't offer our service in France." No agent time wasted.
If true → send an SMS telling them they fit the bill and an agent will call for the last pieces of information. Why call instead of pushing a signature immediately? For a purchase like a car, a lot more info is needed - and it's far easier to gather by phone. You're warming the lead, not rushing it.

4️⃣ Schedule the call
Next node: scheduled call. If the lead replied to the SMS with a preferred time, the call scheduler automatically uses it. If not → the agent calls 2 minutes later, while the form is still fresh in their mind.

5️⃣ The telli agent takes over
It follows its script for the remaining questions and books the appointment - natively integrated with Cal. com, Calendly, the HubSpot calendar, or any custom calendar via an HTTP request in the agent prompt. Everything the agent learns is captured through telli custom call outcomes - you can extract any type of information from the call.

6️⃣ Generate the quote
The moment the call completes, an HTTP request block bundles the extracted call outcomes and sends them to the Claude API, which generates a custom quote on a custom landing page.

7️⃣ Close
As soon as it's ready, the agent texts the customer the link. They click, review their quote - every detail pulled from their own call - and accept.

That's form to signed quote in under 10 minutes.

Try the playbook yourself → https://t.co/3surXAdJ1G

[telli @tellicom]

telli now natively supports SMS in workflows and mid-call → meaning you can go straight from online form to signed quote in under 10 minutes. ☎️→💬

Watch our engineer Jannis walk you through the exact playbook customers are using.

Voice starts the conversation. But the payment link, the calendar invite, the quote? All handled inside telli - including HTTP request blocks calling the Claude API to generate the quote itself.

Now it's native:
→ Send SMS block in any workflow - template + sender number, done
→ mid-call texting - the link arrives while the caller is still on the line
→ inbound replies attach to the same conversation, next to the voice context

See comments for the exact playbook to copy 👇

[telli @tellicom]

Curious how it works? Try it here -> https://t.co/fxdGfXR3tm

[telli @tellicom]

telli now runs your post-call automation natively - no Zapier, n8n, or Make required. ☎️

Because the call is only half the work: the CRM update, the outcome routing, the follow-up. Until now that logic lived in external node chains that fail silently and page no one. One broken node = one lost lead.

With Workflows, you build it inside telli:
→ pick a trigger, drop in action blocks - webhooks, CRM create/update, contact writes
→ branch with if/else + switch on call outcomes, collected data, any contact property
→ runs automatically on every completed call

Versioned like a deploy: draft → publish → rollback in two clicks.

Keep n8n for the weird stuff. The standard path is built in.