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.
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.
☎️@tellidotcom 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
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 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 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.
Building a production voice agent from a single prompt. In seconds ☎️
That's Charlie, the new telli agent builder.
The hard part of voice agents was never v1 but making them good enough to go live and deliver real outcomes. That used to mean reviewing 1000s of calls by hand.
Charlie puts all of it on autopilot:
→ builds agents from prompts, flowcharts, scripts, even voice notes
→ analyzes your calls, shows exactly what's breaking and self-improves instantly
→ drafts every change - test with a real call, diff line by line, 1-click rollback
Your agent gets better every single day. Kinda insane to watch 👇
Sky chooses telli for proactive AI voice agents
Sky Deutschland GmbH (part of Comcast Group), Europe's leading media and entertainment company handles hundreds of thousands of customer calls every year.
Today they use telli to proactively engage with customers at scale.
@tellidotcom at CCW ☎️
We had a fantastic time at this year's @ccw_berlin in Berlin, where customer experience leaders from top companies joined us to explore the future of voice AI.
Thank you for everyone who joined and thanks for the great conversations!
Our biggest launch yet - the telli prompt editor ☎️
Performant agents in minutes instead of hours.
Over the last few months, we’ve helped our customers set up thousands of voice agents and we realized: successfully prompting a voice agent is a huge pain.
Getting an agent to work is the first challenge. But after the initial version is set up, you want to change the script, test different flows, and make it perform better. This is frustrating and time-consuming.
So we took everything we’ve learned from our customers and turned it into our newest feature: the telli Prompt Editor.
The fastest, most powerful way to set up, experiment with and improve a voice agent just by having a chat.
telli customers are already loving it. Try it and sign up for a demo in the comments! 🔗
Big thanks to Philipp, Błażej, and Paulus for making this happen!
🚀 @tellidotcom launched! ☎️ outbound call automation for B2C companies
"Call Operations Simplified."
🌐 https://t.co/kUK7lHShKQ
telli is building the AI call automation platform for B2C companies. telli lets businesses:
📞 reach leads with a smart calling strategy and multi-modal approach (SMS)
🗣️ make human-like calls in multiple languages
✅ achieve clear outcomes like qualification, booking appointments, or direct transfers
🔍 understand what’s going on in calls at scale
Congrats @finnzurm, @sebselassie & @philippppb!!
https://t.co/QhOPkz2kkG