More on what we’re doing with Instinct and Muse around the personal agent work we announced last week!
Today, we're open-sourcing the Personal Agent Consent & Trust Protocol (PACT), co-developed by @Instinct. We're also joining the Personal Agent Protocol working group by @Muse.
Built on A2A and OAuth, PACT enables businesses to verify who a personal agent is acting for and what the customer has authorized it to do.
Excited to shape the industry standard for how personal agents will interact with businesses.
Show more
Our first voice model!! Built specifically for realism in real-world calls.
Turns out that when you’re talking about calls between a consumer and a business, making sure that Agents sounds like humans (with all the imperfections that come with that) makes a huge difference
Show more
Voice 3 is here.
Our most advanced voice experience yet combines Chord, our new voice model from Decagon Labs, with a duplex architecture that lets agents process incoming audio even while speaking.
Chord is post trained specifically for customer conversations, giving agents more natural pacing and intonation, while the duplex architecture enables smoother interruptions and less dead time as the agent keeps working.
Also launched today at Decagon Dialogues:
- Personal Agent Gateway: a dedicated communication layer for handling interactions with personal AI agents.
- Agent Modules: a foundation for expanding agents into new customer journeys.
- Duet Apprentice: a learning layer grounded in your company’s knowledge and the teammates who know the business best.
Show more
We are accelerating toward a world where consumer agents interact deeply with business agents whenever you need/want something.
Great write-up by @cyrusasg on our research team!
a coding agent delegating work and a consumer agent negotiating a refund are both “multiagent systems.” but only one lets you design both sides of the interaction.
wrote about what changes, from context and verification to incentives and training.
Show more
Had a nice discussion on @tbpn last week!
The hard problem with deploying in enterprises is bridging the gap between what models can do and learning all the bespoke processes/procedures in the business.
Show more
I'm building a new team at @DecagonAI: Engineering Lead, Strategic Deals 🚀
After founding & selling my last company, I was worried about how I'd replicate the same autonomy and agency in a job that I felt running a company of my own.
That line of thinking shaped the team I'm building now, and I'm positive it's what every former technical founder is looking for. It has astonishing breadth (you sit across infrastructure, model research, agent development, security, etc.) and even more astonishing autonomy: you make decisions that affect millions of dollars of revenue every single day.
If you're a former technical founder, or any engineer looking for a high agency gig, take a look at the blog post below!
Show more
I’m biased ofc but agree with many of the points here..
Historically lots of people viewed customer service as a cost center to limit as much as possible.
Now it can be a competitive differentiator.
Show more
In a world where it’s easier than ever to start and scale a new business, customer service may end up being the ultimate differentiator.
We're hosting our annual conference, Decagon Dialogues, in SF on 10/1!
@ScottWu46 from Cognition is joining us for a keynote.
We'll have folks from American Airlines, Verizon, Paypal, Chipotle, etc discussing how they're deploying agents at scale.
Come by:
Show more
BCV has been awesome to work with. Congrats to the team!
Make money. Have fun. Live with integrity. Everything else can change.
Fund XI. $1.6B total capital for those who know that it will.
The way engineering works is changing so quickly that you have to be very adaptable
In July, 80% of our team's AI coding happened in Claude. By August, 80% was happening in Cursor or Codex.
One of the most valuable traits for engineering teams right now is a willingness to abandon a workflow they relied on just weeks ago.
Show more
Qasar Younis, CEO of @AppliedInt, has been a mentor and friend to @AshwinSreenivas since the earliest days of Decagon.
He came to our SF office to share what he’s learned across two startups, Google, YC, and 8+ years building Applied Intuition.
Thanks for joining us, @qasar!
Show more
Oh no they found our secret headquarters...
HUBBLE DISCOVERED THAT SATURN HAS A DECAGON AT ITS SOUTH POLE!!!
SO NOW IT HAS A HEXAGON AT ITS NORTH POLE AND A DECAGON AT ITS SOUTH POLE!!
"What it comes down to is what tools you're giving it access to," says Decagon CEO @thejessezhang on enforcing guardrails on AI agents.
One cool technique to improve latency in LLMs is to have a small, fast model generate tokens and a larger, slower model review the output in one pass.
It'd be like having a junior employee write a report, and then having a senior employee review it in one go before it gets sent to a client.
This is called "speculative decoding" and lets you generate faster while maintaining the output quality.
Great write-up from the @DecagonAI team on how we've been doing this:
Show more
We were very excited by @inco_ai's Dflash2 release and started building with it immediately.
A few tweaks to the training recipe further improved acceptance length by another 33%. Full write-up below.
Show more
More great writing from our Decagon Labs team, this time on our post-training efforts!
at decagon, we’ve been building around a simple idea: the failures of your current model checkpoint should shape the training data for the next one.
What a time to be alive
fwiw I think it is _extremely_ unlikely that user data had any influence here - there is no way OAI would pull user transcripts for this, or knowingly train on it in a way that would've influenced this.
I think its pretty important people don't run away with 'your user data isn't safe in codex' - because it surely is (based on everything I can assume from the outside)
Show more
Big +1 to this. We were a bit skeptical of this when we were first starting out, but once the task is defined, it's strictly better to move to smaller models. Better latency, better cost, AND you can tune it for the specific task.
Great reason for frontier labs to open-source small models since they don't compete with the big models on the same use cases.
Show more
Training tiny models for special purpose use cases works so incredibly well if you have a great self improving recursive flywheel. Shopify ML team is on fire.
finetuned 0.8b model beats GPT 5.6-sol xhigh in this very specialized task.
Show more
One interesting learning I've had is that if you have a good AI experience in place, people find new ways to interact with their customers.
This usually leads to MORE interactions, not fewer.
Agents should be proactive and not just reactive.
Show more
Introducing Campaign Composer, a new way to build AI agents for proactive outreach.
Agents can coordinate voice and SMS across days or weeks, carry context between interactions, and follow campaign rules while working toward a customer outcome.
Show more
GPU prices have actually gone up over the last handful of months.
As you scale inference aggressively, especially with open-source models, being more GPU-efficient is a big win.
This is an awesome post by our Decagon Labs team about how we achieved some of these gains!
Show more
My AI agent when I say 'you're absolutely right' back to it
