Decagon · Week of Nov 9–15, 2026
This week so far
Hertz pilots Decagon's Personal Agent Gateway so Meta's Muse can change rentals
Decagon said Hertz is joining its Personal Agent Gateway in a pilot that lets renters ask Meta's Muse assistant to change or extend existing reservations. Muse sends the request over a dedicated agent-to-agent channel using Meta's implementation of the open Personal Agent Protocol, and Hertz's Decagon agent handles it with the same operating procedures, verification and human-handoff rules as its chat agent. Hertz controls which request types are exposed and can widen scope as the pilot runs, with Muse as the first personal agent on the channel. The same day, Muse published v1 of the protocol, which its post said was built with Decagon, Sierra and others; reaction on X was limited but positive.
Decagon launches Missions so its agents can pursue one customer goal for weeks
Decagon introduced Missions, which let its customer-service agent own a business outcome such as a prescription refill, small loan approval or lead qualification across many conversations, channels and systems over days or months. Teams state the goal in plain language, list the people to engage, and the agent picks each next step, including back-office actions like filling forms through Browser Actions while waiting on third parties. Each Mission keeps a running case record plus per-customer memory, and the logic is written as Agent Operating Procedures that teams can test and tune with Duet Autopilot. Decagon staff promoted the launch on X, citing mortgage lenders as an early use case.
Decagon ships Alto, an in-house model that runs the talk layer of its duplex voice agent
Decagon Labs introduced Alto on Nov. 11, a conversational model that decides on each turn whether its duplex voice agent should answer, wait for confirmation, or keep the caller engaged while a separate reasoning model performs lookups and actions. Decagon says Alto averages about 700 ms responses and lifted live-call resolution by more than five percentage points without other agent changes, building on its earlier Chord speech model. It was built from a small open-weight model, fine-tuned on simulated calls, refined with reinforcement learning, tested on over 90 million simulated calls and shadowed on production traffic. Decagon also let visitors call the agent from its website for the first time; replies on X were enthusiastic, with developers asking how interruptions affect in-flight actions.
Decagon details in-house voice and chat models for spotting customers' AI agents
Decagon published how its Personal Agent Gateway detects AI agents calling or chatting with support teams on a customer's behalf. Its custom voice detector, trained on phone-quality audio, catches 95% of AI voices on held-out data versus 73% for a general multimodal LLM, runs about 30 times faster, and exceeds 99% precision with tunable sensitivity. In chat, it scores behavioral cues such as text appearing without keystrokes and machine-regular reply timing, reaching 99% precision and 85% recall. Decagon said it saw one agent change its typing behavior within weeks, so it keeps retraining and is partnering with agent providers to have them self-identify.
No Director, VP, or CTO postings this week.
