Decagon

@DecagonAI

AI agents for concierge customer experiences. Trusted by the world's most impactful companies.

San Francisco

decagon.ai

Replies Reposts Media Articles

Decagon
@DecagonAI
Sep 2
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.
00:00
6
Decagon
@DecagonAI
Aug 28
Exciting to see GLM-5.3 and GLM-5.3-Flash advance the frontier of the intelligence vs. latency tradeoff.
Z.ai
@Zai_org
Aug 26
Introducing GLM-5.3-Flash - Leading capabilities at a highly competitive price - Natively multimodal with a 1M-token context window - A 320B-A18B model released under the MIT License - Previously previewed as Ox Alpha, running entirely on Chinese AI chips Blog:
2
Decagon
@DecagonAI
Aug 28
We’re partnering with @perplexity_ai to bring live web search to Decagon agents. Customer questions often depend on information that changes by the hour. Agents can now search the live web mid conversation, pull in current information, and respond with cited sources.
5
Decagon
@DecagonAI
Aug 27
Conversational voice agents need to know when a different person is speaking, but not every background voice should count. We combined speaker embeddings with a post-trained audio-language model to determine when a speaker change matters.
Article
Detecting Relevant Speaker Changes with Audio-Native Models
By @alon_rag and @EveraertDante The problem: knowing when another user joins the conversation In customer support, voice agents need to know not only what was said, but who is participating. If...
12
Decagon
@DecagonAI
Aug 27
New benchmark from one of our engineers with friends at @baseten! The two highest scoring models are open-weight, and GLM-5.3-Flash is the highest performing GLM model, ranking #7 overall.
Mika Okamoto
@mikahokamoto
Aug 27
We're releasing PACT, a benchmark for rule-following under pressure in enterprise AI assistants. One sentence of pressure raised violations 65% across 23 models. None is reliable enough to run unsupervised. Paper and leaderboard: trace-ai-labs.github.io/pact Data:
2