Decagon

Engineering blog · decagon.ai/resources/blog

Watch

82posts0this week0watchers

WatchOpen blog (opens in a new tab)

DecagonBlog4w

DuetBench-2: Measuring agent self-improvement in production

DecagonBlog4w

Autopilot in production: Governance of self-improving agents

DecagonBlog4w

Proactive customer service strategies for CX leaders

DecagonBlog4w

Automated customer service without losing the human touch

DecagonBlog4 Sept

How we made one of our largest inference workloads 4.7× more GPU-efficient

DecagonBlog4 Sept

Audio-native semantic speaker-change detection

DecagonBlog2 Sept

Introducing Campaign Composer: Proactive, compliant outreach

DecagonBlog28 Aug

Your Decagon agent can now search the live web

DecagonBlog20 Aug

Scaling real-time text-to-speech inference

DecagonBlog20 Aug

Why speech-to-speech models aren’t ready for the enterprise (yet)

DecagonBlog19 Aug

Introducing Decagon Assist: Empower every representative to deliver concierge experiences

DecagonBlog19 Aug

How conversational AI components work together in customer service

DecagonBlog18 Aug

Teaching flow-matching text-to-speech models with RL

DecagonBlog13 Aug

How Decagon shipped real-time voice AI on Modal

DecagonBlog12 Aug

Getting closer to the build: How I helped create agent deployment engineering

DecagonBlog6 Aug

"Agent, agent, agent": designing conversations to reduce barge

DecagonBlog6 Aug

How we debugged a latent PgBouncer bug across four layers of the stack

DecagonBlog5 Aug

Introducing Browser Actions: AI agents that act across any web-based system

DecagonBlog13 Jul

What I learned building voice agents at Decagon

DecagonBlog9 Jul

What an air-gapped AI deployment actually requires

Showing the newest 45 of 82 posts. Browse by feature trail