Writer vs LiveKit Agents
Side-by-side trajectory, velocity, and editorial themes.
Writer is building the buyer-side ecosystem around its enterprise AI agents.
Recent moves cluster around making Writer the default platform for enterprise marketing teams running AI agents — an AI Academy opened to all users with a Passport curriculum and credentials, a newly launched AI CMO Council for senior buyers, and WRITER Agent connectors to FRED, OECD, World Bank, and SEC EDGAR for citation-grade research. The feed itself is heavy on thought leadership and customer storytelling alongside the actual product news.
Writer is investing on the buyer side of the agent platform — credentialing for users, peer community for executive buyers, and connector breadth for use cases where citation accuracy matters. Less new core modeling, more making the enterprise AI workflow purchase rationale concrete. The repeated 'agentic marketing' framing across customer stories, thought pieces, and product posts reads as deliberate category positioning.
Expect more vertical data connectors in the FRED/SEC pattern (legal, regulatory, healthcare reference sources), and for AI Academy credentialing to become a sales-enablement asset tied to the CMO Council. The thought-leadership cadence suggests Writer wants to own the enterprise-AI-marketing category narrative before competitors anchor it.
LiveKit Agents added Answering Machine Detection — voice agents are becoming a serious telephony runtime.
LiveKit Agents is releasing roughly twice a week along the 1.5.x line, accumulating telephony-grade primitives around its voice loop. The headline is Answering Machine Detection in 1.5.9 — an LLM-classified detector for what kind of endpoint an outbound call hit. Surrounding work is split between reliability (barge-in cooldown, interruption guards, preemptive-generation tuning, observability retries) and provider breadth (Perplexity Responses, Soniox, Speechmatics, Cerebras, xAI, Rime WebSocket TTS). The mcp_servers parameter was also deprecated on Agent and AgentSession.
The product is converging on a real contact-center runtime, not just a realtime meeting agent. AMD, warm transfer, DTMF handling, recording retries, and avatar join/playback metrics are the feature surface phone deployments demand. The provider plugin universe keeps widening; LiveKit positions itself as the neutral broker between voice models and the actual network. Internal cleanups (mcp_servers deprecation, instruction parts, AvatarSession base class) suggest a tidying pass before a 1.6 cut.
Expect more telephony primitives — supervisor barge-in, richer DTMF flows, call-recording controls — and a unified MCP configuration surface across Agent and Session as the mcp_servers deprecation lands fully.
See more alternatives to Writer →
See more alternatives to LiveKit Agents →