Chat SDK adds native Slack agent support
Chat SDK now supports building Slack agents with native features including agent badges, agent conversations in Messages tab, suggested prompts, streaming replies, rotating status messages, and built-in feedback buttons. The new Slack adapter enables token-by-token streaming with fallback support for workspaces that don't support streaming.
Chat SDK's now supports the agent messaging experience . Agents built with Chat SDK could already talk in channels and DMs and stream replies token-by-token. This update adds the Agent badge, agent conversations in the Messages tab, suggested prompts, rotating status messages, and native feedback buttons.Slack adapterSlack introduced on June 30
Here's what the adapter gives you:
One thing to know: under , Slack threads each user message individually, so channel history only returns the user's side of a DM. Use to build AI conversation history instead.agent_viewChat SDK transcripts
Read the to get started, or begin with one of our .documentationtemplates
Pass a static payload or an async resolver that receives the thread context, including what the user is currently viewing under . Prompts are pinned automatically whenever an agent thread opens.Suggested prompts, per thread:
agent_viewStreamed replies render token-by-token via Slack's streaming API, including task and plan cards. If a workspace doesn't support streaming (e.g., GovSlack), the adapter switches to post-and-edit mid-stream without losing content.Native streaming with a fallback:
Set and every streamed reply ends with Slack's native thumbs-up and thumbs-down buttons. Clicks dispatch through the regular flow with a positive or negative value.Built-in feedback:
feedbackButtons: truebot.onAction
Source: original entry ↗
More from Vercel
Follow Vercel to get its new changes in your feed and email digest.
OpenAI Decisions API now available on AI Gateway
OpenAI's Decisions API is now accessible through Vercel's AI Gateway with an OpenAI-compatible endpoint, enabling decision models to answer typed questions and return probabilities, choices, and scores for routing, triage, and guardrails use cases. Support is available across the OpenAI SDK, AI SDK, HTTP API, and CLI with the latest versions.
Timestamp attributes now supported in Vercel Flags
Vercel Flags now supports timestamp attributes for entities, allowing you to create time-based targeting rules. Use this feature to run limited-time campaigns, show content between specific dates, or target users based on registration date.
Glyph Cluster now available in stealth on AI Gateway
Glyph Cluster, a reasoning model for coding and long-context analysis, is now available as a stealth model on Vercel's AI Gateway for Pro and Enterprise plan teams with purchased AI Gateway credits at no cost during the stealth period. The model supports function calling, streams responses, and can be accessed via AI SDK, OpenAI-compatible APIs, and coding agents.