
Salesforce is announcing several major updates to Slack that will enable customers to leverage their conversation history for AI apps and agents.
The company is announcing a real-time search (RTS) API, which surfaces up-to-date discussions, files, and channels to provide agents access with context-aware information. To ensure secure use of information, data remains in Slack and the API adheres to existing user access permissions and only retrieves data that is relevant to the query.
“It unlocks your organization’s collective intelligence, securely connecting agents to conversations and decisions that were once trapped in silos,” Salesforce wrote in a blog post.
Slack also now has its own Model Context Protocol (MCP) server, which will enable AI agents to find information and act autonomously on behalf of Slack users.
“With this foundation, developers can move beyond basic integrations to create contextual, intelligent experiences that automate complex workflows. Their agents can now search, analyze, and act on Slack data to deliver more accurate, relevant, and personalized outcomes — reducing hallucinations and increasing reliability. The result: smarter, more stable agents that users can trust and adopt at scale,” Salesforce wrote.
The company also announced Work Objects, a standard way for third-party data to be displayed in apps, so that users can communicate, share, and take actions without leaving Slack.
According to Salesforce, several companies are already leveraging these new features to build applications for Slack users, including Anthropic, Cognition Labs, Cursor, Dropbox, Google, Notion, Perplexity, Vercel, and Writer.
“Alongside Slack functionality, the marketplace apps and third-party integrations play a crucial role in creating a unified ecosystem for human-AI collaboration. The marketplace makes it easier than ever for customers to discover tools that customize and securely extend the functionality of Slack to fit their teams’ needs,” the company wrote.