Friday Oct 10, 2025
Friday Oct 10, 2025
Friday, 10 October 2025 04:21 - - {{hitsCtrl.values.hits}}
Slack, a Salesforce company, has unveiled major enhancements to its platform that enable partners and developers to build secure, context-aware AI apps and agents powered by customer-owned conversational data.
The launch introduces a real-time search (RTS) API and a Model Context Protocol (MCP) server, giving flexible, permission-aware access to the latest messages, files, and channels in Slack—so AI can act with the right context while meeting enterprise governance and control requirements.
Thousands of companies are racing to deploy agents, but most stumble on the same hurdle: usefulness in the day-to-day flow of work. Agents run on data, and the most powerful signal is conversation. Slack unlocks this previously unstructured, hard-to-reach corpus so apps and agents can move beyond generic output to deliver user-specific, context-rich assistance that drives productivity.
An ecosystem of leading innovators—including Anthropic, Google, Perplexity, Writer, Dropbox, Notion, Cognition Labs, Vercel, and Cursor—is already building on these capabilities, with new AI Slack apps and agents available in the Slack marketplace. By securely tapping Slack’s conversational data, these partners are bringing intelligence directly into the flow of work, reducing app-switching and turning discussion into action.
Slack CEO Denise Dresser said: “The future of work is undeniably agentic, and the success of AI depends on its seamless integration into human workflows. Our latest Slack platform innovations create the secure, data-rich environment necessary for AI agents to become trusted companions. We make it simple for customers and partners to build their AI solutions directly into Slack so that work is more connected, intelligent, and productive than ever before.”
Built for the agentic enterprise, the expanded platform delivers:
1.RTS API surfaces the most current discussions, files, and channels in real time without bulk exporting or duplicate storage, always honouring user and channel permissions.
2.MCP server standardises how LLMs, apps, and agents discover context and execute tasks in Slack, replacing fragmented integrations with a single, consistent protocol.
Organisations can unlock unstructured knowledge and save users an average of 97 minutes per week; accelerate decision-making by 37% and customer responses by 36% by connecting app data (e.g., Agentforce Sales, Workday) to conversations; and increase productivity by eliminating context switching.
With 1.7 million+ apps used weekly in Slack, and 95% of users saying apps are more valuable inside Slack, developers overcome the adoption gap by delivering tools directly in the workspace.
Slack’s security, privacy features, and granular permissions provide a robust foundation for compliant, agentic collaboration.
Slack also introduced Work Objects—standardised, rich previews that connect third-party data (details, images, documents) directly to conversations—and new agentic developer tools, including AI best practices, prebuilt Block Kit Tables, and updated CLI resources for Bolt apps, streamlining the entire build lifecycle.
The RTS API and MCP server are in closed beta with general availability expected early 2026. Third-party AI agents using these capabilities are available now in the Slack Marketplace. Work Objects will reach general availability in late October, and the new developer tools are currently available.
