Unlocking the Power of Conversation: How Slack’s New Platform is Fueling the Agentic Era

 

The future of work is here, and it’s agentic. AI agents are essential for getting things done efficiently, but in order for them to be effective, they need context. The richest context comes from the everyday conversations happening within your team.

Think about it: Your team’s most valuable insights, decisions, and ideas are often shared in discussions. This conversational data is a goldmine, yet it’s frequently locked away, difficult for people to search and impossible to access for tools designed to help.

We recently announced the next evolution of the Slack platform, giving partners and developers the tools they need to build powerful AI apps and agents. These are securely connected to the rich, customer-owned and -controlled conversational data in Slack.

Both the new Real-Time Search (RTS) API and new Model Context Protocol (MCP) server provide secure, flexible, and agent-ready access to conversational data. This rich context empowers agents to move beyond generic responses, enabling context-aware, user-specific conversations. AI becomes more relevant, more accurate, and far more powerful in boosting productivity.

Leading companies — including OpenAI, Anthropic, Google, Perplexity, Writer, Dropbox, Notion, Cognition, Vercel, Cursor — have built new AI and agent app experiences using these innovations. Look for these powerful apps and agents coming soon to the Slack Marketplace.

Slack is the natural home for modern AI apps and agents

The average enterprise juggles over 1,000 applications, leading to employees wasting countless hours copying, pasting, and context switching, draining productivity by up to 40%. It’s a frustrating reality for users, and it results in nearly half of SaaS licenses going unused.

But what if there was a better way? Imagine a seller simply asking an agent to update CRM records, an employee resolving an IT issue without filing a ticket, or a marketing leader analyzing campaign performance without pulling a single report.

By unifying your tech stack with AI apps and agents in Slack, you’re not just making work easier for your teams, you’re maximizing the return on your entire IT investment. That’s why Slack is the 2% of your IT budget that amplifies the other 98%.

• Unlock unstructured data: Enhance your AI agents with access to your team’s discussions and files (with permissions, of course), giving you personalized, relevant insights right in Slack. Teams save an average of 97 minutes a week using existing data intelligently and securely.
• Accelerate decision-making: Connect all app data, like Agentforce Sales, Asana, or Workday, with Slack conversations to provide complete context, enhancing search and AI for faster insights and action. This results in 37% faster decision-making across teams and 36% faster responses to customers.
• Boost productivity: Build your AI and agents directly into Slack, unifying your tech stack. This means fewer clicks, less wasted time, and more focus on work, all from the place where your conversations are already happening.
• Drive app adoption: Bring all your apps and agents where you and your team already work, enabling them to use all their tools in a single place.
• Stay secure and compliant: Keep your data protected with enterprise-grade security, robust privacy features, and granular permissions, providing a secure foundation for collaboration.

 

Powering trusted, context-aware AI

We know one size does not fit all. That’s why the Slack platform is built for flexibility and extensibility, allowing you to integrate all your apps, data, and agents. Our platform enhancements power agentic AI, making it easy for developers and partners to build powerful, custom agents tailored to your unique needs. These agents securely access rich, contextual conversational data directly within Slack, significantly boosting productivity. With built-in security, we are dedicated to safeguarding your Slack data and providing the tools you need to develop robust AI apps and agents with secure access and retrieval on your terms.

The Real-Time Search (RTS) API and Model Context Protocol (MCP) server provide secure data access on your terms for developers and third parties:

• The RTS API gives apps real-time access to one of your company’s most valuable assets: the rich, conversational data within Slack. By surfacing the most current discussions, files, and channels, the RTS API empowers AI to act on information in context. It unlocks your organization’s collective intelligence, securely connecting agents to conversations once trapped in silos. Crucially, the RTS API is designed with enterprise security at its core. Tools interact with conversational data without needing to bulk-download it or store it elsewhere, respecting existing access permissions and retrieving only the specific messages or files relevant to a query. The result: AI agents get the precise, contextual information they need — nothing more, nothing less.
• The MCP server takes it a step further by simplifying and standardizing how large language models (LLMs), AI apps, and agents discover contextual information and execute tasks on behalf of Slack users, reducing complexity for developers. With its unified communication layer between the LLM and Slack, the server establishes a universal way for AI systems to connect to data sources and tools. Fragmented integrations are replaced with a single, consistent protocol that adheres to the user’s specific permissions. Developers don’t have to write code to define every possible task an agent can perform or implement complex, service-specific integrations for each LLM or external service.

In addition, the Slack platform continues to advance the fundamental building blocks available to admins and developers with new innovations:

• Slack work objects: Developers can now build apps with dynamic, interactive previews directly within Slack. Work objects standardize how third-party data appears, providing detailed information, images, and documents in Slack and eliminating the need to switch applications. This deep integration gives AI agents greater context, improving their ability to find information and act quickly and accurately. We launched partner integrations with Google Drive, OneDrive, Asana, PagerDuty, Box, and Highspot in August.
• Enhanced developer toolkit: Developers have everything they need to build and customize Slack for their business. From apps and agents to automated workflows, new capabilities include AI best practices, prebuilt Block Kit Tables, and updated resources like the CLI for Bolt apps. These upgrades streamline the entire development lifecycle, from the first line of code to the finished end-user experience, making it easier than ever to build for the agentic era.

Powerful AI apps you can use in Slack

The best way to see the power of the latest platform innovation is through the incredible apps our partners are already building. They’re using these capabilities to deliver powerful AI applications and agents that live natively in Slack, bringing intelligence directly into your workflow.

ChatGPT

OpenAI’s ChatGPT app for Slack uses our new RTS API so you can use ChatGPT directly inside Slack. By combining real-time collaboration with the power of ChatGPT, teams can surface insights about conversations, draft posts and replies, and take action faster. 

OpenAI Codex

Codex let’s you start contributing directly from team conversations in Slack — just tag @Codex in a team channel or thread. It automatically gathers relevant context from the conversation, chooses the right environment, and answers with a link to the completed task in Codex cloud. From there, you can merge its changes, continue working, or pull the task down to your local environment via the IDE extension to keep working.

Claude

Anthropic’s Claude for Slack lets teams collaborate with Claude through direct messages or @mentions in channels, with access to web search, data connections, and document analysis. By connecting Slack data to Claude, users can search across workspace channels, messages, and files for deeper insights — bringing AI directly into their workflow.

Google Agentspace

Google Agentspace, now part of Gemini Enterprise, is a single, secure platform to build, manage, and adopt AI agents at scale. It connects data across productivity tools to turn organizational knowledge into insights and actions. The Agentspace integration with Slack’s RTS API enables seamless information flow, letting users access insights through Agentspace agents in Slack or by querying live Slack data through Agentspace.

Perplexity

Perplexity is redefining search as a conversational, transparent discovery experience. By connecting to Slack through the MCP server, it can ground queries in the context of your team’s conversations. This helps you surface answers that aren’t only accurate but also directly relevant to your work.

Dropbox Dash

Dropbox Dash uses our RTS API to deliver instant insights across both Slack and Dropbox Dash. This gives you immediate access to your content while making sure all permissions and security remain intact. Instead of dealing with the friction of switching between apps, you can stay focused on what matters most: doing your best work.

Notion

The Notion AI Slack app allows you to ask questions about threads, conversations, or updates you might have missed. Using the RTS API, Notion AI can search for content across public and private channels and DMs (with appropriate permissions) so that your work in Notion reflects the most current conversations happening on Slack.

The future of work is here

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’re making 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. Learn more about the Slack platform or head to Slack Marketplace to find vetted, third-party AI apps today.