- “Conversation data is the gold in the agent’s era,” says Salesforce
- New upgrades allow Slack to use your unstructured conversations
- Salesforce also uses Anthropics MCP server
Few companies have gone as publicly ‘all-in’ on AI agents as much as Salesforce, and the company now hopes that the use of Agentic AI within its Slack Online partner platform will help it compete with Microsoft teams as new ways.
The company explained that while AI agents are dependent on a strong data afond., They thrive on additional context that they have so far been missing to some extent.
“Conversation data is the gold in the agent’s era, yet it has been locked away in unstructured messages and chats, virtually out of reach for employees, so much smaller applications,” Salesforce declared.
Slacks Agent AI gets a huge lift
Salesforce adds a new real -time search (RTS) API, a model Context Protocol (MCP) server and improved developer tools to relax to help it develop from offering generic answers to producing more relevant and accurate answers.
RTS API unlocks unstructured conversation data in slack through discussions, files and channels, so AI tools can interact with customer data without having to formalize them for a structured export and store it securely elsewhere.
With the MCP server (an open standard from anthropic), Salesforce is also to standardize and simplify integrations across multiple business systems for improved interoperability.
For developers, an updated CLI AI app/agent building process is improving.
“By building AI-run applications directly in Slack, developers and partners help organizations unite their tech-rack-what makes Slack the 2% of your IT budget that maximizes the return on the other 98%,” Salesforce wrote.
With the upgrades, companies can unlock the unstructured data, they have had all the time for extra intelligence, resulting in faster decision making (37% faster team insight and 36% faster customer response) and increased productivity (3x higher revenue growth per employee).
