Slack adds AI-fueled search and summarization to the platform

Key Points:

  • New features introduced by Slack to make information more accessible
  • Ability to summarize channel content for easier understanding
  • Usage of generative AI to provide answers to natural language questions based on Slack content


Slack, the popular enterprise communications platform, has introduced new features aimed at improving access to institutional knowledge stored within the platform. The new AI-fueled search tool and the ability to summarize information within channels are designed to address the challenge of extracting valuable insights from the vast amount of data stored in Slack.


Noah Weiss, Slack’s chief product officer, highlighted how the platform naturally accumulates corporate information in an informal and unstructured manner, making it difficult to surface relevant knowledge. The incorporation of generative AI, such as SlackGPT, enables the platform to extract deeper meaning and intelligence from the accumulated data, enhancing users’ ability to access and leverage this information effectively.


The introduction of channel summaries allows employees to quickly grasp the key points of conversations and catch up on missed discussions without having to delve into lengthy threads. Users can request a summary, and Slack’s AI model will generate a concise overview of the topics discussed, complete with references to demonstrate the model’s reasoning process, promoting transparency and trust in the information provided.


Moreover, Slack’s AI-powered search functionality enables users to ask natural language questions within the platform, retrieving specific information from Slack’s content archive. This feature, akin to ChatGPT, offers detailed answers, sourced directly from Slack content, and includes a quality check mechanism for users to provide feedback on the accuracy and reliability of the responses, enabling continuous learning and improvement of the AI model.


Despite not disclosing detailed information about the underlying model, Weiss mentioned that it incorporates a blend of large language models optimized for Slack’s data specifics and prompt engineering techniques to enhance performance and quality.


Slack’s AI search and summarization features are available as an add-on product for enterprise plans, offering enhanced functionality for an additional cost. Currently accessible in English in the U.S. and U.K., Slack plans to expand language support in the near future, catering to a broader user base. This strategic move by Slack aligns with its commitment to empowering businesses with advanced tools to streamline information retrieval and boost productivity within the platform.



Prompt Engineering Guides



©2024 The Horizon