As a corporate communication platform, Looseness has become a de facto repository for institutional knowledge, but obtaining this information has been difficult with conventional search tools. Today Slack introduced some new features designed to make this information more accessible, including a new AI-powered search tool and the ability to summarize information within channels.
Noah Weiss, Slack’s chief product officer, says the platform naturally collects company information in an informal and unstructured way. The problem is to find a way to bring this hidden treasure trove of knowledge to the surface. “The key to all of this is that now this new wave of productive AI capabilities allows us to extract a whole new set of meanings and intelligence from all this analysis that has been built up for years [on our platform]Weiss told TechCrunch.
Last May Slack announced that he was incorporating genetic AI into the platform at the Salesforce World Tour in New York. It was more of a generalized call to action with the creation of SlackGPT, its own flavor of genetic artificial intelligence designed specifically for content on the Slack platform.
Today’s announcement concerns its implementation in more specific ways. Weiss says the ability to summarize channel content helps employees catch up after a break or simply avoid reading a long thread to get the gist of the conversation. With channel summaries, you can request a summary and Slack’s AI model creates a summary of all the topics discussed along with reports to show how the model generated each part of the summary, which Weiss says was an essential part of the design of this possibility.
“You can drill into any area and we show you all the detailed context. So we were really thinking about transparency, building trust, making sure we’re showing our work and empowering people to learn more if they want to,” he said.
Image Credits: Looseness
The company also allows users to ask questions naturally, just like with ChatGPT, but it uses Slack content instead of more general internet content, so a user could ask a question like “What is Project Gizmo?” SlackGPT then provides a response, again with a commission, to allow users to see where the response came from and whether they can trust it.
Image Credits: Looseness
Each response includes a quality check, where users can say whether the response was good, bad, or neutral, so the model can learn about the quality of responses and system engineers can see how well the model performs.
He won’t go into detail about the underlying model, saying only that it was a combination of large language models. “What we found is that they all perform in different ways and with different speed and quality characteristics. We’ve spent a lot of time refining the models for the data we actually have in Slack, and also doing a lot on the direct engineering side.”
Slack AI with search and summarization is an add-on product for enterprise plans, which means it will cost extra money over and above the normal license cost. Slack didn’t provide cost details, but it’s available today in the US and UK, only in English for now, but will be available in additional languages in the near future, according to the company.
