AI-powered Slack digest cuts notification overload by 80%
My dream is for someone else to watch this video, look at this and say, 'I want to build that app on top of Slack,' and then I can go pay that person $15 a month for this app to be maintained and used, and then I can file bug reports with them instead of having to fix it myself, because I would happily pay that.
I think we will see a Cambrian explosion of like businesses that wouldn't have existed without venture funding or that people wouldn't have wanted to build, that can make their own money or get acquired by larger companies.
The more extreme you get with the examples, the more it's like, 'Okay, on this shot, I promise I will get it.' Even if you supply no reason, it has to be nowhere close to connected for you to actually get it to do better, but I will really tell it there are negative repercussions, and it does get stricter sometimes.
- Yash Tukerall developed a custom Slack digest tool using AI to categorize and prioritize his hundreds of daily Slack notifications, allowing him to focus on truly important messages.
- The custom Slack digest categorizes messages into 'action required,' 'need to read,' and 'FYI,' with 60-80% falling into the FYI category, significantly reducing anxiety and improving focus.
- AI can be used in two main ways: to directly perform a task (like categorizing or summarizing) or to build a tool that would have been much harder to create otherwise.
- Perplexity Computer's ability to use multiple AI models (like Sonnet 4.6, Gemini, Opus) in parallel for different parts of a task makes it uniquely powerful for complex development workflows.
- The native connection of Perplexity Computer to various tools and its cloud-based nature allows for more fluid development and faster iteration at the speed of thought.
- The speaker predicts a 'Cambrian explosion' of software being created and used due to AI tools, with many smaller businesses emerging that wouldn't have been viable before.
- AI can be used to prototype and communicate design ideas more effectively between design and other stakeholders, bridging the gap in understanding visual context.
- When AI isn't performing as expected, strategies include recognizing if the task is suitable for AI, being strict and emphasizing negative repercussions, and building custom skills while iteratively refining them.
- 100 to 150 new Slack notifications daily (Yash Tukerall's typical daily volume of Slack notifications.)
- 60-80% of notifications (Percentage of Yash Tukerall's Slack notifications that fall into the 'FYI' category.)
- 30-40 notifications (The actual number of Slack notifications Yash Tukerall needs to act on after filtering.)
- 15 dollars a month (The amount Yash Tukerall would happily pay someone to maintain a custom Slack app for him.)
- 80% of the custom Slack digest (The portion of the Slack digest tool that was built within the first four messages of interaction with Perplexity Computer.)
- 10 minutes (The time it took to kick off four different tasks in Perplexity Computer concurrently.)
- 10, 12, 20 messages (The number of messages it might take to iteratively improve an AI's performance on a specific task.)
RevBots.ai View:
- Classic AI Sprinkler move: bolting AI onto Slack instead of rethinking comms workflows.
- Shows the ARM opportunity to replace 15 SaaS tools with one orchestrated AI builder.
- Revenue teams stuck in SaaS Hoarder stage could prototype custom tools like this.
- Warning: building point solutions creates tech debt unless part of an ARM strategy.
Join The RevBots ARMy
The insider daily for Autonomous Revenue Masters.