Transform a structured text digest into an interactive board for scanning, acting on, and clearing work.
Source episode · 12:24
How I AI: Yash Tekriwal on Taming Slack with a Custom AI-Built Dashboardwith Claire Vo
12:24 to 20:26: Yash gives Perplexity Computer the structured digest and turns it into a Kanban-style interface with ordered categories, interaction, and archive behavior.
An interactive Kanban board whose cards preserve source context and state across refreshes.
AI search engine
Step by step
Follow the sequence once, then adapt the prompts, checks, and handoffs to your own setup.
5 steps
Start with a structured text digest of your notifications. The digest should be pre-categorized by source (like DMs, threads, and mentions) and by urgency (like 'Action Required,' 'Need to Read,' and 'FYI'). This text will be the data input for the visual dashboard.
Generate the digest as structured items with ID, source, category, urgency, summary, action, and URL.
Paste the text digest into Perplexity Computer. The initial prompt can be a direct instruction to transform the list into a visual dashboard. Perplexity Computer will analyze the structure of your text to begin building the app.
Build an interactive board from the supplied digest without dropping or inventing items.
Instruct Perplexity Computer to create a three-column Kanban board. Specify that the columns should correspond to your urgency levels: a red column for 'Action Required,' a yellow column for 'Need to Read,' and a green column for 'FYIs'.
Create ordered columns for [categories] and show urgency, source, summary, and action on each card.
Refine the dashboard by adding interactive features. Instruct the AI to add filters for your source categories (like DMs and threads). Also, ask it to make each item a deep link that points back to the original message in Slack.
Allow move, archive, open source, and filter actions; persist each change by item ID.
Add an 'Archive All' button to the 'FYI' column. Instruct the AI to program the button to clear items from the dashboard and simultaneously use the Slack API to mark the corresponding messages as read in Slack. This will clear the notification badges in the Slack app.
Archive only the currently visible completed cards, show the count, and provide undo.
Turn an idea into a PRD, user stories, and a plan.
After the steps
How to recover when the loop fails and where human judgment helps.
Recover
Keep building
Design a weekly meta-workflow that analyzes your interactions with your AI assistant to make it smarter. This system learns your writing style from edits, suggests new automations for repetitive tasks, and helps you filter valuable AI techniques from hype.
Create a daily AI workflow that summarizes yesterday's meetings, identifies urgent tasks, and proactively learns internal company terms it doesn't understand. This keeps your AI assistant's knowledge current and highly relevant to your work.
Build a recurring AI task that automatically gathers updates from your calendar, Slack, and notes to suggest weekly priorities and prepare you for upcoming meetings. Start every Monday with a clear, comprehensive plan without the manual effort.
Join 100,000+ product managers who use ChatPRD to write better docs, align teams faster, and build products users love.