Turn Slack notifications into a scheduled text digest organized by rules that reflect how the user actually prioritizes work.
Source episode · 05:57
How I AI: Yash Tekriwal on Taming Slack with a Custom AI-Built Dashboardwith Claire Vo
05:57 to 12:24: Yash reverse-engineers Slack’s notification timestamps, builds a Jarvis digest channel, and applies his own urgency categories to the messages.
A recurring digest that groups new messages by urgency, category, source, and action needed.
Step by step
Follow the sequence once, then adapt the prompts, checks, and handoffs to your own setup.
6 steps
Before you start, define your notification categories. A useful approach is to sort by two layers: Source (e.g., DMs, Group DMs, Threads, Group @mentions) and Urgency (e.g., Action Required, Need to Read, FYI).
Define urgency levels, categories, senders, keywords, and examples of what belongs in each.
Select an AI agent that can write and execute code, such as OpenClaw. Host the agent in a platform that supports long conversations and has good search functionality, like Discord, to keep your work organized.
Choose an agent that can inspect Slack, write code, and deploy a scheduled job.
Task your AI agent with reverse engineering Slack's notification logic. The goal is for the agent to understand how Slack uses timestamps ( ts ) to differentiate between read and unread messages and threads. This avoids you having to read the API documentation yourself.
Inspect how Slack represents notification timestamps and pagination; document the request and cursor behavior.
Work with the agent in a conversational back and forth to write the core script. The script needs to pull only unread notifications, group them into the Source categories you defined earlier, and use the timestamp logic to avoid fetching content you have already seen.
Fetch new notifications since the saved cursor, normalize them, deduplicate by message ID, and preserve source links.
Once the script pulls and groups messages by source, use the AI agent for the final subjective step. Have it analyze the text of each notification and categorize it into your Urgency buckets, such as 'Action Required,' 'Need to Read,' or 'FYI'.
Classify each item using the approved rules and include the reason for urgent items.
Automate the final script to run on a schedule, such as daily. Configure it to post the organized, text based digest into a dedicated Slack channel for your review.
Post the digest to [channel] on [schedule], then save the cursor only after a successful post.
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
Log your workouts effortlessly without ever opening a spreadsheet. This workflow uses the Claude mobile app to parse a simple voice note and automatically update your workout tracking spreadsheet in the background.
Create a custom email management interface within Claude to read, triage, and draft replies without opening the Gmail tab. This workflow helps you reclaim focus and compound your learnings by training your AI on every interaction.
Build a fully automated system in Claude to generate personalized, interactive HTML proposals and client onboarding materials, saving hours on administrative work and creating a high-touch experience.
Join 100,000+ product managers who use ChatPRD to write better docs, align teams faster, and build products users love.