Skip to content
How I AIHow I AI

How to use Perplexity Computer to build a custom slack inbox (full tutorial)

Yash Tekriwal is the head of education at Clay. A self-described hyper-optimizer, Yash has built multiple custom productivity applications using Perplexity Computer and OpenClaw to manage his overwhelming daily workflow—including a Slack digest system that categorizes over 150 daily notifications into actionable priorities, and a consolidated news/email/Slack dashboard that serves as his personal command center. *What you’ll learn:* 1. How Yash built a custom Slack digest that categorizes 150+ daily notifications into action-required, need-to-read, and FYI buckets 2. Why Perplexity Computer beats Claude Code and Codex for building personal productivity apps 3. His “anti-to-do list” framework: spending an hour daily automating tasks you never want to do again 4. How to use AI for deterministic tasks (APIs, structured data) vs. subjective tasks (categorization, summarization) 5. Why the SaaS apocalypse narrative is wrong—and why we’re about to see an explosion of micro-software 6. How his team uses Perplexity Computer to prototype design systems and communicate with cross-functional partners *Brought to you by:* Guru—The AI layer of truth: http://getguru.com/ ThoughtSpot—Build AI-powered analytics into your product: http://go.thoughtspot.com/howIAI *In this episode, we cover:* (00:00) Introduction to Yash (02:38) The burden of 150 daily Slack notifications (05:45) When to use AI for tasks vs. building deterministic code (06:38) Building the Slack digest with OpenClaw (11:33) Introducing Perplexity Computer and the visual dashboard (14:28) Three reasons Perplexity Computer beats Claude Code (16:14) Using connectors to automate meeting follow-ups across Notion and Asana (18:21) The Kanban-style Slack dashboard (20:15) The long tail of customer requests and the future of micro-software (24:09) The anti-to-do list framework (26:21) Building a consolidated news, email, and Slack digest (29:48) How Perplexity Computer handles authentication and deployment (31:46) Team use case: Prototyping persona-based learning journeys for Clay University (35:49) Lightning round and final thoughts *Tools referenced:* • Perplexity Computer: https://www.perplexity.ai/computer/new • OpenClaw: https://openclaw.ai/ • Discord: https://discord.com/ • Claude Code: https://claude.ai/code • Codex: https://openai.com/codex/ • Asana: https://asana.com/ • Airtable: https://airtable.com/ • Figma: https://www.figma.com/ • Vercel: https://vercel.com/ • ChatGPT: https://chat.openai.com/ *Other references:* • Slack: https://slack.com/ • Notion: https://www.notion.so/ • Superhuman: https://superhuman.com/ • Clay University: https://www.clay.com/university • Kanban boards: https://en.wikipedia.org/wiki/Kanban_board *Where to find Yash Tekriwal:* LinkedIn: https://www.linkedin.com/in/yashtekriwal/ X: https://x.com/yash_tek Company: https://www.clay.com/ *Where to find Claire Vo:* ChatPRD: https://www.chatprd.ai/ Website: https://clairevo.com/ LinkedIn: https://www.linkedin.com/in/clairevo/ X: https://x.com/clairevo _Production and marketing by https://penname.co/._ _For inquiries about sponsoring the podcast, email jordan@penname.co._

Yash TekriwalguestClaire Vohost
Apr 8, 202644mWatch on YouTube ↗

At a glance

WHAT IT’S REALLY ABOUT

Build a custom Slack inbox using Perplexity Computer and connectors

  1. Yash explains how 100–150 daily Slack notifications create anxiety even though most are low-priority FYIs, motivating a system to classify messages by urgency and type.
  2. He first prototypes a deterministic Slack “digest” pipeline using Slack APIs and an AI coding agent (OpenClaw) while reserving AI primarily for the subjective step of message categorization.
  3. He then uses Perplexity Computer to rapidly turn the digest into a usable web UI—a three-column Kanban board with filters and an “Archive All” action that clears FYIs from both the dashboard and Slack.
  4. The conversation argues that AI enables a long-tail “micro-software” ecosystem: users can build highly specific workflow extensions to products like Slack, and small paid tools can thrive without venture scale.
  5. Additional Perplexity Computer use cases include automating meeting follow-ups across Notion and Asana and quickly prototyping persona-based learning journeys for Clay University by leveraging browser-based visual context.

IDEAS WORTH REMEMBERING

5 ideas

Separate “message retrieval” from “message judgment.”

Yash uses deterministic Slack API logic (timestamps, thread context, mention types) to fetch the right items, and applies AI only where human-like judgment is needed (action required vs read vs FYI).

A digest is helpful, but a UI changes behavior.

The initial text digest reduced noise but was still draining to scroll; the Kanban dashboard made prioritization, navigation, and bulk actions (like archiving FYIs) fast enough to become a daily habit.

Perplexity Computer’s advantage is orchestration, not just a model.

Yash highlights multi-model “ensemble” execution, parallel tasks, and automatic troubleshooting loops that reduce the repetitive re-prompting common in single-model coding workflows.

Cloud-native agents make connectors and auth feel “sticky.”

Because Perplexity Computer runs in the cloud and shares connector authentication across apps and deployed UIs, it avoids repeated token setup and can often re-authenticate or proceed via browser actions.

Use connectors to close the loop from insight to action.

Instead of only summarizing meeting transcripts, Yash describes extracting action items from Notion notes, routing them into Asana, and drafting messages/emails—turning AI from reporting into execution.

WORDS WORTH SAVING

5 quotes

I truly wake up to maybe 100 to 150 new Slack notifications… 60 to 80% are more in the FYI category.

— Yash Tekriwal

You can use AI to do a task for you… or you can use AI just to build a tool that would've been much harder to build before.

— Claire Vo

I can just go ahead and click this Archive All button… and then those notifications will also disappear on my Slack.

— Yash Tekriwal

My dream is for someone else to watch this video… and then I can go pay that person $15 a month for this app… because I would happily pay that.

— Yash Tekriwal

There has always been this long tail queue of… niche customer requests… And the answer as a reasonable SaaS PM is like, ‘Never.’

— Claire Vo

Slack notification overload and prioritizationDeterministic code vs AI for subjective tasksSlack digest bot via Slack APIs and timestampsPerplexity Computer: multi-model orchestration and concurrencyConnectors (Slack, Gmail, Notion, Asana, Drive, etc.)Kanban-style personal command centers (Slack/email/news)Micro-SaaS long tail and “anti-to-do list” automation

High quality AI-generated summary created from speaker-labeled transcript.

Get more out of YouTube videos.

High quality summaries for YouTube videos. Accurate transcripts to search & find moments. Powered by ChatGPT & Claude AI.

Add to Chrome