I built a custom Slack inbox. It was easier than you’d think. | Yash Tekriwal (Clay)
Episode
44 min
Read time
2 min
Topics
Productivity, Remote Work, Leadership
AI-Generated Summary
Key Takeaways
- ✓Notification triage framework: Categorize Slack notifications into four buckets — direct DMs, group DMs, thread mentions, and channel at-mentions — then subdivide each into three priority tiers: action required, need to read, and FYI. Applying this framework reveals that 60–80% of notifications are FYIs, shrinking a 150-item inbox to roughly 30–40 genuinely urgent items.
- ✓AI as builder vs. AI as doer: Distinguish between using AI to perform recurring tasks (categorization, summarization) versus using AI once to build deterministic code via APIs. Tekriwal's Slack digest uses AI only for message categorization; everything else runs as fixed, reliable code — reducing hallucination risk and making the system predictable at scale.
- ✓Perplexity Computer's ensemble orchestration: Perplexity Computer selects different models for different subtasks — Sonnet for fetching data, Gemini for planning and Python coding, Opus for intensive reasoning — and runs multiple tasks concurrently. This reduces the human reprompting loop and produces working prototypes faster than single-model tools like Claude Code or Codex.
- ✓Anti-to-do list as automation roadmap: Build a list of tasks you never want to do manually again — such as sorting Slack by hand, deleting spam email, or entering meeting action items into Asana — then spend one focused hour daily automating each item using AI tools. This reframes automation as a concrete, prioritized project rather than a vague aspiration.
- ✓Prototype-to-design communication bridge: Use Perplexity Computer to ingest an existing live website via browser, then rebuild a persona-based UI prototype in roughly one hour of back-and-forth prompting. The resulting visual mock-up — showing role-specific journeys for SDR, RevOps, and GTM engineers — closes the communication gap between non-designer stakeholders and design teams faster than Figma-based tools.
What It Covers
Yash Tekriwal, head of education at Clay, demonstrates how he built a custom Slack inbox management system using OpenClaw and Perplexity Computer, reducing 100–150 daily anxiety-inducing notifications to 30–40 actionable items through AI-assisted code and a Kanban-style dashboard UI.
Key Questions Answered
- •Notification triage framework: Categorize Slack notifications into four buckets — direct DMs, group DMs, thread mentions, and channel at-mentions — then subdivide each into three priority tiers: action required, need to read, and FYI. Applying this framework reveals that 60–80% of notifications are FYIs, shrinking a 150-item inbox to roughly 30–40 genuinely urgent items.
- •AI as builder vs. AI as doer: Distinguish between using AI to perform recurring tasks (categorization, summarization) versus using AI once to build deterministic code via APIs. Tekriwal's Slack digest uses AI only for message categorization; everything else runs as fixed, reliable code — reducing hallucination risk and making the system predictable at scale.
- •Perplexity Computer's ensemble orchestration: Perplexity Computer selects different models for different subtasks — Sonnet for fetching data, Gemini for planning and Python coding, Opus for intensive reasoning — and runs multiple tasks concurrently. This reduces the human reprompting loop and produces working prototypes faster than single-model tools like Claude Code or Codex.
- •Anti-to-do list as automation roadmap: Build a list of tasks you never want to do manually again — such as sorting Slack by hand, deleting spam email, or entering meeting action items into Asana — then spend one focused hour daily automating each item using AI tools. This reframes automation as a concrete, prioritized project rather than a vague aspiration.
- •Prototype-to-design communication bridge: Use Perplexity Computer to ingest an existing live website via browser, then rebuild a persona-based UI prototype in roughly one hour of back-and-forth prompting. The resulting visual mock-up — showing role-specific journeys for SDR, RevOps, and GTM engineers — closes the communication gap between non-designer stakeholders and design teams faster than Figma-based tools.
Notable Moment
Tekriwal reveals that threatening AI models with extreme fictional consequences — such as job loss or family emergencies typed in all caps — measurably improves output quality. He acknowledges the reasoning likely ties to reward specification in model training, but confirms the tactic works consistently across repeated use.
Episode Transcript
I truly wake up to maybe a 100 to a 150 new Slack notifications, not even just like, oh, these are unread channels. Truly, someone has tagged me. To 80% are more in the FYI category. So my 100 to 150 that's giving me anxiety is actually more like 30 to 40 that I really need to be on top of. You can use AI to do a task for you, like categorize things, summarize things, or you can use AI just to build a tool that would have been much harder to build before with very straightforward APIs and structured data. Exactly. Think about, like, a Kanban style board. You have in red on the left, action required, urgent. Yash needs to get back to it. In the middle, we've got a yellow need to read column. And then on the right in green, much more easy, I have a bunch of FYIs. I can just go ahead and click this archive all button. They'll disappear from the dash, and then those notifications will also disappear on my Slack. Ugh. That's magic. And this is such a better way to just get through your queue. My dream is for someone else to watch this video and say, I wanna 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. Welcome back to How I AI. I'm Claire Vogue, product leader and AI obsessive here on a mission to help you build better with these new tools. Today, have Yash Takroral, head of education at Clay, and he is a hyper optimizer showing us how he uses Perplexity Computer to work through the hundreds of Slack messages he gets every day. We're also gonna debate is SaaS really dead? Let's get to it. This episode is brought to you by Guru, the AI layer of truth for your company's knowledge. Here's the problem. Your AI is only as good as the information you feed it. Most companies are getting confident but wrong answers from AI because their underlying knowledge is outdated, incomplete, or just plain incorrect. Bad information doesn't just slow you down. It costs you money and puts you at risk. Guru solves this by adding a verification layer between your company's knowledge Instead of just hoping your AI gets it right, Guru automatically scores content for accuracy, flags, outdated information, and ensures your team gets trustworthy answers every time. It works with the tools you already use, so you don't have to change how you work. Thousands of companies trust Guru to keep their AI accurate and compliant. Ready to stop playing Russian roulette with your company's knowledge? Visit getguru.com to learn more. Welcome to How I AI. Yosh, I'm so excited. We've been trying to make this happen for …
Get the full transcript (8,872 words) + summary by email — free
One-time email with the complete transcript and AI summary of this episode. No account needed.
One email, no spam. We’ll also show you what SignalCast does.
You just read a 3-minute summary of a 41-minute episode.
Get How I AI summarized like this every Monday — plus up to 2 more podcasts, free.
Pick Your Podcasts — FreeKeep Reading
More from How I AI
Build your own company brain: the enterprise AI playbook from Stripe’s engineering team | Sharadh Krishnamurthy
Sep 7 · 50 min
David Senra
Mati Staniszewski on ElevenLabs, Voice AI & Building the Communication Layer for AI
Sep 9
More from How I AI
GPT-6 Astra is a banger - here’s everything I’ve built
Sep 3 · 32 min
The Founders Podcast
#430 How to Write Ads That Sell
Aug 23
Books, tools, and gear mentioned in this episode
SignalCast may earn commission on purchases via these links.
Tools
- ClayBy guest
by Clay
“Yash Tekriwal, head of education at Clay, demonstrates how he built a custom Slack inbox management system”
“built a custom Slack inbox management system using OpenClaw and Perplexity Computer”
- Perplexity ComputerRecommended
by Perplexity
“Perplexity Computer selects different models for different subtasks — Sonnet for fetching data, Gemini for planning and Python coding, Opus for intensive reasoning — and runs multiple tasks concurrently. This reduces the human reprompting loop and produces working prototypes faster than single-model tools like Claude Code or Codex.”
by Asana
“automating each item using AI tools. This reframes automation as a concrete, prioritized project rather than a vague aspiration. — such as sorting Slack by hand, deleting spam email, or entering meeting action items into Asana”
by Figma
“The resulting visual mock-up — showing role-specific journeys for SDR, RevOps, and GTM engineers — closes the communication gap between non-designer stakeholders and design teams faster than Figma-based tools.”
by ThoughtSpot
“💼 SPONSORS ["name": "ThoughtSpot", "url": "https://go.thoughtspot.com/howiai"]”
More from How I AI
We summarize every new episode. Want them in your inbox?
Build your own company brain: the enterprise AI playbook from Stripe’s engineering team | Sharadh Krishnamurthy
GPT-6 Astra is a banger - here’s everything I’ve built
Grok Bot vs. OpenClaw: How I replaced my entire agent stack
How I turned Claude into a self-improving PM assistant | Daniel Blum (PM, Melio)
I spent $20,000 on Devin in a month. Here’s what I learned | Ryan Carson (solo founder)
Similar Episodes
Related episodes from other podcasts
David Senra
Sep 9
Mati Staniszewski on ElevenLabs, Voice AI & Building the Communication Layer for AI
The Founders Podcast
Aug 23
#430 How to Write Ads That Sell
Accidental Tech Podcast
Aug 20
705: Relentless in a Gentle Way
How I Built This
Aug 13
Advice Line with Bobbi Brown of Jones Road Beauty (September 2025)
All-In with Chamath, Jason, Sacks & Friedberg
Aug 13
Rahm Emanuel: Trump's Foreign Policy, China, Europe's Decline, Immigration & DSA vs Democrats
Explore Related Topics
This podcast is featured in Best AI Podcasts (2026) — ranked and reviewed with AI summaries.
You're clearly into How I AI.
Every Monday, we deliver AI summaries of the latest episodes from How I AI and 192+ other podcasts. Free for one show.
Start My Monday DigestNo credit card · Unsubscribe anytime