I built a custom Slack inbox. It was easier than you think. | Yash Tekriwal (Clay)

2026-04-08 · Source: How I AI · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Software Development & Engineering, Emerging Technologies & Innovation · Depth: Intermediate, extended

Summary

Yash Tekriwal, Head of Education at Clay, demonstrates how he uses AI to manage a deluge of Slack notifications and emails, often exceeding 100-150 daily. He initially built a custom Slack digest using OpenClaw in Discord, which categorizes messages into "action required," "need to read," and "FYI" buckets, reducing his critical notifications to 30-40. This system, while effective, still presented a long text-based list. Tekriwal then enhanced this solution by building a Kanban-style dashboard UI using Perplexity Computer, which offers multi-model orchestration, concurrent task execution, and native integration with numerous applications like Google Drive, Gmail, Notion, and Asana. This dashboard allows for visual prioritization, deep linking to original messages, and an "archive all" button for FYIs, significantly streamlining his workflow. The discussion also explores the future of SaaS, suggesting a "Cambrian explosion" of niche, custom-built applications that can be monetized or acquired.

Key takeaway

For product leaders and AI engineers struggling with information overload, consider building custom AI-powered tools to optimize personal workflows. Your team can leverage platforms like Perplexity Computer to create tailored dashboards that integrate with existing SaaS applications, transforming generic notification streams into prioritized, actionable task lists. This approach not only boosts individual productivity but also opens avenues for developing niche, monetizable applications that address specific user needs not met by off-the-shelf software.

Key insights

AI can transform overwhelming digital communication into manageable, prioritized workflows through custom tools.

Principles

• Not all notifications are created equal.
• AI can build tools or perform tasks.
• Orchestrating multiple AI models enhances performance.

Method

Prototype with an AI coding agent (e.g., OpenClaw) to build a deterministic data organization system, then use a multi-model AI platform (e.g., Perplexity Computer) to create a custom UI for enhanced usability and integration.

In practice

• Categorize messages by urgency and type.
• Use AI to automate repetitive tasks.
• Build custom dashboards for personalized workflows.

Topics

• Slack Inbox Management
• Perplexity Computer
• AI Coding Agents
• Custom Productivity Apps
• Workflow Automation

Best for: AI Engineer, Software Engineer, Entrepreneur

Related on AIssential

• I built a custom Slack inbox. It was easier than you’d think. | Yash Tekriwal (Clay) — AI agents and platforms can transform overwhelming digital communication into actionable, prioritized workflows.
• Building My Own Personal AI Assistant: A Chronicle, Part 2 — API-driven data access and AI-powered task decomposition significantly enhance personal agent efficiency and utility.
• Computer comes to Excel, Word, PowerPoint, and Outlook - Perplexity — Perplexity's Computer integrates into Microsoft 365 apps, streamlining complex workflows with AI-powered content generation and data analysis.
• Personal Computer for Windows - Perplexity — Perplexity's Personal Computer for Windows orchestrates AI agents across local files, Microsoft apps, and the web with user-controlled access.
• Perplexity Max Debuts Multi-AI Agent Tool — Perplexity's new agent tool unifies 19 AI models for complex workflows, targeting professionals with a multimodal strategy.
• Building a custom Slack digest with OpenClaw — Automating Slack notification organization can significantly improve communication efficiency.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by How I AI.