Yash Tekriwal

AI Summary

→ 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 INSIGHTS - **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. 💼 SPONSORS [{"name": "Guru", "url": "https://www.getguru.com"}, {"name": "ThoughtSpot", "url": "https://go.thoughtspot.com/howiai"}] 🏷️ Slack Automation, Perplexity Computer, Personal Productivity, AI-Assisted Development, Workflow Optimization