Observed Signal · Apr 8, 2026 · Product Use Case / Implementation · Source: Lennys Newsletter · Impact: 1/5 · Sentiment: Neutral
Clay's Yash Tekriwal Builds AI-Powered Slack Digest
Yash Tekriwal, Head of Education at Clay, describes building a custom Slack digest and consolidated dashboard to manage 150+ daily notifications using Perplexity Computer and the OpenClaw agent harness. The system categorizes messages into action-required, need-to-read, and FYI buckets and integrates with tools like Notion and Asana for follow-ups. Tekriwal explains when to use deterministic code vs. LLM-driven AI (APIs/structured data vs. categorization/summarization), argues Perplexity Computer outperforms Claude Code and Codex for his use cases, and shares an “anti-to-do list” framework focused on automating repetitive tasks. He also notes Clay’s team uses Perplexity Computer for prototyping design systems and persona-based learning journeys for Clay University.
Practical personal and team use case showing LLM-based tooling (Perplexity Computer, OpenClaw) applied to productivity workflows; relevant to MarTech teams exploring AI integrations but not industry-shifting.
Track Clay Signals & Market Shifts in Real-Time
Polaris7 autonomous intelligence agents track regulatory filings, primary sources, executive changes, and deal flow 24/7. Create your free Explorer workspace to monitor these entities.
Key Takeaways & Evidence Grounding
- Yash Tekriwal is Head of Education at Clay.
- He built a custom Slack digest that categorizes 150+ daily notifications into action-required, need-to-read, and FYI buckets.
- The system was built using Perplexity Computer and OpenClaw and integrates with tools like Notion and Asana for automated meeting follow-ups.
- Tekriwal argues Perplexity Computer outperformed Claude Code and OpenAI Codex for his personal productivity app use cases.
- He advocates an “anti-to-do list” framework: spend time automating recurring tasks you don’t want to do again.
Connected Companies & Entities
8 Entities mappedOntology Mapping & Concepts
Related Market Signals & Shifts
Recent verified developments and strategic activity across this market segment.
Custom AI Slack Inbox and Claude Cowork Guide
This newsletter episode covers two How I AI interviews showing non-engineers building practical AI-driven productivity systems. Yash Tekriwal (Head of Education at Clay) explains how he used Perplexity Computer and OpenClaw to build a Slack digest that reduces roughly 100–150 daily notifications to about 30 actionable items by categorizing and routing messages via APIs and deterministic code. JJ Englert (Enablement & Community Lead at Tenex) demonstrates using Claude Cowork to create a daily operating system that drafts emails, reviews work, plans the day, and runs reusable "skills" driven by a project-specific "brain" file. Both guests advocate automating hated repetitive tasks (an "anti-to-do list") and predict growth of personalized micro‑software built atop existing SaaS platforms.
OpenClaw guide: Build and run personal AI agents
A detailed how-to and user report on OpenClaw — an open‑source, agentic personal AI assistant that runs locally or on a hosted/VPS machine. The newsletter summarizes installation options (hosted services, VPS, or personal hardware like a Mac Mini), onboarding steps, key concepts (gateway, agents, crons, tools/skills), useful integrations (email, calendar, GitHub, Linear, search APIs), and operational/security best practices (use isolated machines, prefer read-only tokens, audit crons and skills). The author describes running multiple specialized agents (e.g., personal assistant, family manager, marketer, sales bot), practical example crons/tasks, model choices (Claude Opus, Codex/ChatGPT), and notes ongoing costs and governance considerations. The piece emphasizes agentic workflows' productivity benefits while warning about prompt injection, credential exposure, and the need for robust operational security.
Morning Brew Founder Built a Claude-Powered Content Machine
Alex Lieberman (co‑founder of Morning Brew and co‑managing partner at Tenex/10X) described a productionized, AI-native “content machine” built on Claude/Claude Code. An “AI Oracle” scans the last seven days of internal systems (Slack, Notion, Gmail, meeting notes) plus followed internet sources to surface ~15 ranked content spikes daily. The pipeline uses a six‑persona AI Interview Panel with voice‑to‑text capture (Whisperflow) to elicit specifics, drafts in a codified personal‑voice markdown, and routes pieces through a six‑person Writers’ Council that revises drafts until they meet a high editorial score. Integrations include Slack, Notion, Linear, Git and Gmail, and a reinforcement loop captures lessons from published posts. Lieberman emphasized mapping workflows before automating and running employee advocacy programs (Tenex Creator Cup) as a durable distribution moat.
Track Real-Time Market Signals & Shifts
Set up custom watchlists to receive automated, evidence-grounded executive digests whenever material signals or shifts occur across your tracked landscape.