Observed Signal · Apr 13, 2026 · Technical Release · Source: Lennys Newsletter · Impact: 1/5 · Sentiment: Positive
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.
Practical tutorial-level coverage of LLM-powered productivity workflows for non-technical users; useful signal about adoption patterns and emerging micro‑software but not industry-shifting platform or policy news.
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 built an AI-powered Slack digest using Perplexity Computer and OpenClaw that reduces ~100–150 daily Slack notifications to ~30–40 actionable items.
- Perplexity Computer uses multi-model orchestration (different models for subtasks) and cloud connectors to services like Gmail, Slack, Notion and Asana for cloud deployment and shareable apps.
- JJ Englert uses Claude Cowork to build a "daily operating system" that runs reusable skills, guided by a Markdown "brain" file that encodes personal working preferences and context.
- Both guests recommend an "anti-to-do list" approach: identify repetitive tasks you hate and automate them into deterministic tools or reusable AI skills.
- Guests argue AI will expand micro‑software on top of SaaS rather than kill SaaS; Yash said he’d pay about $15/month for a maintained Slack digest product.
Connected Companies & Entities
4 Entities mappedOntology Mapping & Concepts
Related Market Signals & Shifts
Recent verified developments and strategic activity across this market segment.
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.
OpenClaw Home Agents and Coinbase's AI Playbook
This newsletter episode of How I AI (host Claire Vo) features two interviews: Jesse Genet describes running five specialized OpenClaw agents—each on its own Mac Mini—to manage homeschooling, family finances, scheduling, development projects and household operations, emphasizing role definition, data partitioning, photo-first inputs, and 'decision files' for settled policies. Chintan Turakhia (leads engineering at Coinbase) explains how Coinbase scaled AI adoption across engineering (1,000+ engineers), using tactics like short “speed run” sessions (100 engineers shipping 75 PRs in 15 minutes), internal agents to convert feedback into shipped features quickly, targeting tedious work first, and measuring end-to-end feedback-to-feature cycle time (cut PR review from ~150 to ~15 hours). The episode highlights practical agent governance, productivity gains, and playbooks for broad AI adoption in engineering teams.
Build a Self-Improving AI PM OS with Claude Code
Aakash Gupta’s May 14, 2026 podcast episode and newsletter explains how product managers can build a self-improving AI-powered PM operating system using Anthropic’s Claude ecosystem—Chat, Cowork, Claude Code and Dispatch. Guest Pawel Huryn demonstrates practical workflows: when to use each surface, how to connect real files and tools via MCP connectors, and how to design persistent, iterating knowledge systems (CLAUDE.md router pattern, skills marketplace, hooks, subagents). The piece contrasts personal automation (Claude Code) with production automation (n8n), outlines a 24/7 PM workflow across devices, and gives actionable patterns (three-line self-improving prompt) to make agentic systems learn from data and improve over time.
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.