Skip to main content
How I AI

Claude Cowork 101: How to automate your workday without touching code | JJ Englert (Tenex)

50 min episode · 2 min read
·

Episode

50 min

Read time

2 min

AI-Generated Summary

Key Takeaways

  • Project Architecture: Create a dedicated folder on your computer, attach it to a Claude Cowork project, and add a "brain" file — a detailed markdown document containing your working preferences, team members, and communication style. Every subsequent task in that project inherits this context automatically, eliminating repetitive setup and producing more consistent outputs across sessions.
  • Email Style Cloning: Connect Gmail via Cowork's one-click connector, then prompt Claude to analyze your last 30 sent emails and generate a personal writing style guide saved to project memory. This produces AI-drafted emails that match your actual tone, stored as drafts for review before sending — never auto-sent without explicit approval.
  • Sub-Agent Review Panels: Build a reusable "sub advisory" skill that spins up three separate agents, each assigned a distinct persona — such as your boss, an engineering partner, and a customer. Each agent reviews your work from a fresh context window with no shared bias, returning consolidated multi-perspective feedback before you present work to real stakeholders.
  • Scheduled Morning Debrief: Set a daily 7:30 AM scheduled task within your project that reads Gmail, Slack, and Google Calendar simultaneously, then outputs a prioritized action plan for the day. Because the task runs inside a project, it carries all connector permissions, skill context, and memory — producing a briefing specific to active workstreams rather than generic summaries.
  • Workspace Map Navigation: After populating a project folder with files, prompt Claude to generate a workspace map — a structured index of all folder contents. This allows Claude to navigate directly to relevant skills or documents when processing requests, reducing token consumption and preventing context bleed between unrelated materials stored in the same workspace.

What It Covers

JJ Englert from Tenex demonstrates how non-technical professionals can use Claude Cowork to build a personal daily operating system — connecting Gmail, Slack, and Calendar through one-click integrations, creating reusable skills, and orchestrating multiple AI agents simultaneously without writing a single line of code.

Key Questions Answered

  • Project Architecture: Create a dedicated folder on your computer, attach it to a Claude Cowork project, and add a "brain" file — a detailed markdown document containing your working preferences, team members, and communication style. Every subsequent task in that project inherits this context automatically, eliminating repetitive setup and producing more consistent outputs across sessions.
  • Email Style Cloning: Connect Gmail via Cowork's one-click connector, then prompt Claude to analyze your last 30 sent emails and generate a personal writing style guide saved to project memory. This produces AI-drafted emails that match your actual tone, stored as drafts for review before sending — never auto-sent without explicit approval.
  • Sub-Agent Review Panels: Build a reusable "sub advisory" skill that spins up three separate agents, each assigned a distinct persona — such as your boss, an engineering partner, and a customer. Each agent reviews your work from a fresh context window with no shared bias, returning consolidated multi-perspective feedback before you present work to real stakeholders.
  • Scheduled Morning Debrief: Set a daily 7:30 AM scheduled task within your project that reads Gmail, Slack, and Google Calendar simultaneously, then outputs a prioritized action plan for the day. Because the task runs inside a project, it carries all connector permissions, skill context, and memory — producing a briefing specific to active workstreams rather than generic summaries.
  • Workspace Map Navigation: After populating a project folder with files, prompt Claude to generate a workspace map — a structured index of all folder contents. This allows Claude to navigate directly to relevant skills or documents when processing requests, reducing token consumption and preventing context bleed between unrelated materials stored in the same workspace.

Notable Moment

JJ describes sending an AI agent to research a real colleague — their role, communication style, and likely objections — then using that agent to simulate the feedback that person would give before any actual meeting occurs, effectively pre-testing work against specific human reviewers.

Know someone who'd find this useful?

You just read a 3-minute summary of a 47-minute episode.

Get How I AI summarized like this every Monday — plus up to 2 more podcasts, free.

Pick Your Podcasts — Free

Keep Reading

More from How I AI

We summarize every new episode. Want them in your inbox?

Similar Episodes

Related episodes from other podcasts

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 up to 3 shows.

Start My Monday Digest

No credit card · Unsubscribe anytime