Jj Englert

AI Summary

→ 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 INSIGHTS - **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. 💼 SPONSORS [{"name": "Tines", "url": "https://tines.com/howiai"}, {"name": "Cursor", "url": "https://chatprd.ai/howiai"}] 🏷️ Claude Cowork, AI Workflow Automation, Multi-Agent Systems, Personal Productivity, No-Code AI Tools