Skip to main content
WORKSHOPS & DEMOS

Live Sessions

Hands-on workshops and demos focused on practical AI transformation outcomes.

Recorded

Past Sessions

Catch up on every workshop, demo, and live build. Hands-on AI transformation content you can rewatch any time.

Claude Cowork Scheduled Tasks: Automate What You Repeat
Session 15 | Jun 3, 2026

Claude Cowork Scheduled Tasks: Automate What You Repeat

In this live session, Tim Cakir (Founder, AI Operator) shows how to turn the work you repeat into workflows that run on autopilot using Claude Cowork scheduled tasks. The goal isn’t more AI usage. It’s less manual work on the tasks you repeat every day and every week — describe a task once, set a cadence, and let Cowork run it while you focus on strategy, sales, and product. We covered: - What Claude Cowork is (the agentic “get it done” mode in the Claude desktop app) and how it differs from Claude Chat (“chat”) and Claude Code (“build”) - How scheduled tasks work: describe a task once, pick a cadence (daily, weekly, weekdays, hourly, or on demand) — no cron syntax, no YAML, fully GUI - Working in a safe, dedicated folder so Cowork doesn’t “run wild,” and why you’re always the human in the loop (Claude asks before it acts) - Using connectors (Gmail, Calendar, Drive, Notion, Slack, Mercury) and Claude-in-Chrome to pull data from tools that don’t have an API or MCP (Google Analytics, Search Console, LinkedIn) - Choosing the right model: plan with the best model (Opus) and let a faster, cheaper one (Sonnet, Haiku) do the execution - Using Projects to give a workflow persistent instructions, memory, and its own folder so scheduled tasks run with the right context Live demo highlights: - We built a week-over-week marketing analysis (Google Analytics + Search Console) using Claude-in-Chrome, then turned it into a scheduled task that emails the results every Friday - We set up a daily weekday morning brief that pulls from Gmail, Calendar, Notion tasks, and Slack - We created a “Marketing Insights” project with role instructions, scheduled tasks, a context folder, and memory - We built a live marketing dashboard that auto-created a Notion database to store weekly snapshots and feed the dashboard Main takeaways: - The shift is from reactive prompting to autonomous execution: describe once → schedule → review → refine → scale. - Start with one high-value recurring task, match the cadence to how fast the info changes, and spot-check the outputs. - You don’t need an API for everything — Claude-in-Chrome lets Cowork act in your browser on tools like Analytics and LinkedIn. - The goal is not more AI usage. It’s less manual work on the things you repeat.

Tim Cakir Tim Cakir
Watch
Claude Code for Founders: Ship an Internal Tool in 60 Minutes — Live Build
Session 14 | May 13, 2026

Claude Code for Founders: Ship an Internal Tool in 60 Minutes — Live Build

In this build-in-public session, Tim Cakir (Founder, AI Operator) goes live with Claude Code and ships a real internal tool end-to-end in under an hour. The goal isn't "coding for coders." It's showing founders and operators how to turn a messy idea into a working system fast, using Claude Code as a thinking + building partner. What we covered 👇 🛡️ How to set up a safe build environment (working in a dedicated folder so Claude Code doesn't "run wild" in sensitive directories) 🖥️ Using Claude Code inside a terminal (Warp) and why the terminal is where you get the most leverage from AI ❔ How Claude Code works best: it asks clarifying questions instead of guessing, so you can steer architecture and scope 🧠 Designing a context layer / operating system that ingests business signals (calls, emails, Slack, Notion, meeting notes) and turns them into usable outputs 🚢 The difference between "AI that talks" vs "AI that ships": how to push Claude Code to build faster by tightening scope and time constraints 📘 Creating and using CLAUDE.md as a "map" that points Claude to key docs, conventions, and where the real context lives Live build highlights 🎬 🧱 We scaffolded a "Context OS" concept: ingest → unify → extract entities/insights → present in a simple UI 🚀 We shipped a quick demo front end to make the concept tangible (seed data, early dashboard) 🔌 We discussed how this becomes powerful once connected to real sources via MCPs (Slack/Gmail/Notion/meeting notes, etc.) Main takeaways ✨ 🎯 The biggest unlock is context. AI becomes dramatically more useful when it can reference your real work (emails, calls, docs, tasks), not just generic prompts. 🛠️ Claude Code is not just for engineers: with the right guardrails and workflow, it's a practical build tool for founders. 📈 Start small, ship something usable, then iterate — your context layer compounds over time.

Tim Cakir Tim Cakir
Watch

Want a session for your team?

We run workshops and training sessions for teams of all sizes. Tell us what you need.