https://claude-advanced.manuelqg.people.aws.dev/en/03-sesion-2/index.html Session 2 · Automate with Governance Info ⏱ Duration: ~2 h (120 min core + optional block) · 🎯 Goal: leave an automated, governed AI operation running —scheduled tasks, permission modes, and Dispatch— with a written mode policy for your team. · 📅 Week 2 of 4. Tip Cohort assumptions: this workshop assumes a Team/Enterprise plan. Blocks marked 🎥 Instructor demo (like Dispatch, Pro/Max only) are demonstrations, not hands-on. Confirm your plan in Settings before the session. Week 2 of 4. Last week you standardized your team with skills and plugins. Today you scale the next link: automate with governance. You’ll stop running every task yourself and put Cowork to work on a cadence —but with clear rules about who approves what. Hugo en-US https://claude-advanced.manuelqg.people.aws.dev/en/03-sesion-2/01-tareas-programadas-a-fondo/index.html Mon, 01 Jan 0001 00:00:00 +0000 https://claude-advanced.manuelqg.people.aws.dev/en/03-sesion-2/01-tareas-programadas-a-fondo/index.html Info ⏱ Duration: ~35 min · 🎯 Goal: schedule a weekly Elektra KPI report and run it once on-demand, understanding what runs remotely and what runs locally. Your division produces the same KPI report every Monday. Instead of building it by hand, today you delegate it to Cowork on a cadence: describe it once and it runs on its own. Scheduled tasks let you delegate recurring or on-demand work, and each runs as its own Cowork session with access to your connectors, skills, and plugins. https://claude-advanced.manuelqg.people.aws.dev/en/03-sesion-2/02-modos-y-gobernanza/index.html Mon, 01 Jan 0001 00:00:00 +0000 https://claude-advanced.manuelqg.people.aws.dev/en/03-sesion-2/02-modos-y-gobernanza/index.html Info ⏱ Duration: ~45 min · 🎯 Goal: read the Manual/Auto/Skip matrix against each connector’s permission and draft your team’s mode policy. Automating without governance is a risk. Before leaving tasks running on their own, your team needs clear rules about who approves what. There are three modes, switchable anytime from the selector in the message box, and their behavior depends on each connector’s permission. https://claude-advanced.manuelqg.people.aws.dev/en/03-sesion-2/03-dispatch/index.html Mon, 01 Jan 0001 00:00:00 +0000 https://claude-advanced.manuelqg.people.aws.dev/en/03-sesion-2/03-dispatch/index.html Info ⏱ Duration: ~15 min (🎥 instructor demo) · 🎯 Goal: understand what Dispatch is, how to set it up, and why its phone→desktop chain demands extra governance. Info Pro/Max only (beta): Dispatch is in beta for Pro and Max plans only —not Team or Enterprise. Since this cohort is assumed Team/Enterprise, this section is an instructor demo (not hands-on). A director is rarely at their computer. Dispatch solves that: you message Claude from your phone and it works on your desktop —with your local files, connectors, plugins, and apps— and returns the finished work. https://claude-advanced.manuelqg.people.aws.dev/en/03-sesion-2/04-sub-agentes/index.html Mon, 01 Jan 0001 00:00:00 +0000 https://claude-advanced.manuelqg.people.aws.dev/en/03-sesion-2/04-sub-agentes/index.html Info ⏱ Duration: ~10 min (informational) · 🎯 Goal: understand that sub-agents are native coordination Claude decides on, not something you launch manually. Scaling doesn’t mean you orchestrate more pieces: it means Claude coordinates the work for you. When a task is complex, Cowork breaks it down and works several streams in parallel —without you launching anything. Info Reconciling with the basic track: in the basic workshop you modeled a “board of advisors” as a prompting technique —you wrote each voice in the message. Native sub-agents are different: Claude coordinates them on its own, decides when to fan work out, and runs them in parallel, without you writing or launching them. Native coordination Verbatim: “Claude breaks complex work into smaller tasks and coordinates parallel workstreams to complete them.” During a task, “for complex tasks, Claude may coordinate multiple sub-agents working simultaneously.” https://claude-advanced.manuelqg.people.aws.dev/en/03-sesion-2/05-cierre-sesion-2/index.html Mon, 01 Jan 0001 00:00:00 +0000 https://claude-advanced.manuelqg.people.aws.dev/en/03-sesion-2/05-cierre-sesion-2/index.html Info ⏱ Duration: ~15 min · 🎯 Goal: close the session checkpoint and set the bridge task toward Session 3 (Claude Code). Today you moved from running every task to governing an automated operation: you left a live scheduled task, wrote your team’s mode policy, and understood Dispatch and native sub-agent coordination. Automation without governance is risk; you left it with rules. Step 1 — Close the session checkpoint Confirm you have all of this: https://claude-advanced.manuelqg.people.aws.dev/en/03-sesion-2/06-si-hay-tiempo/index.html Mon, 01 Jan 0001 00:00:00 +0000 https://claude-advanced.manuelqg.people.aws.dev/en/03-sesion-2/06-si-hay-tiempo/index.html Info ⏱ Duration: ~15 min (optional block) · 🎯 Goal: understand where Claude’s memory lives —and where it does NOT— so you govern automation without assuming context that isn’t there. When you automate, it’s easy to assume Claude “remembers everything.” It doesn’t: memory has clear boundaries, and confusing them is a silent source of errors in scheduled tasks and governed workflows. The three boundaries Chat does NOT carry into Cowork. What Claude “knows” from your chat conversations does not transfer to Cowork. A Cowork task starts without that context. In Cowork, memory lives only in Projects. Within Cowork, persistent context across tasks is stored in a Project: the Project’s files, instructions, and knowledge are the shared memory. Outside a Project, each task starts cold. Dispatch adds cross-session memory (Pro/Max only). Dispatch’s single thread retains context from one task to the next —cross-session memory— but this is a Pro/Max-only capability, not Team/Enterprise. Tip Governance implication: if your scheduled task needs context (a policy, a glossary, baseline data), don’t trust Claude to “remember it”: put it in the Project where the task runs, or attach it in the prompt. Memory that isn’t in the Project doesn’t exist for that run. ✅ Checkpoint You can explain that chat does not share memory with Cowork, that in Cowork persistent memory lives in Projects, and that Dispatch’s cross-session memory is Pro/Max only. You know where to place the context a scheduled task needs.