The Cowork operating layer.
Cowork is where the daily ops happen. Connectors talk to 12 categories of tools. 8 scheduled tasks fire while Vlad's away from the keyboard. This page is the public-safe version of that — task shapes, connector categories, service names — never workspace IDs, contacts, or account-level data.
Cowork's local app data contains live OAuth tokens, channel IDs, mentee names, deal names, customer emails, vault paths. Surfacing any of that is one screenshot from a leak. This page works backwards instead — it shows the shape of the setup, derived from Vlad's published chapters (Ch 7, Ch 12, Ch 24). Same teaching value, zero surface area.
A Cowork day, in shape
What fires when. Most of these run without Vlad opening Cowork. The Slack channel is the consumer.
- 6:30 AMMorning briefing fires→ Slack DM lands while coffee brews
- 7:30 AMPipeline ticker→ What moved overnight in the funnel
- 8:00 AMRead briefing on phone→ Decisions for the day, before tabs open
- ~30 min beforePre-meeting prep auto-runs→ Attendee context, open threads, agenda
- 5:00 PM ETDeal-advancement alerts→ Slack canvas to leadership channel
- 7:00 PMEnd-of-day vault sync→ Tomorrow's instance starts smart
- Friday 4 PMFriday wrap-up cross-system synthesis→ Saturday-morning canvas
- Monday 9 AMProcess-mining scan→ Candidate skills for next week
Connectors by category
Twelve categories. One source of truth per category. Read-only by default; write-access only where a workflow demands it. The S/A/B tags mirror the chapter 24 taxonomy.
- Filesystem S read-writeThe agent's hands. Without it, none of the rest matters.
- Google Drive A readRead-only first; expand only when the workflow needs write.
- Slack S read-writeRead everything; writes go through a confirmation step.
- Gmail / Outlook A readInbox = highest-ROI connector after filesystem.
- HubSpot A read-writeNo autoclose without human-in-the-loop.
- Stripe A readMRR motion, dispute trends. Read-only.
- GitHub S read-write
- Vercel B readBuild logs, deploys, runtime errors.
- Sentry B readErrors, stack traces, regression context.
- Postgres / Supabase A readWarehouse-shape SQL on demand.
- Ahrefs B readKeyword + backlink data inline.
- Google Search Console B read
- Customer.io B readPulling segments + campaign analytics through Claude.
- Klaviyo B read
- ElevenLabs A read-writeOutput voice — no second place.
- Whisper B readVoice-to-text. Solid. Mostly invisible.
- Google Calendar A readHalf the questions need calendar context.
- Fireflies B readPick ONE transcriber, not three.
- Granola B read
- Gong B read
- Notion A readRead-only at minimum for teams that live in Notion.
- Obsidian (community connector) A read-writeWhere the second brain lives.
- Playwright B read-writeLock down the agent's allowlist tightly.
Scheduled tasks
Cron expression on the left, task on the right. None of these names a deal, person, channel, or workspace. The shape is portable — copy any pattern, swap your own inputs, ship.
Calendar, overnight Slack, portfolio metrics. Lands as a Slack DM by the time the coffee is poured.
Overnight HubSpot motion + recent call notes — what advanced, what stalled, what went dark.
Stage changes since 5 PM yesterday. One paragraph each, "why this matters."
Reads what shipped today, writes back to the vault so tomorrow's instance starts smarter.
Cross-system synthesis — pipeline, revenue, SEO, leadership signal, Monday priorities.
Looks at last week's activity for repeating workflows that should become skills.
Codex-style — opens auto-PRs for non-trivial bugs. Reviewed like junior-engineer work.
Attendees, last interaction, open threads, suggested agenda. Walk into every call already loaded.
This page deliberately does not show: workspace IDs, OAuth scopes per integration, channel names, contact lists, deal pipelines, mentee names, account-level configurations, or any vault path beyond ~/Vault/. If the question is "which exact Slack channel does the morning briefing land in," the answer is "not on this page, by design." The book teaches the pattern; the pattern is enough.