> ## Documentation Index > Fetch the complete documentation index at: https://docs.adsmcp.si/llms.txt > Use this file to discover all available pages before exploring further. # Automate Ad Ops with Scheduled Tasks > Run your ADSMCP project on a schedule — a Monday scorecard, a mid-month pacing check, an alert when CPA drifts. What each assistant calls scheduling, how to write a recurring-task prompt that behaves, and what a cadence costs. Once your [project is set up](https://docs.adsmcp.si/guides/set-up-your-project.md), the real payoff is automation: the same agent, run unattended on a cadence. A Monday performance scorecard. A mid-month pacing check. An alert the moment a campaign's CPA drifts past your target. You wake up to the answer instead of remembering to ask. ## What your assistant calls it Every client has this feature — the name and the reliability differ. | Assistant | Feature | Runs when your computer is off? | | - | - | - | | **ChatGPT** | Scheduled tasks | Yes — cloud-run, notifies by push + email | | **Codex** | Scheduled tasks (automations) | Yes | | **Claude Cowork** | Scheduled tasks, via the `/schedule` skill | Yes — they run remotely | | **Claude Code** | Routines: a *local* task **or** a *remote* routine | Local: **no**. Remote: yes | On most hosts you create one just by asking — *"every Monday at 9am, review my campaigns and post the three things worth my attention."* No UI hunting required. > [!WARNING] > > **The one that bites: a Claude Code *local* scheduled task only runs while the desktop app is open > and your computer is awake.** A laptop asleep at 9am silently skips the run (on wake it starts one > catch-up for the most recently missed time and discards the rest). For anything that matters — > budget pacing, spend spikes, disapprovals — create a **remote routine** instead: it runs on > Anthropic's infrastructure with the machine off. Cowork and ChatGPT scheduled tasks don't have > this problem. Codex **hooks** (`SessionStart`, `PostToolUse`, …) are event handlers, not a scheduler — never use one for a recurring report. ## Write a recurring prompt that behaves A scheduled prompt is different from a chat message: no one is there to answer a follow-up, and it may fire hours late. Write for that. > **Describe the result, not the steps** > > Say what you want to arrive — "a scorecard with spend, conversions, CPA, ROAS, and the three > things worth my attention" — and let the agent plan the tool calls. > **Goal · Context · Output · Boundaries** > > The four parts of a good work prompt: what to do, what to look at, the format and length, and > what must stay unchanged. > **Add a late-run guardrail** > > A 9am task might fire at 11pm after a sleep. Add: *"Only look at today's spend; if it's past > 6pm, just summarize what changed."* > **Refine first, then schedule** > > Get the prompt producing a reliable result in a normal chat, then turn that into the scheduled > version. Don't schedule a prompt you haven't seen run. Keep it read-only unless you mean otherwise. A scheduled run that changes budgets or status spends real money with no one watching — say **"propose, don't change"** unless you've built the full [safety model](https://docs.adsmcp.si/guides/claude-cowork-ad-ops.md) for unattended writes. ## What a schedule costs Every scheduled run re-runs the work, which means it calls ADSMCP tools again — each run draws on your monthly tool-call quota exactly like a live conversation. A **daily** review costs roughly thirty times a monthly one. Pick a cadence your plan can carry, and say what it should watch. **Weekly is the right default for a review; daily is for accounts spending enough to justify it.** Checking your usage is free — ask "what's my usage this month?" any time. ## Example task prompts > **Weekly performance scorecard (read-only)** > > ```text theme={"theme":{"light":"github-light","dark":"github-dark"}} theme={null} > Every Monday at 9am, pull a cross-channel scorecard for my accounts — trailing 7d and 30d spend, > conversions, CPA, and ROAS per campaign — and post the three things worth my attention this week. > Read-only: propose changes, don't make any. If it runs late in the day, just summarize what > changed; don't start fresh analysis. > ``` > **Mid-month pacing check** > > ```text theme={"theme":{"light":"github-light","dark":"github-dark"}} theme={null} > On the 15th, check month-to-date spend against my monthly budgets. For each budget pool, tell me: > projected end-of-month spend at the current pace, and whether I'm on track, under, or over. Flag > any campaign pacing to blow its cap. Don't change any budgets — just report. > ``` > **CPA alert (a monitoring task)** > > ```text theme={"theme":{"light":"github-light","dark":"github-dark"}} theme={null} > Check my account once a day. If any campaign's CPA rises above my target, or spend pace projects > over budget for the month, tell me which campaign and by how much. Otherwise stay silent. Never > change budgets or status — only alert. > ``` > > A monitoring task re-checks and stays quiet until there's something worth saying — the right shape > for "tell me if my CPA moves." > **Competitor landing-page watch** > > ```text theme={"theme":{"light":"github-light","dark":"github-dark"}} theme={null} > Every Monday, check for changes to their offer, pricing, or hero message, and > tell me what's different from last week. Summary only. > ``` ## Going further: unattended optimization The examples above only *read* and *propose*. To let a scheduled task actually **write** changes — reallocate budget, pause dead campaigns — you need the full safety model: shadow mode, per-run change caps, one writer per portfolio, propose-vs-act, and a kill switch. That's covered in depth here: > **[Cowork for Ad Ops](https://docs.adsmcp.si/guides/claude-cowork-ad-ops.md)** > > The seven-property safety model for a self-optimizing task you can trust. > **[Set up your project](https://docs.adsmcp.si/guides/set-up-your-project.md)** > > Instructions, context, memory, and connectors — the foundation a schedule runs on. This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.