---
title: "Automate Recurring Monetization Work with Tasks"
description: "CloudX Agent can now run monetization checks on a schedule. Describe a task once, pick when it runs, and get the results in chat or by email."
url: "https://www.cloudx.ai/posts/introducing-tasks"
published: "2026-09-24T17:00:00+02:00"
authors:
  - "Sanja Zakovska"
category: "Product Updates"
---

# Automate Recurring Monetization Work with Tasks

Recurring monetization work that CloudX Agent runs for you.

*By Sanja Zakovska · Published Sep 24, 2026*

[Video](https://www.cloudx.ai/videos/cloudx-agent-tasks-sizzle.mp4)

Monday morning at most publishers starts the same way. Someone opens the dashboard to find out what happened to revenue over the weekend, and then spends the next hour working out why. Later in the week someone else on their team will look at floors against clearing prices and nudge the ones that drifted. They'll check whether the A/B test that started ten days ago has finished.

None of this is hard. All of it is recurring, and all of it depends on a person remembering to look. In most publishing teams that person is also the one shipping the next update, so the checks happen when there's time, which means they happen less often than they should.

Since we launched CloudX Agent, publishers have been using it for exactly this kind of work. The prompts publishers reuse most are the ones they'd rather not type again. So we made them recurring.

**Today we're launching Tasks, a way for CloudX Agent to take on the work that has to happen on a schedule.**

Describe the task once, pick when the task runs, and choose where the results go. Each run, the agent works from your live auction data, line items, floors, and experiments, decides what's worth telling you, and sends it to the in-app chat or by email.

## How Tasks work

**Describe the job.** Write it the way you'd ask the agent in chat. "Summarize last week's revenue, fill and eCPM by app. Flag anything that moved more than 10% and explain why."

**Pick when it runs.** Daily, weekly, monthly, at a time and timezone you choose. Or start from one of the templates (weekly report, daily health check, A/B test analyzer, total revenue analysis) and edit from there.

![The CloudX Agent task editor, showing a Total Revenue Analysis template scheduled to run daily, set to private access, with in-app notification delivery enabled](https://jwdpljtafm8phaor.public.blob.vercel-storage.com/setup-panel.png)

**Choose who can see it.** New tasks are private by default, visible only to you. Share one with your organization when you are ready, and every member gets access to the task, its run history, and its notifications. Any organization Editor can edit it, and each person controls their own email alerts, so anyone can turn them off entirely and stick to the in-app feed.

**Only hear about what matters.** By default, CloudX Agent decides for itself whether a run is worth flagging, so recurring checks don't fill your inbox when there are no noteworthy updates. Prefer to hear from every run instead? Turn off Smart Notifications on any task and you'll get an alert every time the agent runs the task.

**Review at any time.** Every task run is logged. You can open any run, see what the agent looked at and what it concluded, and continue the conversation from there.

![Run history for a Total Revenue Analysis task, listing recent scheduled runs with the revenue and eCPM changes the agent flagged for each](https://jwdpljtafm8phaor.public.blob.vercel-storage.com/run-history.png)

## From Claude Code and the CLI

Tasks for CloudX Agent are also available through the CloudX MCP server and the [CLI](https://docs.cloudx.io/en/cli/tasks). If you already manage inventory from Codex, Claude Code, or a terminal, you can create and manage tasks from there too.

```bash
cloudx tasks create \
  --name "Weekly revenue review" \
  --prompt "Review weekly revenue and flag material changes" \
  --schedule "0 9 * * 1" \
  --timezone Europe/Madrid \
  --access workspace
```

## Tasks publishers are automating

Here are some of the favorite tasks publishers have been automating.

### Weekly CloudX revenue review

Reviews weekly CloudX revenue and its biggest changes.

```text
Prepare the workspace's weekly CloudX revenue review for the last complete Monday-through-Sunday period. Compare it with the preceding complete week.

Use CloudX reporting data. Report revenue, requests, impressions, fill rate, eCPM, clicks, and CTR. Quantify the absolute and percentage change for the measures that support both. Break down the largest revenue and delivery movements by the most useful available dimensions, such as app, ad unit, country, device OS, and demand source.

Lead with a short executive summary. Then cover the main gains, declines, anomalies, and likely drivers. Separate observed facts from interpretations. Note material data gaps or coverage limits. End with up to three concrete follow-up actions.
```

[Use template](https://app.cloudx.io/tasks?template=weekly_performance_report) · [View in the task library](https://www.cloudx.ai/task-library/weekly_performance_report)

### Fill-rate monitor

Flags material fill-rate declines across key segments.

```text
Check fill rate for the latest complete reporting day. Compare it with the same weekday one week earlier. Use the preceding seven complete days to establish the normal range.

Review requests and impressions with fill rate so traffic-mix changes do not create a false alert. Find the main contributors by app, ad unit, country, device OS, and demand source. Give priority to sustained declines on meaningful request volume. Ignore small segments that do not affect workspace delivery or revenue.

For each material decline, report the baseline and current fill rate, percentage-point change, request volume, affected scope, likely start time, related revenue impact, and next diagnostic step. If fill rate is healthy, record the workspace result and the largest non-material movement.
```

[Use template](https://app.cloudx.io/tasks?template=fill_rate_monitor) · [View in the task library](https://www.cloudx.ai/task-library/fill_rate_monitor)

### A/B test reviewer

Reviews active experiments and flags results that are ready for a decision.

```text
Review every active A/B test in this workspace.

First, inspect the live inventory to find the active tests. For each test, load its report from the test start through the latest complete reporting day. Compare the control and test variants across revenue, eCPM, fill rate, impressions, requests, sample size, lift, confidence interval, and significance.

Classify each test as one of these states:
- Keep running: the result is not decision-ready.
- Review now: the result is decision-ready or the test status is achieved.
- Investigate: the data is invalidated, traffic is badly imbalanced, or a material guardrail metric has deteriorated.

Write a compact review. Lead with tests that need action. Include the evidence behind each classification and a clear next step. Do not recommend a winner when the data is not decision-ready. If no tests need action, state that briefly.
```

[Use template](https://app.cloudx.io/tasks?template=ab_test_reviewer) · [View in the task library](https://www.cloudx.ai/task-library/ab_test_reviewer)

You can find more examples in the [task library](https://www.cloudx.ai/task-library), or pick one of the templates when setting up a new task in the CloudX dashboard.

## Getting started

Tasks are available today in limited free preview. Open CloudX Agent, pick [**Tasks**](https://app.cloudx.io/tasks) in the sidebar, and start from a template or a blank prompt.

Docs: [docs.cloudx.io](https://docs.cloudx.io/en/dashboard/agent-tasks). Questions and requests: [hello@cloudx.io](mailto:hello@cloudx.io).