How CloudyBot works

CloudyBot is built for execution, not chat. It opens a real cloud browser, edits your files line-by-line, runs scheduled Specialists while you sleep, and delivers results to WhatsApp, Slack, Notion, Sheets, GitHub, or your dashboard. This page explains every part — in plain English.

The 30-second tour

1. You describe the job in chat — or hire a pre-built Specialist (Scout, Watchdog, Analyst, Postmaster, Notion Reporter, Slack Poster, Power Analyst, Instagram Manager) in two clicks.
2. The Workflow Architect can design an entire AI team for you — named roles, duties, cron schedules, handoffs — from a single paragraph.
3. CloudyBot executes in a real cloud browser, with a persistent file workspace, web search, sandboxed code execution, and native integrations.
4. Results arrive where you are — WhatsApp, push notification, Slack channel, Notion page, Google Sheet, GitHub commit, email, or your dashboard.
5. Your bill stays predictable — every plan has a hard monthly cap on AI Tasks and browser minutes. When you hit zero, the service pauses. No overage charges, ever.

The core idea

Most AI tools require you to be present. You open them, type a prompt, wait, close them. Nothing happens when you are not there.

CloudyBot is designed around the opposite model. You describe what needs to happen. The AI plans the steps, executes them with real tools — a browser, your files, web search, external services — and delivers the result wherever you are. You can be in a meeting, on your phone, or asleep. The work happens anyway.

That shift — from "AI that responds" to "AI that executes" — is what every section below is built around.

The cloud browser

The most distinctive thing about CloudyBot is that your AI has a real browser. Not a text scraper. Not a simplified HTTP request. A real browser running in the cloud that navigates actual websites the same way a human would — logging in, clicking buttons, filling forms, scrolling dynamic content, extracting data that would be invisible to a basic scraper.

When you ask CloudyBot to research five competitors, it actually opens their websites. When you ask it to find a LinkedIn profile, it actually navigates LinkedIn. When a scheduled Specialist monitors a competitor's pricing page every morning, it actually loads that page and reads it — comparing against what it saw yesterday and telling you only what changed.

The browser is paired with residential IPs (on plans that need them) so it is not blocked by sites that detect automated traffic. Each session is fully isolated — your cookies, login state, and data are completely separate from any other user's session. Sessions are ephemeral by default: when the session ends, all state is cleared unless you have explicitly saved it to your workspace.

You can watch the browser work live in your dashboard. The live view streams in real time — every page, every click, every form. If something looks wrong or the AI hits a captcha it cannot handle alone, you can take over the browser directly and hand control back when you are done.

Pre-built Specialists you can hire today

Specialists are AI workers you deploy once. They run automatically on a schedule you set — hourly, daily, weekly, or any custom cron — whether your device is on or not. Each Specialist has a defined role, scheduled duties, the tools it needs (browser, web search, files, integrations), and a delivery destination. Hire any of these from the dashboard in seconds:

• 🔭 Scout — competitor & web monitoring. Watches the URLs and products you care about, surfaces only what changed since the last run.
• 🐕 Watchdog — site & page change detection. Compares against a saved baseline and alerts you when something meaningful differs — not on every minor variation.
• 📊 Analyst — weekly data analysis & reporting. Pulls structured data, builds versioned reports, highlights deltas vs the previous period.
• 📬 Postmaster — daily inbox digest, urgent flags, draft replies. Works through the browser (Gmail, Outlook, any webmail — just log in once) or via the AgentMail API if you prefer programmatic access.
• 📓 Notion Reporter — structured research saved straight to your Notion workspace each scheduled run, using your own API key.
• 💬 Slack Poster — scheduled digests posted to your Slack channel via webhook or bot token.
• 🧠 Power Analyst (Pro+) — deep multi-source weekly research with code execution and a growing knowledge base in your workspace.
• 📸 Instagram Manager — three-duty content pipeline (Strategist → Creative → Publisher) running on the same shared thread, with a persistent browser login.

Beyond pre-builts, you can define custom Specialists with any duties your business needs. Any repeatable job that happens the same way every day or week is a candidate.

The Workflow Architect

Building a team requires decisions: which roles, what duties, what schedule, where to deliver, how Specialists hand work to each other. The Workflow Architect handles all of it.

It is a Specialist whose job is to understand your business, design the right team of AI workers, and deploy them — all through a plain-English conversation. You describe what needs to happen each week. It proposes a team with named roles, defined duties, and cron schedules. You review each Specialist, adjust anything, and deploy. Your first Specialist can be running within fifteen minutes of starting the conversation.

Multi-agent pipelines

Specialists hand work to each other automatically. A research Specialist finishes and triggers an analysis Specialist, which triggers a reporting Specialist, which posts to your Slack channel. Each picks up where the last one left off through shared workspace files.

The whole chain runs on the schedule you set once. No one needs to initiate each step. Every run adds to a shared knowledge base — so the team gets smarter over time, not noisier.

File workspace & surgical edits

Every CloudyBot account has a persistent file workspace in the cloud. Documents, spreadsheets, CSVs, PDFs you upload stay across sessions and accumulate into a knowledge base over time. Research Scout saved last month is available to Analyst this month when it produces its report.

The AI edits files surgically — changing only the lines that need changing rather than rewriting entire documents. This matters for your monthly task budget: editing three sentences in a 200-page document should not cost the same as summarising the whole thing. With surgical editing, it does not.

Storage scales with your plan: 50 MB (Free) → 1 GB (Growth) → 2 GB (Pro) → 5 GB (Max). Files stay private to your account and are never used for model training.

GitHub & sandboxed code execution

Connect a GitHub account and CloudyBot can clone repos into your private workspace, read code, edit files line-by-line, run shell commands, execute Python or Node, and push commits — all from a chat thread or a scheduled Specialist. Code runs in a sandboxed Daytona environment that is fully isolated from your machine and your other workspaces.

Three-layer memory

Context window limits are the reason most AI tools forget things. Long conversations, large files, and complex tasks push against the limit constantly. CloudyBot uses a three-layer system to solve this without you managing it:

Layer 1 — Active context

The current conversation, the last several messages, and any files or tool outputs from the current session — full fidelity, immediate recall.

Layer 2 — Rolling summary

As a conversation grows, older messages are progressively compressed into a rolling summary. Key facts and context survive without keeping every message verbatim, keeping token costs manageable across long sessions.

Layer 3 — Pinned memory

Facts you explicitly tell the AI to remember permanently — your name, your business, your preferences, your projects. Injected into every interaction so the AI always knows the context that matters most.

Scheduled Specialists also have their own memory of previous runs. When Scout checks a competitor on Wednesday, it compares against what it found on Tuesday and tells you the delta — not a full re-summary every time.

WhatsApp & mobile delivery

CloudyBot reaches you rather than waiting for you to check in. On paid plans, Specialists deliver results directly to WhatsApp — same AI, same threads, same workspace, accessible from your phone like a contact in your address book. Proactive sends scale from 100/month on Growth → 200 on Pro → 500 on Max.

The dashboard installs as a PWA on iOS, Android, and Windows — full workspace, same files, same Specialists, same threads as the web version. Push notifications fire when scheduled jobs finish so you know when work is ready without checking.

Integrations

Specialists deliver to and read data from the services your team already uses. Native integrations include:

• WhatsApp & Telegram — chat with CloudyBot from your phone
• Slack — post digests to channels via bot token or webhook
• Notion — append to pages and databases with your API key
• Google Sheets — read and write structured data via service account
• GitHub — OAuth, clone repos, edit files, commit changes
• AgentMail — fast programmatic email reading for Postmaster
• Stripe — payment event triggers
• Zapier & Make — connect to thousands of other tools via webhooks

These are native — the Specialist calls each service directly rather than driving the browser through its UI. That means faster, more reliable delivery and less browser usage for integration tasks.

Hard billing caps & AI Tasks

Every CloudyBot plan has a hard monthly cap on AI Tasks and browser minutes. When you hit the cap, the service pauses. It does not charge you more. It does not silently keep metering. It pauses, shows you a clear message, and gives you the option to upgrade, buy a top-up pack, or wait for the next billing cycle.

AI Tasks are the billing unit — a whole number you can reason about. 1 AI Task ≈ one message on the standard model. Premium models use multipliers, shown in the model picker before you commit:

• DeepSeek (default) — 1×
• GPT-4o mini — 1.5×
• Kimi K2.5 — 6.5×
• Claude Haiku 4.5 — 10×
• GPT-4o — 25.5×
• GPT-5.4 — 28×
• Claude Sonnet 4.6 — 30.5×
• Claude Opus 4 — 153.5× (Pro+)

Plans run from Free (30 tasks, no card) → Growth $19 (1,500 tasks, 750 browser minutes, 100 WhatsApp sends) → Pro $39 (3,000 tasks, 1,500 browser minutes, 200 WhatsApp sends) → Max $149 (7,000 tasks, 3,500 browser minutes, 500 WhatsApp sends, priority queue). Running low mid-month? Top up your task wallet — extra tasks never expire. Your maximum monthly spend is always knowable before the month starts. Paid plans include a 7-day free trial with Pro-level limits.

Privacy & data

CloudyBot does not train AI models on your data. Your conversations, files, and browser sessions are private to your account. We use your data only to provide the service — never to train anything or share with third parties beyond the subprocessors listed on our subprocessors page.

Each browser session is isolated. Sessions are ephemeral by default: nothing persists between sessions unless you explicitly save it to your workspace. See Security and Trust & Safety for the full picture.

Frequently asked questions