> ## Documentation Index
> Fetch the complete documentation index at: https://docs.boostgpt.co/llms.txt
> Use this file to discover all available pages before exploring further.
# Tasks
> Work your agent proposes, and work it runs on a schedule
## What Tasks are
Tasks turn your agent from a passive chatbot into something that keeps working when you close the
tab. Two kinds share one board:
* **Schedules** run on their own — a weekly site review, an hourly inbox check. They repeat.
* **Cards** are single pieces of work. Your agent files them when it finds something worth doing;
you decide what actually happens.
**The agent proposes. You decide.** A schedule can file as many cards as it likes, and none of them
run until you move one. That boundary is the whole design — see [Autonomy](#autonomy) below.
## Availability
Tasks are available from **Free** and there is no task-count ceiling. Message credits and rate
limits govern the work tasks run, rather than the number of cards or schedules you can keep.
Accounts with no plan cannot create or run Tasks.
## The board
Five columns, and work moves left to right:
| Column | What it means |
| --------------- | ------------------------------------------------------------------- |
| **Backlog** | Ideas and requests, waiting to be picked up. Your agent files here. |
| **Todo** | Scoped and ready — you have decided it should happen. |
| **In Progress** | An agent is working on it now, in your builder conversation. |
| **Review** | Paused for you: it needs approval, asked a question, or failed. |
| **Done** | Finished, with the full trail of what happened. |
Drag a card to move it. Above the board, a **Schedules** strip lists the recurring runs — they have
no column because they never finish.
## Autonomy
How much your agent may do without you, set per Site and overridable per task:
| Rung | What it does |
| ------------- | ---------------------------------------------------------------- |
| **Suggest** | Files cards to Backlog. Never runs anything itself. |
| **Prepare** | Runs when you move it, edits the working copy, stops for review. |
| **Execute** | Runs cards you move to Todo. It never picks its own. |
| **Autopilot** | Picks up cards from **Todo** by itself and runs them. |
Autopilot moves cards out of **Todo**, never out of **Backlog**. So "let it run things by itself"
never means "let it run things I have not read".
Publishing is always yours. No autonomy rung lets an agent put changes live.
## Site reviews
Every Site gets one review schedule. It reads your pages, screenshots them, checks what visitors
have been asking, and files what is worth improving — with its reasons.
It changes nothing on its own.
The visitor half is the part only your agent can do. Anyone can tell you a page needs a clearer
call to action; only your agent knows that six people asked what something costs and there is no
pricing page.
Choose the cadence in **Site builder → Settings → Reviews & autonomy**. Unavailable cadences stay
visible with the plan that unlocks them.
| Plan | Available review cadences | New Site default |
| ------------------- | ----------------------------------- | ---------------- |
| Free | Off, Monthly | Monthly |
| Pioneer / Hobby | Off, Monthly, Weekly | Weekly |
| Starter | Off, Monthly, Weekly, Daily | Weekly |
| Pro / Prime / Scale | Off, Monthly, Weekly, Daily, Hourly | Weekly |
Hourly is a rolling 60-minute interval. Calendar cadences run at their configured calendar time.
After a downgrade, a cadence the new plan does not include is changed to the fastest cadence that
plan permits.
## Creating your own
Ask in the builder conversation — "check my inbox every morning at 9" — or use the schedule control
in the composer. Recurring tasks appear in the Schedules strip; one-off ones land on the board.
### Configuration
| Setting | Description |
| ------------------ | -------------------------------------------------- |
| **Prompt** | What the agent does on each run |
| **Schedule** | Interval, daily, weekly, cron, or a single time |
| **Timezone** | Timezone for scheduling |
| **Active hours** | Optional window outside which runs are skipped |
| **Max executions** | Optional cap, after which the task disables itself |
### Plan limits
Free and every paid plan include unlimited Tasks. Each accepted attachment used by a Task or chat
costs two ordinary message credits, and task executions consume the same credits and rate limits
as other Agent work.
## Runs and history
Below the board:
* **Run history** — every run with status, duration and tokens used
* **Activity chart** — execution volume over time
* **Stats** — success rate, total executions, active schedules
A run that was **skipped** records why — outside active hours, disabled, or sitting in a column that
does not run. That is the answer to "why didn't my task run last Tuesday?", and it is the reason
run history exists separately from the conversation.
Successful runs happen in your builder conversation, so the full exchange is there to read.
## Safety
* **Circuit breaker** — five consecutive failures (configurable) pauses a task rather than letting
it fail forever
* **Plan and credit gate** — Tasks stop when the plan is inactive or the account cannot fund a run
* **State guard** — a card only runs while it is In Progress, so a Backlog card cannot fire
* **Publishing** — never automatic, at any autonomy rung
## Best practices
* Let Site reviews fill your Backlog before creating tasks by hand
* Read the agent's reason on a card before promoting it; that is what it is for
* Start at Suggest, move a Site to Autopilot once you trust what it files
* Check Review first — it is the only column that needs you
## Next steps
Connect tools for your agent to use
Where Site reviews do their work