Skip to main content
Beta: Automations is in early access. Functionality will continue to improve.

​
What is an Automation?

An Automation is a scheduled prompt that runs inside a Project. It can use the Project’s files, session context, and instructions, then save or send the result. Automations are useful when the work is repeatable, has a clear schedule, and produces an output you can review.

​
When to use Automations

Use Automations for recurring work with clear inputs and a repeatable output:
  • Daily or weekly summaries
  • Project status reports
  • Scheduled file processing
  • Recurring research or monitoring
  • Periodic GitHub, Notion, or email checks
  • Work that should continue while you are away
Automations work best when the prompt explains the goal, source material, output format, and what to do if there is nothing new.

​
Create an Automation

You can create an Automation from the sidebar. You can also ask Happycapy to create one from a Project conversation.
AutomationsSchedule recurring work in a Project.
Create Automation dialog
To use the sidebar, click Automations, then Create Automation. In a Project conversation, describe what should run and when:
Fill in:
  • Name — a short label, such as “Morning summary”
  • Project — the Project where the Automation should run
  • Session binding — the main session or a session inside that Project
  • Schedule — daily at a specific time, or on an interval
  • Prompt — the instruction Happycapy will run
  • Run immediately — run once now in addition to the schedule
Click Create to save it.

​
What each field means

  • Project keeps the Automation tied to the right workspace and files.
  • Session binding decides which session context the prompt should continue from.
  • Schedule controls when the Automation runs.
  • Prompt is the instruction Happycapy executes each time.
  • Run immediately lets you test the prompt once before relying on the schedule.

​
Write a reliable prompt

Automations run without you typing the prompt again, so the prompt should be self-contained.
  • State the goal and output format.
  • Mention the source files, folders, or services to check.
  • Tell Happycapy where to save or send the result.
  • Include fallback behavior, such as “If there is nothing new, write a short no-update note.”

​
Examples

​
Morning brief

​
Project status report

​
GitHub review check

​
File processing

The prompt runs like a normal message in a session. Anything you can do manually in a Project can usually become an Automation when the steps are repeatable.