Guides
Get your first agent working.
The basics track, in the order you meet them: run an agent, put it on a trigger, give it reach, give it context, and hand it to your team.
- 0110 min
Run your first agent
Describe a task in plain English, give the agent a tool to reach for, and watch it work. Ten minutes from an empty workspace to a run you can read end to end.
- 028 min
Put an agent on a schedule
Turn a working prompt into a standing task. Describe the cadence the way you would say it out loud, and Helios writes the cron expression for you.
- 0312 min
React to GitHub events
Start an agent the moment a pull request opens, a build goes red, or a tag lands — filtered down to exactly the events you want it on.
- 0410 min
Connect a database
Give an agent Postgres, MySQL, or ClickHouse. It introspects the schema, writes real SQL, and reasons over the results in its own sandbox.
- 0510 min
Attach an MCP server
Bring your own tools. Point Helios at any MCP server, choose which of its tools agents may call, and they become part of the agent's reach.
- 067 min
Pin repositories as context
Give an agent standing context: pin a GitHub repository and the agent carries it into every run without being told again.
- 078 min
Use secrets and variables
Keep the values a task needs out of the prompt. Variables hold configuration, secrets hold credentials, and both are scoped to the level where they belong.
- 089 min
Share with your team
Hand an agent to the people who need it. Roles decide who may edit, visibility decides who may see, and every run leaves a record of what happened.
Start with the first guide.
Ten minutes from an empty workspace to an agent run you can read end to end.