10 min read
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.
- 01
Connect one integration
Open Settings → Integrations and authorize a single service — Slack and GitHub are the easiest first connections. Helios stores the credential envelope-encrypted and attaches it server-side, so it never appears in a prompt or in the agent's sandbox.
- 02
Create a workflow
A workflow is an agent with a standing task. Give it a name that says what it does — `Daily standup digest` beats `Workflow 1` when you have twenty of them and a run fails at 3am.
- 03
Write the prompt in plain English
Say what the agent should do, which sources it should read, and what a good result looks like. Be specific about the boundaries: what to skip, when to escalate, and what to do when it is unsure. The prompt is the whole configuration — there is nothing else to wire up.
- 04
Give it the context it needs
Every agent runs on Claude Sonnet, tuned for long-running tool use — so the configuration that matters is context. If the task works in a codebase, pin the GitHub repository; if it needs a threshold or an API key, store it as a variable or secret.
- 05
Run it manually and read the run
Trigger the run yourself the first time. The run record shows every tool call the agent made, the arguments it passed, and what came back. This is where you learn whether your prompt said what you meant, so read it before you automate anything.
- 06
Refine the prompt, then add a trigger
Adjust the sentence that produced the wrong behavior and run it again. Once two or three manual runs look right, attach a trigger and the agent starts picking up the task on its own.
Keep going
Next in the track
8 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.
7 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.
9 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.
Templates
Put it to work
Templates that use what this guide covers.
Engineering
Standup without the meeting
Reads yesterday's commits, merges, and review queue, then posts a standup so nobody has to attend one.
Support
Morning inbox triage
Reads what arrived overnight, labels it, drafts the easy replies, and hands you a ranked list of what needs a human.
Support
Slack support triage
Watches your support channel, answers what your docs already cover, and escalates the rest with the account context attached.
Try it in your workspace.
Start free, connect a tool, and describe the first task in plain English.