DevOps and cloud agency
Your next fix, shipped
Someday is now. AI Agents for failing checks and incidents. The Coder reads the failing check, opens the fix, and waits. The Product owner writes the status. You give the final go.
A clearer system
A change prepared for review
- The services you look after
- The checks and incidents that repeat
- Where you give the final go
Nothing is sent or shipped unless you asked for it or approved it, and money always asks.
Sentry, Datadog, PagerDuty, Better Stack, UptimeRobot, and incident.io show what is failing, and the Coder reads them. GitHub holds the fix, and a merge or a deploy waits for you.
A closer look
An idea goes in.
Real work comes out.
A change prepared for review. Explore how the pieces fit.
Illustrated workflow
02 / The team works
The team works
The assistants take the goal, use the ready prompts and skills, and do the work in the tools you connected.
How it works
From a goal to a result.
- 01
Set a goal
You say what done looks like: a ticket, a client, a deadline, or a draft.
- 02
The team works
The assistants take the goal, use the ready prompts and skills, and do the work in the tools you connected.
- 03
You approve the risky step
Anything that sends, publishes, ships, or charges waits for your Approve. Approve a kind of step once and that assistant remembers it, but money always asks.
- 04
You get the result
A pull request with the fix and a status note. The merge, the deploy, and the send all wait for your Approve.
Example
Send the incident summary to your client
It sends to people, so it asks first.
The team
You, and the assistants.
You
You set the goal for the incident and give the final go on the merge, the deploy, and the status note.
Coder
Reads the failing check, the logs, and the incident, writes the fix on a branch, and opens the pull request on its own. A merge or a deploy waits for your Approve.
Product owner
Writes the status update so stakeholders know what failed and what is next. Sending it waits for your Approve.
Integrations
The tools it starts with.
- GitHub
- Slack
- Sentry
- Datadog
- PagerDuty
- Better Stack
- UptimeRobot
- incident.io
Built in
What your assistants can use.
Its own computer
Each assistant works on its own computer in StellarFirm cloud, set up with the tools its job needs, and hands you the files.
Roles you make yourself
Name a role we don't ship, say what it does and give it any of our skills or your own. Comes with Ultra and enterprise.
A running app beside the chat
The Coder starts the app it built and shows it live next to the chat, so you can click through it yourself.
Keep going until it is done
Say what done looks like and the Coder keeps going, up to ten more rounds, until the goal is met. /stop ends it.
Long jobs in the background
A big job starts at once and runs in pieces in the background, streaming back as it goes. You can stop it any time, and sends and spending still ask.
Follows up on its pull requests
Switch it on for a Coder and it takes on failing checks, merge conflicts and review comments on its own pull requests. Merges and replies still ask you.
Put the app it built online
When the Coder has built an app, it can put it online at an address like your-name.stellarfirm.app once you approve. You can take it offline again any time.
It asks only when it matters
Assistants make and change things on their own and ask before they send, publish or delete. Approve a kind of step once and that assistant stops asking; money always asks.
Ready to use
Prompts and skills.
Skills
- Fix CI
- Set up CI
- Debug a failure
- Stakeholder status update
- Review a pull request
Ready prompts
Read the open incident in incident.io and the errors in Sentry, and tell me what is failing before you change any code.
Fix the failing check and open a draft pull request.
Draft the status note for this incident and hold it for my Approve.
Questions
Before you join.
Start with your first assistant.
Leave your email. Invites go out every day until 27 October, and we'll write when your spot is ready.