What you’ll get: By the time your on-call engineer opens their laptop, ewake has already investigated the alert, probable cause ranked by confidence, supporting evidence assembled, next steps ready. The work that takes 30 minutes manually happens in seconds, automatically.
What it does
The On-Call Agent monitors a configured Slack channel for alerts from your observability tools (Datadog, Grafana, etc.). When an alert fires, ewake immediately queries your connected sources, metrics, logs, recent deployments, past incidents, and posts a structured investigation response in the alert thread. Your on-call engineer arrives to a Slack thread that already contains:- The probable root cause, ranked by confidence
- Supporting evidence (relevant logs, metrics, recent commits)
- Suggested next steps
When to use it
- You have alerts routing to a Slack channel (
#alerts,#incidents,#monitoring) - Your team is on-call and needs faster first-response context
- You want to reduce the time between alert firing and understanding what’s happening
What you’ll get
A typical ewake response in a Slack alert thread includes:- Summary, one-line description of what happened
- Probable cause, top hypothesis with confidence indicator
- Evidence, log excerpts, metric spikes, recent deploys that correlate
- Suggested next steps, concrete actions to investigate or resolve
Prerequisites
Before setting up the On-Call Agent, make sure these integrations are connected:Slack
Alert source
Datadog, Grafana, or another connected observability tool
Source control
GitHub or GitLab
Incident.io
Lets ewake reference past incidents and postmortems, surface patterns like “this looks like incident #47 from last month.”
Deployment Tracking
Sends deployment events to ewake so it can immediately correlate an alert with a recent deploy.
How to set it up
1
Add ewake to your alerting channel
Ewake only reads channels it’s been invited to. Before creating a trigger, invite
@ewake to the Slack channel where your alerts land (e.g. #alerts, #incidents, #monitoring).Follow Add Ewake to a channel if you haven’t done this yet.2
Go to Alert Response
In your ewake dashboard, click Alert Response in the sidebar, that is where On-Call Agent triggers live.
3
Start from a template, or from scratch
Click Templates to start from a ready-made trigger, then adjust it. Each one pre-fills the name and prompt; you still pick your own channel and bot.
To start from nothing instead, click New trigger.
4
Name your trigger
In Trigger Name, enter a name that identifies this trigger (e.g.
datadog-alerts-prod, pagerduty-critical).5
Select a Slack channel
In Slack Channel, choose the same channel you invited ewake to in the first step, for example:
#alerts#incidents#monitoring
6
Select the alert bot
In Slack Bot, choose which bot ewake should listen to (e.g. Datadog). This ensures ewake only responds to real alerts, not other messages in the channel.
7
Write the initial prompt
Initial Prompt is the message sent to the On-Call Agent when the trigger fires. This is the main lever to customise tone and depth.Examples:
8
Create the trigger
Leave Active on, then click Create.
The On-Call Agent is live. The next time an alert fires in the selected channel, ewake will automatically respond in the thread.
Switch Active off on a trigger to pause it without deleting it, useful during a planned maintenance window.
Actions
Everything above is read-only: ewake investigates and reports. Actions let a trigger do something afterwards. In the Action field, describe the follow-up in plain words, for example:Actions are a gated feature. If the Action field doesn’t appear on your trigger form, it isn’t enabled for your workspace, contact support@ewake.ai.
How Actions fit the security model →
Need help setting this up? Contact support@ewake.ai.