AI status update generation

Let ilert AI draft the message of a status update, and guess which services it should name.

Writing to customers is the part of an incident that gets postponed, because it is the part that needs a calm sentence and you are not calm. ilert AI takes a few words and turns them into a publishable status update, then guesses which services it concerns and at what impact level.

You are still the one who publishes it. Read what it wrote.

The first update

In the Post status update dialog, type a short description of what is happening into the field and click the 🪄 icon beside it. Something like spacex services unavailable is enough.

ilert AI writes the message and pre-selects the services it believes are affected, each with an impact level.

A handful of words in, a publishable message and a service list out.

Follow-up updates

Once an incident has posted its first update, the AI moves to the Message field, where it drafts the next update in the context of the ones before it — so a Monitoring update reads as a continuation rather than starting the story again.

Follow-ups are drafted against what has already been said.

What is sent to the model

Enough to write the sentence, and no more.

For a first update:

• the service names of a small selection of services, chosen by their relation to your prompt and to you — services owned by your teams, for instance. No other service data leaves ilert.
• the summary you typed, as the prompt.

For a follow-up:

• the service names of the services already on the incident. Services that are not on it are not sent.
• the incident's current status.
• the message you typed, as the prompt.

Not sent, in either case: your alerts, your timeline, your responders, your customers, or anything about services other than their names.

Status update generation uses an external model. It can be turned off account-wide, along with every other external-LLM feature, in account settings.