Skip to main content
What you’ll get: a shared standard for rating investigations, so the skills ewake writes from your feedback are ones you would have written yourself.
Feedback is not a satisfaction score. Every rating you submit in Slack is read back against the thread it rated, and can create, rewrite or archive a skill with effect on the next investigation. A careless πŸ‘Ž teaches a careless rule.

Where feedback comes from

Reacting with :thumbsup: is not feedback. Use the buttons under the message.

What happens after you submit

1

You click πŸ‘ or πŸ‘Ž

A form opens: Help us improve Ewake.
2

You pick dimensions and (optionally) write details

On a πŸ‘Ž at least one dimension is required. On a πŸ‘ the dimensions are optional. The Additional Details box is always optional β€” but it is the part that carries the lesson.
3

Ewake acknowledges immediately

You see β€œThanks for the feedback!” β€” that is the save, not the learning.
4

Ewake reads the thread against your rating

Ewake starts a run in the thread you rated. The rating is about the whole thread, not one message. Ewake reads the thread, your dimensions and your comment, and decides whether they teach a lesson that a later run in the same situation needs.
5

A skill is written, sharpened or archived β€” and goes live

If there is a lesson, ewake changes the skill that covers the situation, or writes a new skill. After a πŸ‘Ž, it can also archive a skill that misled the run. A new or changed skill is active immediately. Ewake is told to change only skills, and not to page anyone, send another message or start an investigation.
This is by design β€” a correction you give today applies to tomorrow’s alert without anyone having to promote it. It is also why the wording of your feedback matters: nothing sits in a review queue between you and the next investigation.
6

Ewake replies in the thread

In one or two sentences. After a change, it says what it changed and links to the skill. After a πŸ‘ with no change, it thanks you. After a πŸ‘Ž with no change, it says that it changed nothing and asks what to change.
A rating of an answer in the Playground, or in Shadow Mode, is saved but starts no run. Nothing is learned from it.

What ewake reads, and what it does not

Ewake reads the thread you rated: the alert or the question, its answer and the messages that followed. It reads your rating: the polarity, the dimensions and your comment. It is told not to start a new investigation, so it does not go back to your data to check what turned out to be true afterwards.
Write in your comment what the thread does not show: what was actually true, and how you knew. Anything you leave implicit is lost.

Choosing the right dimension

The dimension tells ewake which kind of mistake or success it was. Picking the wrong one sends the lesson to the wrong place.
Diagnosis and presentation are separate judgements. An answer that found the right root cause but buried it is Hard to Read, not Missed the Mark. Flagging it as the latter teaches ewake to investigate differently when the investigation was fine.

Writing the comment

The comment is the only place you can say what the right answer was. A good one contains three things:
  1. What ewake concluded β€” briefly, so the lesson is anchored.
  2. What was actually true, and how you knew.
  3. The rule a future run should follow, stated so it generalises beyond today.
Rules of thumb
  • Name services, metrics and thresholds. β€œauth-api p99 over 2s” teaches; β€œthe upstream service was slow” does not.
  • Write the rule, not the incident. The skill applies to later runs in the same situation, so give it something that still makes sense next month.
  • One lesson per rating. Two unrelated complaints in one comment tend to produce one muddled skill.
  • Do not write instructions to a person. The skill body is read by the agent as prior knowledge to weigh against its own evidence, not as an order to obey.
  • Leave out links and ticket ids. They point at today’s incident, not at the rule.

Praise is training too

A πŸ‘ starts the same run as a πŸ‘Ž. Rating a genuinely good investigation is how the ordering that worked becomes the ordering ewake reaches for next time. Rate πŸ‘ when the run changed what you did next. Do not rate πŸ‘ as a thank-you for a run you did not read β€” it is treated as a lesson either way.

When not to leave feedback

  • The gap is a missing integration, not a mistake. If ewake could not see the data, no skill fixes that. Connect the source instead.
  • You are asking for a product change. Send it to support@ewake.ai β€” a rating can only change skills.
  • Someone already rated the same run for the same reason. Each submission starts its own run, and each run can change a skill again.
  • You have not read the answer. A reflex rating is indistinguishable from a considered one.

Reviewing what your feedback taught

Ewake’s reply in the thread links to each skill it changed. Everything it writes is visible and reversible in the dashboard under Skills:
  • The skill’s Versions list shows each change, who made it, and when.
  • Restore puts a previous version back in service.
  • The status toggle disables a skill without deleting it; Archive retires it, and Un-archive brings it back.
Worth doing weekly for the first month: open Skills, read what was written from the week’s feedback, and disable anything that reads like one team’s preference rather than a rule about your production system.

A short checklist

Before you submit:
  • I read the answer and know what it got wrong or right.
  • My dimension matches the kind of problem (diagnosis vs. evidence vs. presentation).
  • My comment names the correct answer and how I know.
  • My comment states a rule that will still be true next month.
  • I would be happy for this rule to apply to the next investigation, unreviewed.

Need help? Contact support@ewake.ai.