TemplatesGet a demo →Book a meeting

Every incident gets a timeline before the post-mortem starts

Describe the incident in your own words and the flow orders what happened against your runbooks, then drafts the timeline, the impact and what is still unknown. Nothing reaches the incident channel in Slack until someone on call approves it.

Engineering · Someone asks · 7 steps · Reads your documents · SlackA person is asked at “Ask a person”

AI Factory · Incident timelinethe flow as it opens in the builder
QuestionQuestion
RetrieveRetrieve
AnswerAnswer
Ask a personAsk a person
ActionPost to Slack
Answer shownHeld back
Answer shownAnswer shown
7 steps in the flowDrag the canvas, or any step, to move it around.

Why teams run it

After an incident, someone has to reconstruct what happened from alert emails, chat scrollback and memory, usually while still tired from the incident itself. Timelines written late are incomplete, and speculation about cause creeps in as fact.

How it is governed

  • Nothing reaches Slack until someone on call approves the post.
  • A rejected timeline ends the run and is recorded as not sent.
  • It is instructed not to speculate beyond the evidence it is given.
  • Testing in the builder describes the Slack post without sending it.
Who runs it
On-call engineers; Incident commanders; Site reliability leads; Engineering managers.
What you supply
Slack connected; Runbooks as a knowledge source.
What “a person approves” looks like in the product: the run stops, the banner says what approving will do, and until someone decides, nothing leaves the system. A demo workspace on synthetic data.

From template to a live agent

The same builder, tests and release review apply to a template as to anything built from scratch.

Open it as a working flow
Every step, source, branch and approval is already in place, and every one of them can be changed before it runs on your data.
Prove it before it ships
An evaluation set can gate the release, so a change that breaks an answer never reaches anyone. A question it cannot answer from the sources leaves the gate unproven, not passed.
Keep a person on the decisions
A run that needs a decision stops and says exactly what approving will do, and who it is waiting for.
Publish where people work
A form, an embedded widget, Microsoft Teams or a scheduled batch — with its own access and limits per deployment.
What teams usually change
Change the Slack channel it posts to after approval; Name who approves: the on-call engineer, the incident lead, or a group; Match the timeline format to your post-mortem template.
Step 02, in the product: an evaluation set that gates the release. A question it cannot answer from the sources leaves the gate unproven, not passed. A demo workspace on synthetic data.

Questions buyers ask

Does it read our monitoring tools?
No. It works from the alerts and messages an engineer gives it, plus your runbooks as a knowledge source. It has no connection to your monitoring or paging tools.
What happens if the approver rejects the timeline?
The run ends with a note that nothing was sent, and nothing is posted to Slack. The draft and the decision stay in the run history.
Will it guess at root cause?
It states a suspected cause only where the evidence supports one, and lists what is still unknown separately. It is instructed not to speculate beyond what it was given.

See it run on your own data

We open it in the builder, point it at a sample of your documents and systems, and run it with you.