Skip to content

Incident Comms Drafter · SaaS & Startups

Calm, clear outage updates for customers, without pulling an engineer

Turns engineers' raw incident notes into customer-ready status updates your incident commander approves, then drafts a blameless postmortem in Notion once it's resolved.

Available now $149 one-time · never renewsIncluded in Enterprise
Get this agent See how it works

Free account to start. Buying and running live need a paid plan.

  • Starts from an event in a connected app
  • 3 AI steps
  • A person approves before it acts
  • About 20 min to set up

Sound familiar?

The job, before and after this agent.

What it feels like today

  • “During an outage the people fixing it are also the ones asked to write customer updates.”
  • “Our status updates are either too technical, too vague or late.”
  • “Postmortems start from a blank page days later, when nobody remembers the timeline.”

What you get with the agent

  • Each update in #incident-updates read with the incident's earlier updates (remembered for 14 days).
  • A customer-facing draft: Investigating, Identified, Monitoring or Resolved, the impact in plain words and the next update time, with no blame, speculation or internal names.
  • The incident commander approves and can edit every update before anything reaches customers.
  • Approved updates posted to #status-comms and emailed to your customer-notice list.
  • On Resolved, a blameless postmortem skeleton in Notion: timeline, customer impact and open questions.

Before

Invoice emails stop sending. An engineer leaves the fix to write a jargon-heavy update forty minutes late, and the postmortem is written from memory a week after.

After

The engineer posts a quick note in Slack. A calm customer update is waiting for the incident commander within moments, goes out on approval, and the postmortem draft is in Notion when the incident is resolved.

How it works

The whole workflow, step by step.

Each engineer update in your #incident-updates Slack channel is read by AI together with the incident's earlier updates, which are remembered for 14 days and treated as untrusted context. It drafts the customer-facing update: Investigating, Identified, Monitoring or Resolved, the impact in plain words and the next update time, with no blame, speculation or internal names. The incident commander approves and can edit every update. It's then posted to #status-comms and emailed to your customer-notice list. When an update is Resolved, the agent reads the incident channel and drafts a blameless postmortem skeleton in Notion: timeline, customer impact and open questions. It isn't monitoring or alerting, doesn't find root causes and doesn't post to Statuspage or Instatus by default.

  1. TriggerNew message in #incident-updates
  2. AI stepIs it an incident update?
  3. LogicAn update?
    • Not an update:Not an update
    • Update:Recall this incident's updates
  4. OutputNot an update
  5. LogicRecall this incident's updates
  6. AI stepDraft the customer status update
  7. Human approvalIncident commander approves
    • Rejected:Not sent
    • Approved:Post to #status-comms
    • Approved:Resolved?
  8. OutputNot sent
  9. App callPost to #status-comms
  10. OutputEmail your customer-notice list
  11. LogicRemember this update
  12. OutputUpdate sent
  13. LogicResolved?
    • Ongoing:Still ongoing
    • Resolved:Read the incident channel
  14. OutputStill ongoing
  15. App callRead the incident channel
  16. AI stepDraft the postmortem
  17. App callSave the postmortem draft
  18. OutputPostmortem drafted

This is the workflow that opens in your workspace when you set the agent up. Every step can be edited.

  1. Step 1New message in #incident-updatesStarts within seconds of a message in your incident channel, where engineers post raw updates (including thread replies). The app's own messages never start it.
  2. Step 2Is it an incident update?AI decides whether the message is an update about an incident (not chatter) and which incident it belongs to.
  3. Step 3An update?Chatter in the incident channel is left alone.
  4. Step 4Not an updateThe run history keeps the message.
  5. Step 5Recall this incident's updatesReads the last 20 updates already posted for this incident (kept for 14 days after the last one). Nothing is found for a new incident.
  6. Step 6Draft the customer status updateAI drafts the customer-facing update: status (Investigating / Identified / Monitoring / Resolved), impact in plain words and the next update time, with no blame or speculation.
  7. Step 7Incident commander approvesThe incident commander reads the engineers' message and the drafted update in Reviews, edits it and approves. Nothing reaches customers before that.
  8. Step 8Not sentThe incident commander rejected the draft; nothing was posted or remembered.
  9. Step 9Post to #status-commsPosts the approved update to your status-comms channel.
  10. Step 10Email your customer-notice listEmails the approved update to your customer-notice list address (e.g. a Google Group or mailing-list alias).
  11. Step 11Remember this updateSaves the engineers' message and the approved update with this incident's earlier ones (the last 20, for 14 days after the last one).
  12. Step 12Update sentThe run history keeps the engineers' message and the approved update.
  13. Step 13Resolved?Updates still Investigating, Identified or Monitoring stop here; once the approved status is Resolved, a postmortem draft is started from the incident channel.
  14. Step 14Still ongoingNo postmortem yet.
  15. Step 15Read the incident channelReads up to 200 messages of #incident-updates since the incident started (top-level messages; thread replies aren't included).
  16. Step 16Draft the postmortemAI drafts a blameless postmortem skeleton from the channel and the approved customer updates: timeline, customer impact, what helped, and open questions for the team.
  17. Step 17Save the postmortem draftAdds the postmortem draft to your Notion postmortems database with Status Draft.
  18. Step 18Postmortem draftedThe run history keeps the Notion link.

Example run

What goes in, and what comes out.

Example with fictional data

Comes in

Slack #incident-updates: INC-311 invoice emails queued, not sending since 14:05 UTC, looks like mail worker pool exhausted after the 13:50 deploy, rolled back at 14:40, queue draining.

The agent produces

Draft (Monitoring): some invoice emails were delayed from 14:05 UTC; a fix is in place and delayed emails are being sent now; next update by 15:30 UTC. No internal details. Waiting for the incident commander, then posted to #status-comms and emailed to the notice list.

What you need

Everything it takes to run it.

About 20 minutes from purchase to live. A checklist above the canvas takes you through each step.

Plan

Included in Enterprise; on other paid plans it's $149 once. Agents run live on paid plans, from Basic ($39/mo).

Your AI key

Connect any of 14 AI providers on your own key. Your provider bills usage directly, at cost; we add no markup.

Apps

Checklist

  • A paid plan (agents run live on paid plans).
  • An AI provider key (Settings → AI Providers).
  • Slack (with channel history permission) and Notion, connected in Settings → Integrations, and a Notion postmortems database.
  • A customer-notice mailing-list address.

Setup, about 20 minutes

  1. Connect your AI provider. The AI steps run on your own key (OpenAI, Anthropic, Google and more). Add one in Settings → AI Providers.
  2. Connect Slack. Connect the Slack workspace with your incident channels (Settings → Integrations → Slack).
  3. Connect Notion. Connect Notion and share your postmortems database with the Fluxo Flow integration (Settings → Integrations → Notion).
  4. Pick the incident channel. Open the trigger and pick your Slack account and #incident-updates.
  5. Write your incident rules. Open “Is it an incident update?” and “Draft the customer status update” and replace the placeholder in each with the same rules.
  6. Pick where approved updates go. Open “Post to #status-comms” and pick the account and channel, then “Email your customer-notice list” and enter the list address and Reply-to.
  7. Pick the postmortems database. Open “Read the incident channel” and “Save the postmortem draft” and pick your Slack and Notion accounts and the database.
  8. Test it with Dry Run. Press Dry Run: the agent runs on sample data with no messages sent and nothing written to your apps.
  9. Switch the trigger on. Open the trigger and press “Activate app trigger”: from then on each engineer update gets a customer draft in Reviews.

Is it a fit?

Who it's for, and what it won't do.

Built for

  • SaaS engineering and on-call teams
  • Support and customer communication leads
  • Startups without a dedicated comms person

What it doesn't do

  • It isn't monitoring or alerting and doesn't find root causes.
  • Nothing reaches customers without the incident commander's approval.
  • It doesn't post to Statuspage or Instatus by default (an HTTP step with your status-page API key can be added).
  • The postmortem reads top-level channel messages (up to 200), not thread replies.

We list the limits up front so you can decide before you buy.

Price

$149 one-time

Per workspace. It never renews.

Available now
  • Included at no extra cost on Enterprise.
  • Buying and running it live need a paid plan, from Basic ($39/mo).
  • Dry Run costs nothing: simulated AI and app calls, nothing sent.
  • AI usage is billed by your own provider, at cost. No AI credits to buy from us.
Get this agent See how it works

One-time agent purchases aren't covered by the 30-day money-back guarantee. Refund policy

FAQ

Questions about Incident Comms Drafter.

What if the AI says the wrong thing to customers?

Nothing reaches customers without the incident commander's approval, and they can edit every word. Drafts avoid blame, speculation and internal names by design.

Does it detect incidents or find root causes?

No. It isn't monitoring or alerting and never guesses causes; the postmortem lists open questions for your team.

Can it post to our status page?

Not by default. You can add an HTTP step after approval with your status-page API key. It needs Slack (with channel history permission), Notion and a customer-notice mailing list. Setup takes about 20 minutes.

Is it worth the price?

A one-time price that never renews, against engineer time and customer trust during every outage. Live runs need a paid plan and your own AI provider key; Dry Run is free.

How does it know which incident an update belongs to?

By the incident id in the message (e.g. INC-123), or the thread when engineers keep one thread per incident. Say which your team uses in the rules.

Can it post to Statuspage or Instatus?

Not by default. You can add an HTTP step after the approval with your status-page API key; the approved text is in the review's output.

Does it find the root cause?

No. It isn't monitoring or alerting and never guesses causes; the postmortem draft lists open questions for your team.

How do I email many customers?

Use a mailing-list or Google Group address as the recipient: the email step sends to up to 5 addresses.

Is this a subscription?

No. Incident Comms Drafter is a one-time purchase of $149 per workspace and never renews. The Enterprise plan includes it at no extra cost. Running it live needs a paid plan (from Basic ($39/mo)), and your AI provider bills you directly for usage.

Can I test it before it touches real data?

Yes. Once it's set up in your workspace, Dry Run plays every step on sample data with simulated AI and app calls: nothing is sent and nothing in your apps changes. Switch the trigger on only when you're happy.

Put Incident Comms Drafter to work.

Free account, no credit card. Your Agents page opens with Incident Comms Drafter ready to buy and set up, then Dry Run it before it goes live.

Get this agent See how it works