Integration · Messaging
Slack + OrchestrAI
Catalog exported 2026-09-02 · Slack website
Post run results and alerts to Slack, set up incoming webhooks, and look up channels and users.
OrchestrAI exposes 7 Slack operations: 7 are low-risk (read-only or low-impact).
What teams use it for
Most teams wire Slack in so that the outcome of a run, a drift detection, or a cost check lands in #platform-ops where people already look, and so an engineer can ask OrchestrAI to tell #oncall that a rollout finished. Setting up an incoming webhook for a new channel and listing workspace channels and users to find the right target are both covered, and every Slack operation is read or send-only with no risk gate. OrchestrAI cannot read channel history, create channels, or reply in threads, so it is a notification and lookup path rather than a full Slack bot.
Every Slack operation, with its risk level
| Operation | What it does | Risk | Step-level approval |
|---|---|---|---|
Create Slack Incoming Webhook |
Set up a Slack incoming webhook for notifications | Low risk | No |
Create Slack Webhook |
Create a Slack incoming webhook for notifications | Low risk | No |
List Slack Channels |
List channels in the connected Slack workspace | Low risk | No |
List Slack Users |
List users in the connected Slack workspace | Low risk | No |
Send Slack Message |
Send a message to a Slack channel | Low risk | No |
Send Slack Notification |
Send a notification to a Slack channel | Low risk | No |
Slack Webhook |
Configure a Slack webhook integration | Low risk | No |
Risk tiers come from the catalog: low is read-only or low-impact, medium creates resources and is reversible, high modifies existing resources, destructive may lose data. Every plan that creates or changes resources is shown with its cost estimate and waits for your confirmation. Operations marked with a step-level approval pause again on their own step. Destructive operations require a typed risk phrase.
What you connect
No Slack-specific credential; these operations run against your connected cloud account. Connected-service tokens are envelope-encrypted with a per-record key wrapped by a cloud KMS.
Prompts that work
- Send a message to #deployments saying the checkout-api rollout to prod finished at 14:32 UTC with no errors
- Create an incoming webhook for #cost-alerts so budget notifications go there
- List the channels in our Slack workspace that have 'infra' in the name
Before anything runs
Every mutation shows its plan, cost estimate, and blast radius, then waits for your confirmation. Destructive operations require a typed risk phrase. Credentials are minted per run through OIDC federation and discarded afterward; nothing you create here is invisible later, because every resource lands in the desired-state ledger where drift is detected and can be converged. Details on the security page.
Frequently asked questions
- Can OrchestrAI send Slack notifications when a run finishes?
- Yes, slack_notification and slack_send_message post to a channel you name, and a webhook can be created for channels that should receive them without a bot user.
- Does OrchestrAI read my Slack messages?
- No, The Slack operations list channels and users, send messages, and configure webhooks. None of them fetch message history.
- How does OrchestrAI authenticate to Slack?
- You add a Slack credential once in the connections screen. It is envelope-encrypted with a per-record key wrapped by a cloud KMS and is only decrypted inside the run that needs it.
Related integrations
Try it on your own account
Connect your cloud read-only and see your resources, drift, and costs before anything runs. $5 minimum to start. Unused credits refunded in your first 14 days.
Unused credits refunded in your first 14 days.