Slack + governed AI agents
A message posted to the wrong channel is a small disaster that spreads quickly. FlozentAi treats posting as a consequential action: the agent prepares the message and the channel, and a person sees both before anything is sent.
Connecting Slack
| Definition | Import the Slack Web API specification for the methods you need. |
|---|---|
| Credential | Bot token from your Slack app, stored in your vault. |
| Stored as | A secret:// reference to your own vault. FlozentAi never holds the value. |
Actions teams usually publish
Action names are yours to choose during review — these are the shapes most teams end up with. Anything that writes is confirmation-gated unless you deliberately publish it otherwise.
| Action | Kind | What it does |
|---|---|---|
conversation.history | Read | Read recent messages in a channel. |
user.get | Read | Resolve a user profile. |
message.post | Write | Post a message. Always approval gated. |
What people build with it
- An incident assistant that drafts the status update and waits for the incident lead to approve it.
- A digest agent that summarises a channel into a report, with no posting action published.
There is no field in the console that accepts a token or a password. You store the secret in your vault and give FlozentAi a reference; the runtime resolves it inside the execution layer, after the policy decision.
Slack questions
Can it post automatically to an internal channel?
You can publish the post action without confirmation if you accept the risk. Most teams leave the gate on for anything customer-visible and remove it only for a low-stakes internal channel.
Use cases that involve Slack
Connect Slack the governed way.
Import the specification, review what it found, and publish only what you want reachable.