
Argent alerts in Slack
When an AI budget nears its ceiling or an unreviewed skill appears, Argent Strategic Intelligence posts it to the Slack channel your team already reads.
What Argent sends to Slack
Argent watches spend, skills and agent notes. When something needs a person, it posts to your channel.
| Event | When it fires |
|---|---|
Budget threshold budget.threshold | A spend budget crosses 50, 75, 90 or 100 percent of its ceiling. One alert per budget, per period, per level. |
Agent budget alert budget.agent_alert | One agent's own budget crosses 70, 90 or 100 percent, when an operator turned that alert on for the agent. It fires once per crossing. |
Skill approval requested skill.approval_requested | An agent loaded a skill version nobody has reviewed, and, with auto-submit turned on, Argent sent it for approval. A skill is a packaged set of instructions an agent pulls in. Its text is never included. |
Agent note mention agent.note_mention | Someone @mentioned colleagues in a note on an agent. The alert names the agent, the author, the people mentioned and the owner, never the note text. |
Budget owner notice budget.owner_notice | Opt-in only. An admin changed a budget and ticked "tell the owner". The reason text is never included. |
Leave the event list blank and the channel carries every event except the opt-in owner notice. Name any events and it carries only those. An event name Argent does not know is rejected when you save.
How it connects
Argent posts to a Slack incoming webhook: a Slack URL that posts messages into one channel.
Slack's own guide says the webhook URL contains a secret (Slack: sending messages using incoming webhooks), so Argent treats the whole URL as one.
- In Slack, create an incoming webhook for the channel that should get the alerts.
- Store the full webhook URL in the tenant vault.
- In the Argent console, open Integrations > Notifications, add Slack and point it at that vault reference.
- Tick the live-send option and press Test. Argent sends one sample alert marked
TEST -through the same path a real alert takes, so you see it arrive. Without the live-send option, Test checks the configuration only.
Wiring many tenants? argentctl integrations apply reads one JSON document, stores the secrets in the tenant vault, then creates, connects and tests each channel. It can be run again safely, has a --dry-run and never prints a secret. argentctl integrations hosts prints the outside hosts the document needs, so the firewall can be opened precisely.
What you configure
| Setting | What goes in it |
|---|---|
| Webhook URL | A reference to the full incoming-webhook URL in the tenant vault. Required: a channel with no credential is refused. |
| Channel label | Optional. Sent only when set. A Slack webhook that does not honour a channel override ignores it. |
| Events | Blank for every event except the owner notice, or the exact events this channel should carry. |
Different teams can get different slices: a finance channel for budget alerts only, an approvals channel for skill approval requests only.
What lands in the channel
Each alert is one Slack message: a header that says what happened, a detail section, and a footer with the event type and id.
- The header reads like
Budget at 90%: Payments team. Names are resolved by Argent before the alert leaves, so nobody has to look up what an id means. When a name cannot be resolved it is left empty, never guessed. - The notification preview starts with a severity icon: information for info, a warning sign for warning, a siren for error and critical.
- No injected links or mentions. The three characters Slack treats as control (
&,<and>) are neutralised in every alert, so text inside an alert cannot add a link or an @mention to your channel.
Delivery and guard rails
One alert path, built so a bad endpoint cannot hurt anyone else.
- Retried: network errors, timeouts, server errors (5xx), too-many-requests (429) and request-timeout (408) replies. Each means the endpoint has not judged the alert yet. Up to three attempts, 10 seconds each, spaced out at random so a struggling endpoint is not hit by every retry at once.
- Not retried: any other 4xx, such as 401, 403, 404 or 422. The endpoint has looked and refused, so a rotated secret or a deleted endpoint shows up at once instead of hiding behind retries.
- Same event, same id: every retry of one alert carries the same event id, so a duplicate is detectable.
- Never in the way: alerts go onto a bounded queue. One endpoint that hangs can never stall budget checks for any other team, and a dropped alert is counted in the
argent_notify_deliveries_totalmetric that your Prometheus and Grafana stack can alert on.
- Secrets are references. The Slack webhook URL lives in the tenant vault. Argent's configuration holds only a reference to it. It is resolved when the channel connects and is never stored in configuration, written to a log or shown back in the console.
- Outbound guard. Every connection is checked at dial time. Addresses on the Argent host itself and cloud provider metadata addresses are refused. A receiver on a private network is reachable only when your operator adds it to the deployment's outbound allowlist (
ARGENT_CONNECTOR_EGRESS_ALLOWLIST). A tenant admin cannot open that by typing an internal address into a form.
Where it fits
The alerts come from the parts of Argent that hold money, skills, owners and evidence.
- AI Spend Caps and the goal Budget and Token Spend: the budgets behind every threshold alert.
- Audit and Accountability and One-Click Audit Evidence: the signed record the verifier watches.
- Threat Defense: skill review, the source of skill approval alerts.
- Agent Identity and Ownership: every agent has a human owner, the person these alerts reach.
- Audit-break alerts go to email or a signed webhook.
- Budget owner notices: when an admin saves a budget and ticks "tell the owner", Argent emails the owners, or copies a shared Slack or webhook channel, without ever blocking or undoing the budget change.
Other alert channels: PagerDuty, Email (SMTP), Signed webhook. Approvals that need a ticket go to ServiceNow or Jira Service Management.
Need a channel that is not listed? Request a connector from the Integrations catalog in the console. See every integration or book a demo.
Want this running on your own use cases?
Book a demo