Overview
Send LangSmith alerts to Callgoose SQIBS. A LangSmith alert watches a project's error count, latency, feedback score or cost, and when it crosses the threshold it posts to a webhook pointed at your SQIBS API endpoint. SQIBS opens an incident with the alert rule name.
How it works
Want SQIBS to fix known issues before anyone is paged? See Fix known issues automatically.
Step 1: Add the API filter in SQIBS
- In SQIBS, open Services, choose the service that should receive these incidents, and click Add Or Update API Integration.
- Add a filter with these values (there is no built-in LangSmith template yet, so enter them by hand):
| Part | Payload JSON key | Key value contains | What it does |
|---|---|---|---|
| Trigger | "alert_rule_id" |
Opens an incident for every LangSmith alert. | |
| Match | "alert_rule_id" |
Keeps repeated alerts of one rule together. | |
| Title from | "alert_rule_name" |
Becomes the incident title. |
- Choose the Priority for these incidents and click Save.
LangSmith sends a message when a threshold is crossed, not when it recovers, so close the incident in SQIBS when the metric is back to normal. To route by metric, add a trigger row on "alert_rule_attribute" with error_count, latency, feedback_score or cost.
Not sure of a key? Send one test message first (step below), then build the filter from the real payload.
In the API Integration window, click the round
{} button at the bottom right. Paste a payload that SQIBS received (copy it from the API log). SQIBS lists every key with its value, each with a copy button. Copy the key into Payload JSON key and the value into Key value contains. No need to read the JSON by hand.Step 2: Create the alert in LangSmith
- In LangSmith, open the project (under Tracing) and go to the Alerts tab. Click + Alert.
- Choose the metric (errored runs, latency, feedback score or cost), the threshold and the time window.
- Under notification settings, choose Webhook and enter your SQIBS endpoint as the URL:
https://<your-endpoint>/sqibs-api/v1/process?from=langsmith&token=<your-token>
Replace <your-endpoint> and <your-token> with the values from your SQIBS account. See how to get the endpoint URL and API tokens.
- Leave Headers as
{}(the token is in the URL) and the request body as{}. LangSmith adds the alert fields itself. - Click Send Test Alert, then save the alert.
Step 3: Test it
The API log saves payloads only while API Tracking is on for the token. Turn it on under API Tokens before you test; it switches itself off after 48 hours.
- Click Send Test Alert.
- In SQIBS, a new incident opens, titled with the alert rule name. LangSmith's payload looks like this (shortened):
{
"project_name": "support-bot",
"workspace_name": "production",
"alert_rule_id": "8f2c7a1e-3b4d-4c5e-9f6a-1b2c3d4e5f60",
"alert_rule_name": "Error rate above 5%",
"alert_rule_type": "threshold",
"alert_rule_attribute": "error_count",
"triggered_metric_value": 42,
"triggered_threshold": 20,
"runs_url": "https://smith.langchain.com/o/.../projects/p/...",
"timestamp": "2026-11-22T10:15:00Z"
}
No incident? Open the API log (with API Tracking on). If the payload is there, the filter did not match it: paste it into the JSON key creator and check the keys. If it is not there, check the URL and token in the LangSmith alert.
Fix known issues automatically
Many alerts have a known fix: restart a service, clear a full disk, run a health check. SQIBS can run that fix for you the moment the incident opens. This is event-driven auto remediation. For example, when LangSmith reports a jump in errored runs, SQIBS can run a workflow that switches the application to a fallback model and alerts the team.
Safe by design. SQIBS runs only workflows your own engineers wrote and approved for your environment. Nothing is guessed or generated: the same steps an engineer would run by hand, run sooner. If the workflow does not fix the issue, the engineer is paged as usual.
To set it up, in the same API filter:
- Select Workflow: choose the automation workflow to run when this filter opens an incident.
- If success then make incident resolved: turn on to resolve the incident when the workflow succeeds.
- Waiting time for escalate to escalation policies: how many minutes to give the workflow before paging the on-call engineer.
Start with low-risk workflows, such as a health check, and add fixes as you come to trust them.
Learn more:
- Prometheus: incident auto remediation, a full worked example.
- Automation workflow: build a workflow from actions.
- Run workflows where your systems are: SSH, Bash, PowerShell, Python, Ansible, kubectl, Terraform.