Skip to main content
Mention @foggy in any Slack channel to start an investigation. Foggy replies in a thread with evidence, root cause analysis, and recommended actions — so the whole team sees the answer without leaving Slack.
For setup instructions and channel mapping, see the Slack integration page.

​
How it works

  1. You @mention Foggy in any mapped channel or thread
  2. Foggy reacts with 👀 to acknowledge the request
  3. Foggy investigates — querying your connected data sources (Grafana, Prometheus, Loki, Kubernetes)
  4. Foggy replies in a thread with findings, evidence, and recommendations
  5. Foggy reacts with ✅ when done, or ⚠️ if something needs attention
  6. Every reply includes a “View in Foggy” link to see the full chain-of-thought in the web interface
Foggy maintains full context within a thread — mention @foggy again to ask follow-ups without repeating your original question. Automation results from scheduled and alert-triggered investigations are also delivered to Slack automatically.

​
Tips for better results

  • Be specific — include service names, error types, and time windows (“last 2 hours”, “since the deployment at 3pm”)
  • Use follow-ups — drill deeper in threads rather than starting new conversations
  • Ask from incident channels — the whole team sees the investigation without extra sharing

​
Next steps

Automations

Set up scheduled and alert-triggered investigations that run automatically.

Knowledge Base

Add runbooks and context so Foggy gives more accurate answers.

How Investigations Work

Chain-of-thought, follow-ups, @mentions, and model selection.

Connect data sources

Add Grafana, Kubernetes, and more to power investigations.