DevOps·5 min read

Monitoring Bots with Logs & Analytics

Watch requests in real time, track success rate and latency, and debug failures with per-run logs.

Monitoring Bots with Logs & Analytics

Once a bot is live, you need to see what it's doing. Bothive gives you three lenses.

Live Logs

Under Developer → Live Logs, watch requests stream in as they happen — inputs, outputs, tool calls, and errors. This is your first stop when something looks wrong right now.

Workflow executions

Every workflow run is recorded. Open the Executions panel to see per-node output and logs for a specific run — which node produced what, which branch was taken, and where a failure occurred.

Analytics & Insights

The Analytics / Insights area aggregates the bigger picture:

  • Volume — how many runs over time.
  • Success rate — how often runs complete cleanly.
  • Latency — how long runs take (spot slow tools).

Debugging a failure

  1. Reproduce it and watch Live Logs for the error.
  2. For workflows, open the run in Executions and find the red node.
  3. Check whether a tool needs a connection (Integrations) or a missing key.
  4. If a model step is the culprit, tighten its prompt or switch the model tier.

Keep an eye on usage

The Usage page shows credit consumption. A sudden spike usually means a loop running hot or a step using a Smart model where Fast would do.

Next steps

Quick tip

Use the test pane to iterate quickly. Every change you make is live — no need to save first.

Important

API keys are shown only once. Store them securely and never commit them to version control.

Best practice

Test your bot with edge cases before deployment. Try empty inputs, long messages, and special characters.

Pro tip

Chain multiple specialized bots in a workflow for better results than one general-purpose bot.

Monitoring Bots with Logs & Analytics