Observability

Yekar.AI records every model call and every tool call as it happens - the arguments, the result, the tokens, the cost and the identity it ran as. That record is the audit trail, and it is queryable from the product without any configuration.

Trace export availability

Exporting turns to your own OpenTelemetry collector is currently unavailable. You can still inspect recorded calls and costs in the product, follow a session's activity, and review per-agent health and outcomes. Contact Yekar.AI if external trace export is a requirement for your workspace.

Where model calls can land

When a provider is unreachable, a turn can finish on a different model rather than failing. This runs only after same-model retries are spent, only for transient failures, and never after any text has reached the reader - replaying a reply on top of what someone already saw is worse than the error.

The fallback chain is a platform setting rather than a per-organization one, and its order is honoured exactly as configured. With no chain set, a turn that exhausts its retries fails honestly rather than answering on a model the agent did not ask for.

What you can see per agent

For the per-agent view - where answers came from, what was repaired mid-turn, and how each Setup revision compares - see Health.