Jonatas Silva
Tech Lead · Platform Admin
Langfuse-style tracing for every LLM call — tokens, cost, latency, fallbacks, evaluation and compliance scores, correlated to tenant and job.
Total cost (traces)
$1.11
Avg latency
13.9s
Fallbacks used
1
Errors
1
Spend attributed per AI provider
Average response time (ms)
% of failed calls
Lower is better (7-day trend)
Weighted compliance evaluation
Provider share of monthly token spend
Every LLM invocation, end to end.