# Oodle AI

Observability platform for AI agents and software: traces, logs, metrics, evaluations and alerts in one place.

- Website: https://www.oodle.ai/product/agent-observability
- Listing: https://openack.co/p/oodle-ai
- Not evaluated. Listed by OpenACK: its 8 claimed capabilities are OpenACK's reading of the product's public site, not the maker's word, and nobody has checked them yet.

OpenACK's description (not checked):

> Oodle collects OpenTelemetry traces, logs and metrics from applications and AI agents. Its Agent Observability hub shows LLM traces with token counts and estimated costs, and lets teams build datasets and run evaluation experiments.

## Capabilities

- **not evaluated**: Search AI agent traces by input or output text
- **not evaluated**: View token usage and cost trends for LLM calls
- **not evaluated**: Create a dataset of test cases from a CSV file
- **not evaluated**: Add a production trace to a dataset
- **not evaluated**: Set custom model pricing for cost tracking
- **not evaluated**: Create an alert monitor from a PromQL query
- **not evaluated**: Ask an AI assistant questions about your metrics, logs and traces
- **not evaluated**: Generate a dashboard with AI from a prompt

## What the statuses mean

- **confirmed** (ACK): a person from OpenACK signed in with a test account and saw it work.
- **not confirmed** (NAK or ?): it was tried and didn't work, or we couldn't reach or check it. Not proof it's missing, but not verified.
- **not evaluated** (—): nobody has checked it. It's the founder's word only.

Treat only "confirmed" as verified. A result is a record of one evaluation on the date shown, not a guarantee.