Skip to main content
Find answers to the most frequently asked questions about Olly.

​
Product positioning & architecture

Olly is a standalone offering of AI across all Coralogix’s capabilities - logs, metrics traces. The AI Center, on the other hand, is a place to monitor and track AI applications.
MCP is access to Coralogix data. Olly is intelligence. While MCP lets AI tools read observability data, Olly uses that data to actually run production investigations.What Coralogix MCP is:
  • MCP is a way to expose Coralogix API to AI systems like Cursor.
  • Coralogix MCP exposes logs, metrics, traces, alerts.
  • It’s an integration layer, not a product.
What Olly is:Olly sits on top of the Coralogix Observability Platform and turns data into action. It is an Agentic Observability System made of:
  • Knowledge: Understands your services, history, incidents, deployments - like an engineer who knows your production.
  • Multi-agents: Specialized agents (logs, traces, metrics, correlation, security, engineering) that work together on any task and prompt.
  • Autonomy: Autonomously decide on how to navigate and solve any challenge.
  • UX & UI: Olly’s UI is specially built for Observability use-cases - support any insight with evidence, generate relevant charts and recommend actions - built for humans in production.
Olly behaves like a Senior Production Engineer and investigates, reasons, and takes action, not just queries data.

​
Token usage & limits

Yes - you can monitor your token usage by navigating to your profile, then Usage. Usage is tracked per your and resets monthly.
This can absolutely happen.Olly’s token usage is not based on the number of questions, but on the total amount of data and context processed to answer them.Even a small number of questions can consume a high number of tokens if they require deeper analysis. Each request may include:
  • Conversation context: Olly sends the full relevant conversation history to keep answers accurate and consistent.
  • Retrieved supporting data: Olly may pull in large volumes of logs, traces, metrics, alerts, or other data to properly analyze your question.
  • Model reasoning and output: Tokens are used not only for the final answer, but also for intermediate reasoning and processing steps.
Because of this, a question that takes longer to analyze or touches a broader dataset can consume significantly more tokens than a simple question — even if you only asked a few.
Olly follows the same token model used by LLMs such as OpenAI and Claude. When you ask a question, Olly may run multiple agents behind the scenes to understand the request, retrieve relevant data, and generate an accurate answer. Because of this, more complex questions consume more tokens. As a rule of thumb, a token roughly represents 4 characters. To keep things simple and transparent, Olly displays input and output tokens together as a single “Token” unit in the UI.
When a user reaches their token limit (based on their seat tier), Olly blocks further usage. This state is clearly shown in the UI