AI Assistant

This section is responsible for integration Energylogserver with Large Language Models LLM. Configuration in this section manages changtes in AI Assistant, which is working in Discovery tab. Each LLM needs powerfull graphics processor where complex semantic operation can run. EnergyLogserver strongly recommend to use local AI resources or trusted providers. Remember, security is always local !

AI on Prem is our on Prem solution that You can deploy in local environment.

Providers

Energylogserver comes with predefined LLM connection that operates in our data center. Energylogserver LLM comes at no cost and allows You to use AI features in a controlled and secured way. You can use that provider while Your system in unders support agreement. Communication is encrypted, and we do not record Your prompts. If You want to process AI locally we encourage You to purchase AI on Prem, hardware AI model ready to operate from Your computer rack. Additionally we support open AI, Fireworks and Ollama. Configure Your model in Provider section. Choose its URL, model name, other atributes.

Prompts

Energylogserver allows You to create own prompts to be used in AI Assistant section. A Prompt is a description of a problem to solve using provided log entry. Prompt can be simply any analytical task or technical inquiry that model can provide. Each prompt can work with own AI Provider. New prompts can be deployed as new button, new entry on the list or stored as draft for later.

AI Assistant

Log analysis is empowered with AI Assistant. For each log entry user can run predefined prompts or use own prompts for deeper analysis.

AI Assistant comes with three sections:

  • User prompts on the list

  • Embeded prompts

  • Default user prompts as buttons

All User prompts can be configured in Empowered AI - AI Assistant.

Empeded prompts are immutable.

Description:

  • Explan log : gives detailed information about the meaning of log entry

  • Detect Thread : AI will semanticly try to understand the meaning of log entry and try to detect possible security thread. Detection is done on a language level, not with regexp

  • Create Alert : AI will generate Alert rule, trying to match context of the message and not exact message value

Default prompts are deployed as buttons and can be modyfied in Empowered AI AI Assistant.

Description:

  • Assignment : match IT department / team with the problem defined - prompt can be adjusted to map team members to departments allwing quick incident escalation

  • Classify : match event category

  • Extract IOCs : easy way to copy all artefact like ip, username, program, etc

  • MITRE : describe thread using MITRE metodology

  • Responsibility : indentify responsible team

  • Priority : analise the entry estimating its priority in details

  • Privacy : check for sensitive, private data

  • Recommend : check for recommendations AI can provide for the problem