Agent Console Guide

This page provides a guide to the Agent entity in the Namirasoft Expert Console. It defines the concepts and configuration fields used when creating and managing AI Agents. Use this guide to understand the purpose and behavior of each setting available during Agent configuration.

What Is an Agent?

An Agent in Namirasoft Expert is an AI-powered assistant individually configured to investigate infrastructure and respond to operational queries using live diagnostic data. Each Agent has its own infrastructure scope, AI model configuration, cost limits, and notification settings, allowing teams to create specialized Agents for different environments, services, or operational use cases.

When you interact with an Agent, it retrieves relevant operational data and performs authorized read-only diagnostic actions to help investigate infrastructure behavior, monitor system statistics such as CPU usage, memory utilization, disk usage, and other operational metrics, identify potential issues or anomalies, and provide answers or suggested solutions. Diagnostic commands executed against your infrastructure and retrieved results are visible in the chat interface, providing transparency into each investigation.

Each Agent belongs to a specific Project and Environment, ensuring that investigations remain scoped to the intended operational context.

Beyond manual interaction, Agents can also be triggered programmatically through the Namirasoft Expert API. External systems such as monitoring tools or alert pipelines can initiate Agent investigations automatically. Investigation findings can then be delivered through configured notification channels using Namirasoft Notification Sender.

For information about connecting external systems through APIs and automated workflows, visit the Integrations page.

For information about currently supported infrastructure types and coverage details, visit the Coverage page.

The Challenge in DevOps and SRE Operations

DevOps and SRE teams responsible for managing infrastructure frequently face the challenge of diagnosing operational issues quickly while minimizing disruption to running systems. When an alert is triggered, engineers often need to investigate multiple systems, run diagnostic commands, correlate information from different sources, and determine the root cause while services may already be experiencing degradation.

Common challenges include:

Time-consuming investigations: A single issue may require collecting and reviewing information across multiple systems before the underlying cause becomes clear.

Context-switching overhead: Engineers frequently move between monitoring dashboards, log platforms, infrastructure tools, and terminal sessions to correlate information from different systems.

AI context preparation overhead: When using general-purpose AI tools for troubleshooting assistance, engineers often need to manually collect logs, metrics, command outputs, and system details, then spend additional time providing sufficient context before the AI can understand the environment and provide useful recommendations.

Knowledge gaps: Less experienced engineers may not always know which diagnostic steps to take or how to interpret operational data accurately under pressure.

Limited investigation visibility: Manual troubleshooting processes can become difficult to review, reproduce, or audit later, especially when information is spread across multiple systems and sessions.

24/7 operational demand: Infrastructure issues do not follow business hours, but experienced team members may not always be immediately available.

How Namirasoft Expert Solves the Problem

Namirasoft Expert addresses these challenges through Agents, which are individually configured AI assistants designed to investigate infrastructure using live operational data and natural language interaction.

Instead of relying primarily on manual investigations across multiple tools and sessions, engineers can interact with an Agent to review system statistics such as CPU usage, memory utilization, disk usage, and other operational data, investigate potential issues or anomalies, and receive suggested solutions or recommendations based on collected findings.

Diagnostic commands executed against your infrastructure and retrieved results are visible in the chat interface, providing transparency and investigation history. By configuring Infrastructure Filters, AI model preferences, notifications, and cost limits, teams can create purpose-built Agents for specific environments and operational use cases.

Overview of Agent Fields and Options

Below is a detailed explanation of the fields available when creating or managing an Agent. Understanding these fields helps ensure your agent is correctly connected to your infrastructure and configured for your operational requirements.

ID (String): This is a unique identifier automatically assigned to the Agent when it is created. The system uses it to track, reference, and manage this specific agent. This value is auto-generated and cannot be modified.

User ID (Namirasoft Account’s ID): This is the unique identifier of the Namirasoft Account user who owns this Agent. It is used internally for permission control, audit logging, and access management.

Workspace ID (Namirasoft Workspace’s ID): This is the identifier of the workspace this Agent belongs to, as defined in Namirasoft Workspace. A workspace is a shared organizational space where teams group their agents, projects, and members, similar to a company account in other platforms.

Project ID (Namirasoft Infra’s Project ID): This is the Namirasoft Infra Project this Agent is scoped to. A Project is a logical container that groups related infrastructure components together. For example, all servers and databases belonging to a specific product or team can be organized under one Project. The agent will only query infrastructure that belongs to this Project.

For more information, visit the Namirasoft Infra Project Console Guide.

Environment ID (Namirasoft Infra’s Environment ID): This is the Namirasoft Infra Environment this Agent operates within. An Environment represents a stage in your operational workflow, such as production, staging, or development. The agent will only query infrastructure within this Environment, preventing accidental access to data from other stages.

For more information, visit the Namirasoft Infra Environment Console Guide.

Target Topic ID (Namirasoft Notification Sender’s Topic ID): This is the Topic in Namirasoft Notification Sender used to receive alerts and deliver investigation reports between the Namirasoft Expert AI agent and Namirasoft Notification Sender. External systems publish alerts to this Topic to trigger automated investigations. The agent also publishes investigation reports back to this Topic, routing results to your configured subscribers such as SMS, Email, Slack, Telegram, or Microsoft Teams.

This field is optional. If it is not set, the agent will not send any notifications.

For more information, visit the Topic Console Guide.

Log Group ID (Namirasoft Log’s Log Group ID): This is the Log Group in Namirasoft Log where logs from this Agent’s activity are stored.

This field is optional. If it is not configured, logs collected from Agent activity will not be stored in Namirasoft Log.

For more information, visit the Log Group Console Guide.

Name (String): This is a label used to identify this Agent in the console. A good name clearly describes the agent’s purpose or the infrastructure it covers. For example: “Production API Server Monitor” or “Database Health Agent”.

LLM Mini Provider (Enum): This is the AI provider used for the Mini model, which handles routine queries where speed and cost efficiency matter, such as checking current CPU usage or confirming whether a service is running. Supported providers include OpenAI, Anthropic, and DeepSeek. Available models for each provider are displayed in the console.

LLM Mini Model (String): This is the specific model from the Mini provider that the Agent uses for routine queries — things like checking current CPU usage, confirming whether a service is running, or fetching a quick log summary. Choose a model that balances speed and cost for everyday operations.

For example, a question like “What is the current CPU usage on the production server?” is a good candidate for the Mini model.

LLM Full Provider (Enum): This is the AI provider used for the Full model, which handles complex investigations where analytical depth matters more than speed, such as diagnosing a memory leak or tracing the root cause of recurring errors across multiple services. Supported providers include OpenAI, Anthropic, and DeepSeek. Available models for each provider are displayed in the console.

LLM Full Model (String): This is the specific model from the Full provider that the Agent uses for complex investigations — things like diagnosing why memory has been climbing over the past 6 hours, or correlating errors across multiple services. Choose a model that prioritizes analytical depth over speed.

For example, a question like “Why has memory usage been climbing on the database server over the past 6 hours?” is a good candidate for the Full model.

Filter: Filters restrict the resources an Agent can investigate within its configured scope.

Some infrastructure types and related filter options may not currently be available. For current supported infrastructure types and coverage details, visit the Coverage page.

Filter Cloud (Enum): This filter restricts the Agent to investigate only a specific Cloud entity configured in Namirasoft Infra.

Filter Server (Enum): This filter restricts the Agent to investigate only a specific Server configured in Namirasoft Infra. For example, you can restrict the Agent to a specific Linux server to focus all investigations on that machine.

Filter Kubernetes (Enum): This filter restricts the Agent to investigate only a specific Kubernetes cluster configured in Namirasoft Infra.

Filter Database (Enum): This filter restricts the Agent to investigate only a specific Database entity configured in Namirasoft Infra.

Filter Cache (Enum): This filter restricts the Agent to investigate only a specific Cache entity configured in Namirasoft Infra.

Filter Messaging (Enum): This filter restricts the Agent to investigate only a specific Messaging entity configured in Namirasoft Infra.

Filter Streaming (Enum): This filter restricts the Agent to investigate only a specific Streaming entity configured in Namirasoft Infra.

Filter Metric (Enum): This filter restricts the Agent to investigate only a specific Metric entity configured in Namirasoft Infra.

Maximum Cost Per Run (USD): Maximum Cost Per Run limits how much this Agent can spend on a single execution. Once the limit is reached, the run stops.

Maximum Cost Per Chat (USD): Maximum Cost Per Chat limits how much this Agent can spend in a single chat session. Once the limit is reached, the session stops accepting new queries.

Maximum Cost Per Day (USD): Maximum Cost Per Day limits how much this Agent can spend in a single calendar day. Resets automatically at midnight.

Maximum Cost Per Week (USD): Maximum Cost Per Week limits how much this Agent can spend in a single calendar week. Resets automatically at the start of each week.

Description (String): This is a free-text field for documenting the purpose, scope, or special notes about this Agent. For example: “Monitors the production API server cluster. Restricted to server and database filters. Alert topic connected to the on-call Slack channel.” This field is especially helpful for teams managing multiple agents across different environments.

Created At (DateTime): This is the date and time when this Agent was created. This value is automatically generated and cannot be modified.

Updated At (DateTime): This is the date and time when this Agent configuration was last modified. This value is updated automatically whenever any field is changed.

Ready to Configure Your AI Agent?

Get Started Explore Console Guide