Feature Overview (aka. Goal Summary)  

An elevator pitch (value statement) that describes the Feature in a clear, concise way.  Complete during New status.

In OCP5, we want to deliver an AI-powered visualization experience for Perseus. Via OpenShift Lightspeed, the user uses to instantly generate UI widgit (chart), that is interactive and allows drilldown, that can be saved directly into their Perses dashboard.

Goals (aka. expected user outcomes)

The observable functionality that the user now has as a result of receiving this feature. Include the anticipated primary user type/persona and which existing features, if any, will be expanded. Complete during New status.

Make PromQL accessible. Users can generate complex, PatternFly-themed Perseus charts simply by using natural language in the OpenShift LightSpeed interface, eliminating the need to manually write complex PromQL queries.

• Leverage OpenShift LightSpeed (OLS) for natural language input for rendering Perseus charts and widgets in OLS, and integration of Perseus charts and widgets into the OpenShift Perses dashboard page, where they are available for monitoring purposes.

Requirements (aka. Acceptance Criteria):

A list of specific needs or objectives that a feature must deliver in order to be considered complete.  Be sure to include nonfunctional requirements such as security, reliability, performance, maintainability, scalability, usability, etc.  Initial completion during Refinement status.

• System must reliably translate natural language prompts within OpenShift LightSpeed (OLS) into a correct and functional Perses chart or widget.
• The OLS generated chart/widget must allow for refresh and drilldown capabilities, as well as the ability to interact with the visualization to understand what is shown.
• User has option to save the Perses chart or widget to a new Perses Dashboard or existing Perses Dashboard (as a panel).
• The saved Perses chart or widget must be accessible to the same user from the designated Perses dashboard landing page.
• The resulting chart in Perses Dashboard, once added to the Perses Dashboard, must be editable using ** native Perseus mechanisms (e.g., YAML editing or Console tools) to ensure full customizability.
• Perses chart/widget generation time must be fast and consistent. If expected to take longer than expected, OLS must provide feedback about to inform user transaction is being processed.
• If the MCP apps approach is utilized, the resulting Perseus view must also be successfully surfaced and accessible in multiple clients (e.g., Claude or Gemini).

Anyone reviewing this Feature needs to know which deployment configurations that the Feature will apply to (or not) once it's been completed.  Describe specific needs (or indicate N/A) for each of the following deployment scenarios. For specific configurations that are out-of-scope for a given release, ensure you provide the OCPSTRAT (for the future to be supported configuration) as well.

Use Cases (Optional):

Include use case diagrams, main success scenarios, alternative flow scenarios.  Initial completion during Refinement status.

• Accelerated Perses Dashboard Creation
  • Use Case: A user wants to build a new monitoring (Perses) dashboard for a specific microservice.
  • Action: The user types a simple request into OpenShift LightSpeed, such as: "Show a line chart for the last 12 hours of CPU utilization for all pods in the 'dev-frontend' namespace, grouped by deployment."
  • Outcome: OLS generates the correct PromQL, renders the Perseus chart preview, and upon user confirmation, pushes the fully configured chart as a widget to the target dashboard.
• On-the-Fly Troubleshooting Visualization
  • Use Case: A Site Reliability Engineer (SRE) notices an issue and needs a quick, non-standard visualization to check a hypothesis.
  • Action: The SRE prompts: "Generate a bar chart comparing the total memory usage of the 'database' stateful set versus the 'caching' deployment over the past 30 minutes."
  • Outcome: A time-sensitive, custom chart is immediately generated and displayed, enabling rapid analysis without manual PromQL construction or navigating complex console menus.
• PromQL Simplification for Custom Metrics
  • Use Case: A developer wants to visualize a custom, application-specific metric they just exposed, but they are unfamiliar with the required PromQL syntax.
  • Action: The user enters: "Create a gauge for my application's 'checkout_conversion_rate' metric over the last hour."
  • Outcome: The system handles the necessary metric selection and aggregation, generating a viewable, real-time chart that can be saved to a dashboard, making advanced metrics accessible to all users.
• Multi-Client Sharing (via MCP apps sub-option)
  • Use Case: A cluster admin wants to access one or more observability KPIs from OpenShift Monitoring via a 3rd party MCP Host (e.g., VS Code or an internal chat app).
  • Action: The user provides text-based prompt to generate a chart in the 3rd party MCP host.
  • Outcome: Because the view is powered by an MCP app, the chart's visualization can be rendered consistently across other MCP hosts as long as they support MCP apps rendering.

Questions to Answer (Optional):

Include a list of refinement / architectural questions that may need to be answered before coding can begin.  Initial completion during Refinement status.

The following options are being considered:

• Native Perseus Approach: Ensures users retain the ability to edit the chart using native Perseus tools after it's generated, maintaining full customizability.
• MCP Apps Approach: While allowing the view to be surfaced in multiple MCP hosts/clients (like Claude or Gemini), it comes with the risk that the UI might be static and hardcoded, limiting the user's ability to customize the chart post-generation.

Out of Scope

High-level list of items that are out of scope.  Initial completion during Refinement status.

<your text here>

Background

Provide any additional context is needed to frame the feature.  Initial completion during Refinement status.

• Every team running OpenShift sits on a gold mine of operational intelligence, and most can't access it because they lack PromQL mastery.
• A conversational AI layer on Perses enables developers, SREs, and platform engineers to simply describe the visualization they want, which then generates production-ready, GitOps-native, dashboard-as-code dashboards.
• Higher fidelity PromQL generation through automated validation against real-world cluster metrics. 
• Other tools in the market: Grafana Assistant, Dynatrace Davis CoPilot, Kagent (PromQL Agent generates PromQL but not Perses widget). 

Customer Considerations

Provide any additional customer-specific considerations that must be made when designing and delivering the Feature.  Initial completion during Refinement status.

<your text here>

Documentation Considerations

Provide information that needs to be considered and planned so that documentation will meet customer needs.  If the feature extends existing functionality, provide a link to its current documentation. Initial completion during Refinement status.

<your text here>

Interoperability Considerations

Which other projects, including ROSA/OSD/ARO, and versions in our portfolio does this feature impact?  What interoperability test scenarios should be factored by the layered products?  Initial completion during Refinement status.

<your text here>