[FE] MD Table / Ranked List widget

[01painadam]

Goal

Implement a simple markdown table ranking list widget that orders KBAs within a portfolio based on a selected metric. The ranking should be dynamically generated from RAG-sourced data and support user-driven metric selection.

Users should be able to:

• View a ranked list of KBAs based on a selected metric
• Change the ranking metric to reorder the list
• Edit the summary text to reflect insights about the ranking
• Save the customised ranking to the dashboard

Designs

Ranking List

A simple, structured markdown list displaying KBAs ranked by a selected metric.

Supported Metrics

Users can rank KBAs by various quantitative indicators, including:

• Tree cover loss, gain, or extent (ha)
• Protected Area coverage (%)
• Forest carbon emissions (Mg CO2e)
• Natural/semi-natural grassland area (ha)
• Gross Primary Productivity (gC per m²)
• Biodiversity importance (e.g. no of species or other dat pulled from RAG)

List Features

• Numbered ranking of KBAs
• Metric displayed for each KBA (e.g. "KBA Name – 5,600 ha tree cover loss")
• Ability to change the ranking metric from a predefined set

Title and Summary Text

Each ranked list is accompanied by dynamically generated summary text, tailored to the user persona via LLM processing.

Summary Content Requirements

• Quantitative ranking data retrieved from RAG
• Qualitative insights from KBA factsheets (also in RAG)
• Data sources, citations, or disclaimers for transparency
• Title automatically generated by LLM

Edit/Save Interface

The widget allows users to customise the ranking list by:

• Selecting a different ranking metric, which updates the order dynamically
• Editing the summary text using:
  • Concise – Shortens the summary
  • Simplify – Adjusts language for accessibility
  • Explain – Adds detail and context
• Manual ranking adjustments, if necessary
• Saving the final version to the dashboard

Scope

In Scope

• Ranked list generated from selected RAG metric
• Persona-based summary text generation
• Chat based editing, quick-select refinements
• Ability to change the ranking metric and order (asc/desc)
• Ability to save the final output to the dashboard

Out of Scope

• Editing does not persist previous versions of rankings
• No full customisation of ranking logic beyond predefined metrics
• No multi-metric rankings or weighted scoring

Job Stories & Acceptance Criteria

Viewing a Ranked List

When I am analysing KBAs in my portfolio,
I want to see a ranked list based on a key metric,
So that I can identify high-priority areas for action.

Acceptance Criteria:

• The ranked list correctly displays KBAs ordered by the selected metric
• Each KBA entry includes the metric value

Changing the Ranking Metric

When I want to compare KBAs by a different metric,
I want to change the ranking criteria,
So that I can analyse different aspects of KBA performance.

Acceptance Criteria:

• Users can select a different ranking metric from a predefined list provided by chat
• The ranking updates dynamically based on the new metric

Summary Text Generation

When I am reviewing a ranked list,
I want to see a natural-language summary alongside it,
So that I can quickly interpret the key insights.

Acceptance Criteria:

• The LLM generates summary text based on the ranking and user persona
• The summary includes quantitative data, qualitative insights, and citations where relevant

Summary Editing & Refinement

When I want to adjust the generated summary,
I want to modify the text using quick actions or chat,
So that I can tailor the insights to my communication needs.

Acceptance Criteria:

• Quick-select buttons adjust summary length and complexity
• Users can manually edit the summary or request changes via chat
• The final edited version is saved when added to the dashboard

Saving to Dashboard

When I finalise a ranking list and its summary,
I want to save it to my dashboard,
So that I can reference it later or share it with others.

Acceptance Criteria:

• Clicking "Add to Dashboard" saves the final edited version
• The saved version retains all edits and metric selections

Risks & Questions

Data Integrity

• How do we handle missing or incomplete data for ranking metrics?
• Should we offer fallback descriptions if certain metrics are unavailable?

LLM Processing

• Should summary generation be fully automated, or should users confirm the text before saving?
• How do we ensure the LLM maintains factual accuracy and does not over-interpret rankings?

Solution Hints

• Use a structured layout with clear ranking numbers and metric labels
• Ensure summary text is concise but informative, adapting to user personas
• Allow simple, non-destructive edits with preview before saving

Future Work

Enhanced Ranking Features

• Multi-metric ranking (e.g. weighted scoring)
• Comparative rankings across different different unit e.g. regions or countries