Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[FE] Report Widget #132

Open
01painadam opened this issue Jan 31, 2025 · 0 comments
Open

[FE] Report Widget #132

01painadam opened this issue Jan 31, 2025 · 0 comments
Assignees

Comments

@01painadam
Copy link
Collaborator

01painadam commented Jan 31, 2025

Goal

Implement a long-form report widget that generates a comprehensive portfolio report using data and metadata from multiple KBAs. The report should be dynamically generated based on RAG-sourced data and tailored to the selected user persona.

Users should be able to:

  • Generate a structured report summarising key insights across all KBAs in their portfolio. This should be initiated via chat. See examples of possible prompts.
  • Edit and refine the report using quick-select buttons or chat-based interactions
  • Save the customised report to the dashboard for reference and sharing

Designs

Example outputs can be seen here

Report Structure

The report provides a detailed overview of key metrics, trends, and contextual insights across the user’s KBA portfolio.

Report Sections

The report consists of dynamically generated sections, including for example:

  1. Executive Summary – High-level overview of key insights
  2. Portfolio Overview – Number of KBAs, total area, key species and habitats, people/orgs
  3. Key Findings (aggregated across the portfolio)
  4. Threats & Risks – Identified pressures (e.g. deforestation, habitat conversion)
  5. Opportunities & Interventions – Potential conservation actions based on data
  6. Data Sources & Limitations – Citations, disclaimers, and methodological notes

Title and Summary Text

The report is dynamically generated by the LLM and tailored to the user persona.

Summary Content Requirements

  • Quantitative data retrieved from RAG
  • Qualitative insights from KBA factsheets (also in RAG)
  • Persona-specific framing to match user needs and expertise
  • Data sources, citations, or disclaimers for transparency

Edit/Save Interface

The widget allows users to refine the report content by:

  • Chat-based editing for custom modifications
  • Option to regenerate specific sections based on new criteria
  • "Add to Dashboard" button to save the final report

Scope

In Scope

  • Automated report generation from portfolio-wide RAG data
  • Persona-based language adaptation
  • Chat-based editing

Out of Scope

  • Editing does not persist previous report versions
  • No ability to regenerate specific sections
  • Ability to save the final report to the dashboard

Job Stories & Acceptance Criteria

Generating a Report

When I need to understand the status of my KBA portfolio,
I want to generate a long-form report summarising key insights,
So that I can make informed decisions based on consolidated data.

Acceptance Criteria:

  • The report includes structured sections covering key metrics, threats, and opportunities
  • The report aggregates relevant data from all KBAs in the portfolio

Persona-Based Framing

When I generate a report,
I want to receive insights presented in a way that matches my expertise and domain,
So that I can easily interpret and act on the findings.

Acceptance Criteria:

  • The report language is adjusted based on the selected user persona
  • The LLM ensures accessibility and relevance for different expertise levels

Editing & Refinement

When I review my report,
I want to modify the language and level of detail,
So that the report is better suited to my needs.

Acceptance Criteria:

  • Users can edit sections manually via chat
  • Changes are applied to the final saved version

Saving to Dashboard

When I finalise my report,
I want to save it to my dashboard,
So that I can access 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 persona customisation

Risks & Questions

  • How do we handle missing or incomplete data across KBAs?
  • Should users be able to generate alternative report formats (e.g. PDF export)?
  • When asking general questions in the chat, should the output have the option of being a report widget?

Solution Hints

  • Use structured sections for readability and clarity
  • Ensure summary text is concise but informative, adapting to user personas
  • Allow non-destructive edits with preview before saving

Future Work

Enhanced Reporting Features

  • Export (e.g. PDF, Word)
  • Interactive elements (e.g. expandable sections, inline editing, embedded charts)
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants