demoprep / PROJECT_STATUS.md
mikeboone's picture
Feb sprint: vertical×function matrix, structured outliers, unified prompts
3b2cd7b

A newer version of the Gradio SDK is available: 6.12.0

Upgrade

Demo Wire - Project Status

Purpose: Single source of truth for overall project state. Updated at the end of each sprint.


What Is Demo Wire?

An AI-powered demo builder for ThoughtSpot that automatically creates complete demo environments:

  • Snowflake schemas and realistic data
  • ThoughtSpot connections, models, and liveboards
  • Conversational chat interface for demo creation

Goal: Create the "perfect demo" that helps sell Thoughtspot's data analytics, bi and ai and software effectively.


Development Phases

Phase 1: Button-Driven App ✅ COMPLETE

  • Original Gradio UI with button-based workflow
  • Research → DDL → Population → Deploy → Model → Liveboard
  • Linear progression through stages

Phase 2: Chat Interface ✅ COMPLETE

  • Conversational AI interface (launch_chat.py, chat_interface.py)
  • Natural language demo creation
  • Works end-to-end through chat

Phase 3: Making It Better 🔄 IN PROGRESS

  • LegitData integration - Realistic data generation (integrated)
  • Outliers - Strategic data points for compelling demos (needs work)
  • snake_case naming - Better ThoughtSpot object names ✅ DONE
  • MCP + TML hybrid - Create with MCP, polish with TML ✅ DONE (Jan 18, 2026)

Current Capabilities

Working:

  • End-to-end demo creation via chat interface
  • Liveboard creation: MCP creates visualizations + TML post-processing for Groups, KPIs, colors
  • LegitData for realistic data generation
  • Supabase settings persistence
  • ThoughtSpot authentication and deployment

Needs Work:

  • Outliers need better integration into liveboard creation
  • Data adjuster has column matching issues
  • Tags not assigning to objects

Key Technical Decisions

Liveboard Creation: MCP creation + TML post-processing

  • MCP (via agent.thoughtspot.app) generates AI-driven visualizations
  • TML post-processing adds Groups, KPI sparklines, brand colors, layout refinement

Data Generation: LegitData

  • Uses AI + web search for realistic data
  • Replaces faker-based scripts

Golden Demo Reference:

  • dev_notes/liveboard_demogold2/🏬 Global Retail Apparel Sales (New).liveboard.tml

Known Concerns

  • Outliers: Was strong in old app, not working well now. Need to revisit.
  • Latest changes: Some recent changes may have broken things. Need to verify.

Sprint History

  • Sprint Feb 2026: Current - see sprint_2026_02.md in root
  • Sprint Jan 2026: Closed - see sprint_2026_01.md in root
  • (Previous sprints archived in dev_notes/archive/)

Last Updated: February 4, 2026