Guided analysis involves complex data exploration, combining manual and automated steps, with actors including backend systems, extraction services, AI models, and user interfaces, focused on data analysis and AI-driven insights.

HBS Economics worked as a consultant on the SVGV Budget Analysis Project. HBS Economics is one of the consulting firms involved in the SVGV Budget Analysis Project.

The DOCX extractor will track heading hierarchy levels to enable semantic section boundary detection during chunking.

The Docker deployment includes Health checks for components. The Docker deployment uses health checks for monitoring service health Backend API implements health checks exposing HTTP GET / to validate readiness. Frontend implements health checks exposing HTTP GET / for availability verification.

Design element specifying entity attributes, including element_type and identification rules, appears complete and up-to-date based on the message.

The DataLens Project exposes a high-level API through lib/datalens.py. lib/datalens.py API interacts with DuckDB for data storage and querying.

SvelteKit page at route / displaying DataLens interface. Home page is implemented as a SvelteKit page. Home page is part of the DataLens system. The Home page is part of the DataLens project.

DataLens Agent Mode communicates with IronClaw via HTTP webhooks and WebSocket for integration.

DataLens is deployed to and runs live at https://datalens.exerun.com after Ops Engineer approval.

httpx is used as part of tests covering the FastAPI app implementation of the DataLens Platform. Httpx is used in tests with pytest and pytest-asyncio for async HTTP testing compatibility.

User story with goal to accurately calculate and display total budget reduction between 2025 and 2028, a key analytical question.

The Hybrid (manual + AI-Assist) Approach uses Claude to generate a detailed project goal from a brief description. AI Generated Goals are derived using the Hybrid (manual + AI-Assist) Approach combining user brief input with AI expansion via Claude.

DataLens implements Hybrid Search combining semantic search with Qdrant vectors and structured Text-to-SQL on DuckDB. Document RAG incorporates a hybrid SQL+RAG orchestrator to combine structured and unstructured queries.

Translation file for Danish UI strings, supporting multilingual UI.

Translation file for English UI strings, part of internationalization setup.

Typescript setup for i18n utilities, managing language switching and translations.

The Discovery Service applies the ID matching join strategy for join discovery with 85% confidence.

The PPTX extractor will extract image metadata such as image counts and types for added document context without OCR in Phase 2.

PHASE2_SCOPE_DECISION.md contains the IMPLEMENTATION_PLAN.md design element. PHASE2_SCOPE_DECISION.md includes IMPLEMENTATION_PLAN.md as part of the Phase 2 research outputs. Phase 2 research outputs include IMPLEMENTATION_PLAN.md as a component of research.

A system view in SQL databases used to retrieve metadata about existing tables, crucial for detecting and managing schema changes during the data extraction and consolidation processes.

Infrastructure includes GPU usage as a monitored specification. Infrastructure includes Disk space as a monitored specification. Infrastructure includes Network as a monitored specification. The DataLens Master Implementation Plan depends on the Infrastructure specification to manage computational resources and environment. DataLens Master Implementation Plan depends on the operational Infrastructure for deployment and execution. The implementation plan builds upon the existing infrastructure.

DataLens must read and follow the INFRASTRUCTURE.md document during every session before work. DataLens agent must read and follow the infrastructure rules documented in INFRASTRUCTURE.md before starting work. INFRASTRUCTURE.md reserves port 8002 for the DataLens backend. INFRASTRUCTURE.md reserves port 8002 for DataLens backend.

The Frontend uses Input.svelte UI component.

Insight physical table holds insights derived from project data. The insights table has a project_id column that links each insight to a project. Query physical table generates Insight physical table containing analytical insights from executed queries. Insight physical table is derived from AgentFinding data entity representing findings extracted by the agent. Projects possess insights tables which store generated insights tied to project data analysis.