answering-natural-language-questions-with-dbt

# Answering Natural Language Questions with dbt

## Overview

Answer data questions using the best available method: semantic layer first, then SQL modification, then model discovery, then manifest analysis. Always exhaust options before saying "cannot answer."

**Use for:** Business questions from users that need data answers
- "What were total sales last month?"
- "How many active customers do we have?"
- "Show me revenue by region"

**Not for:**
- Validating model logic during development
- Testing dbt models or semantic layer definitions
- Building or modifying dbt models
- `dbt run`, `dbt test`, or `dbt build` workflows

## Decision Flow

```mermaid
flowchart TD
    start([Business question received])
    check_sl{Semantic layer tools available?}
    list_metrics[list_metrics]
    metric_exists{Relevant metric exists?}
    get_dims[get_dimensions]
    sl_sufficient{SL can answer directly?}
    query_metrics[query_metrics]
    answer([Return answer])
    try_compiled[get_metrics_compiled_sql<br/>Modify SQL, execute_sql]
    check_discovery{Model discovery tools available?}
    try_discovery[get_mart_models<br/>get_model_details<br/>Write SQL, execute]
    check_manifest{In dbt project?}
    try_manifest[Analyze manifest/catalog<br/>Write SQL]
    cannot([Cannot answer])
    suggest{In dbt project?}
    improvements[Suggest semantic layer changes]
    done([Done])

    start --> check_sl
    check_sl -->|yes| list_metrics
    check_sl -->|no| check_discovery
    list_metrics --> metric_exists
    metric_exists -->|yes| get_dims
    metric_exists -->|no| check_discovery
    get_dims --> sl_sufficient
    sl_sufficient -->|yes| query_metrics
    sl_sufficient -->|no| try_compiled
    query_metrics --> answer
    try_compiled -->|success| answer
    try_compiled -->|fail| check_discovery
    check_discovery -->|yes| try_discovery
    check_discovery -->|no| check_manifest
    try_discovery -->|success| answer
    try_discovery -->|fail| check_manifest
    check_mani