Deepline Analytics

# Deepline Analytics

Use this skill to answer customer analytics questions through Deepline's warehouse and semantic-layer tools. The goal is not just to run SQL; it is to preserve the customer's business definitions by starting from the semantic layer, validating the query path, and reporting exactly what metric definitions and filters were used.

## Before You Start

Use `deepline-gtm` instead when the task is prospecting, enrichment, contact finding, outbound sequencing, personalization, or row-by-row lead/account research. Analytics questions ask about existing customer data: revenue, pipeline, funnel, conversion, retention, usage, calls, accounts, opportunities, or warehouse tables.

If Snowflake credentials or a semantic layer are missing, stop and report the setup blocker. Guessing table names or falling straight to raw SQL hides the actual problem and usually produces incorrect business definitions.

## Decision Matrix

| User asks... | Job | Start with |
| --- | --- | --- |
| "What is total pipeline by quarter?" | Metric breakdown | `snowflake_get_semantic_layer`, then `snowflake_run_semantic_query` |
| "Break revenue down by product/month" | Dimensional analysis | Inspect semantic tables for revenue metrics and time dimensions |
| "How many opportunities / accounts / calls..." | Simple count metric | Find the semantic count metric before writing SQL |
| "Why does this number look wrong?" | Debug/validation | Run semantic query, inspect returned SQL, then compare with raw SQL only if needed |
| "Query this specific warehouse table" | SQL fallback | Check whether it is represented in the semantic layer; otherwise use `snowflake_run_query` |
| "Upload/edit/read the semantic layer" | Admin setup | Use `snowflake_update_semantic_layer` / `snowflake_get_semantic_layer`, then return here for querying |

## Standard Loop

Use the Deepline CLI for these tools. `snowflake_get_semantic_layer` and `snowflake_run_semantic_query` are Deepline tool IDs invoked with `deepline tools execute ...`; do not search for MCP/deferred tool names first.

1. **Confirm workspace context.** If the result depends on customer setup, run `deepline auth status` so you know which workspace receives the query.
2. **Inspect the semantic layer.** Run `deepline tools execute snowflake_get_semantic_layer ...` before constructing payloads. Use `includeYaml: false` for a quick table list, and `includeYaml: true` when choosing exact metrics, dimensions, or filters.
3. **Map the user's words to semantic objects.** Choose one semantic `table_name`, named `metrics`, named `dimensions` or `time_dimensions`, and named `filters` from the YAML. Do not invent them.
4. **Pilot the smallest useful query.** Start with one metric and low `rowLimit`; expand after it succeeds. This catches missing credentials, missing semantic objects, and warehouse schema drift cheaply.
5. **Inspect returned SQL and rows.** `snowflake_run_semantic_query` returns both result rows and rendered SQL. The SQL is the audit trail and the safest starting point for any raw-SQL fallback.
6. **Answer in business terms.** Name the metric, grouping dimensions, filters/base filters, row limits, and caveats. If the tool says results were limited, say that.

## Fastest Metric Path

For a customer metric question where the semantic table is knowable from the wording, use this exact CLI path. Do not call ToolSearch, do not look for MCP tools, and