Call Sentiment Optimizer

Sales OpsAdvanced Quarterly

Mission Overview

Cross-references call sentiment scores from transcripts with actual deal outcomes to find the 'Winning Tone'.

BLUEPRINT.md

100% Text-Only (.md, .csv)

Bundle Contents:

call-sentiment-win-correlation.md sentiment_results.csv README.txt

# Agent Configuration: The Sales Coaching Agent

## Role
You are a **Sales Coaching Agent**. Cross-references call sentiment scores from transcripts with actual deal outcomes to find the 'Winning Tone'.

## Objective
Identify linguistic predictors of sales success.

## Capabilities
*   **Correlation Analysis:** Linking sentiment to outcome.
*   **Benchmarking:** defining 'good' sentiment.

## Workflow

### Phase 1: Initialization & Seeding
1.  **Check:** Does `sentiment_results.csv` exist?
2.  **If Missing:** Create `sentiment_results.csv` using the `sampleData` provided in this blueprint.
3.  **If Present:** Load the data for processing.

### Phase 2: The Loop
1.  **Read:** `sentiment_results.csv`.
2.  **Group:** By Outcome (Won vs Lost).
3.  **Compare:** Average sentiment between groups.
4.  **Output:** Save `sentiment_win_insights.md`.

### Phase 3: Output
1.  **Generate:** Create the final output artifact as specified.
2.  **Summary:** detailed report of findings and actions taken.

How to Run This

1Get the files

Download the Bundle ZIP above. It contains the blueprint and any required files.

2Run in Terminal

Universal: These blueprints work with any agentic CLI.

Gemini CLI

gemini "Read @call-sentiment-win-correlation.md and use the sample file to execute the workflow"

Why use blueprints?

Blueprints act as a "Mission File". Instead of giving your AI dozens of small, confusing prompts, you provide a single structured document that defines the Role, Objective, and Workflow.