Productivity
sales-ai-assistant avatar

sales-ai-assistant

An AI-powered sales assistant that transforms business scenarios into optimized prompts, automatically generating high-quality emails, proposals, and analysis reports without requiring prompt engineering skills.

Introduction

Sales AI Assistant is a specialized tool designed for sales professionals to streamline content creation workflows. By utilizing a structured scenario-based framework, it eliminates the learning curve typically associated with advanced prompt engineering. The tool intelligently identifies user intent and maps it to one of 25 predefined sales scenarios—ranging from cold outreach and demo follow-ups to complex competitive battlecards and pipeline data analysis—ensuring that the generated output is professional, relevant, and immediately actionable.

  • Intelligent Scene Recognition: Employs a scoring algorithm to match user inputs against 25 specific sales scenarios, including email outreach, strategic account planning, and competitor analysis.

  • Smart Information Extraction: Automatically parses user inputs for key variables (company names, job roles, product value propositions) and prompts for missing data in a single, efficient step.

  • Standardized Output Formatting: Generates high-quality sales materials including emails, strategic proposals, and data analysis summaries formatted for immediate professional use.

  • Learning-Oriented Design: Displays the optimized background prompt alongside every generated result, allowing users to learn how to structure their own future queries.

  • Feedback Loop Integration: Supports quick refinement commands such as 'more formal,' 'more concise,' or 'add data evidence,' enabling users to iterate on content without starting over.

  • Users should describe their sales requirement in natural language to trigger the assistant's identification process.

  • The assistant operates by identifying key keywords (e.g., cold mail, demo follow-up, conversion rate) to select the most appropriate template.

  • Expected inputs range from simple natural language requests to structured data (like CSV formats for pipeline analysis).

  • Constraints include staying within the provided 6 high-frequency templates or 19 additional specialized references.

  • Practical tips: Users can ask for 're-generation' or 'scenario changes' if the initial match does not perfectly align with their specific business goal.

Repository Stats

Stars
80
Forks
14
Open Issues
1
Language
Python
Default Branch
main
Sync Status
Idle
Last Synced
May 3, 2026, 05:37 PM
View on GitHub