CoPilot Overview

TigerGraph CoPilot combines two of the most powerful technologies for extracting value from a knowledge base — LLMs and graph databases. This combination delivers superior AI performance — more accuracy and greater contextual relevance.

It features:

  • Natural Language Inquiry: The product’s natural-language and auto-execution capabilities empower non-technical users to focus on mining insights from their data through an AI assistant that they can “talk” to. Rather than having to learn a new technology or language when a question is posed in natural language, TigerGraph CoPilot determines the best available query needed to answer that question, runs the query, and returns the results in natural language, graph visualizations and other ways a user can more clearly understand.

  • Graph-Augmented Generative AI: TigerGraph CoPilot creates chatbots with augmented AI on a user’s own documents. The tool builds a knowledge graph from source material and applies graphRAG (graph-based Retrieval Augmented Generation) to improve the contextual relevance and accuracy of answers to their natural-language questions.

  • Reliable and Responsible AI: TigerGraph CoPilot mitigates AI hallucination by allowing LLMs to access the graph database via curated queries. It also adheres to the same role-based access control and security measures (already part of the TigerGraph database) to assure responsible AI. TigerGraph CoPilot also enables transparency by open-sourcing its major components and allowing users to choose their LLM service.

  • High Scalability and Performance: By leveraging the TigerGraph database — the most scalable and performant platform for connected data — TigerGraph CoPilot runs graph analytics and obtains insights from a graph much faster than other LLM-graph solutions. As a graph-RAG solution, it is able to utilize knowledge bases at a much larger scale than other knowledge graph-powered Q&A solutions.

Example Use Cases

TigerGraph CoPilot has a wide variety of use cases and even more out there to be discovered. Here are some example use cases for TigerGraph CoPilot.

Natural Language to Data Insights

Whether you are business analysts, specialists, or investigators, CoPilot enables you to get information and insights quickly from your data.

For example:

  • It can generate reports for fraud investigators by answering questions like:

    “Show me the list of recent fraud cases that were false positives";

  • It facilitates more accurate investigation like:

    “Who had transactions with account 123 in the past month with amounts larger than $1000”.

What further differentiates TigerGraph CoPilot from similar products is that it can even answer the “what if?” questions by traversing your graph along dependencies.

For example:

  • You can easily find out:

    From a graph with supply chain data:
    “What suppliers can cover the shortage of part 123”
    From a graph with digital infrastructure data:
    “What services would be affected by an upgrade to server 321”

Accurate, Context-Rich Q&A Solution

TigerGraph CoPilot provides a complete solution to build Q&A chatbot on your own data and documents.

Its knowledge graph-based RAG approach enables contextually accurate information retrieval that facilitate better answers and more informed decisions.

This solution directly improves the productivity and reduces the cost in typical Q&A applications such as call centers, customer services, knowledge search, and so on; but by merging the document knowledge graph with existing business graph (e.g., product graph) into one intelligence graph, CoPilot can tackle problems that cannot be addressed by other RAG solutions.

For example:

  • By combining your customer’s purchase history with product graphs, we can get more accurate personalized recommendations when customers type in their search queries or ask for recommendations.

  • By combining your patient’s medical history with healthcare graphs, doctors or health specialists can get more useful information about the patients to provide better healthcare or precision healthcare.

Next Steps

Next, learn how to Get Started with TigerGraph CoPilot or go deeper learn about TigerGraph CoPilot’s Architecture Overview

Return to TigerGraph CoPilot Overview page for a different topic.