ResolveSx/Resolve Assist - An Introduction

Modified on Mon, 13 Jan at 4:58 AM

Introduction

ResolveSx/Resolve Assist leverages advanced AI technologies, including GPT and Natural Language Processing (NLP), to extract and utilize knowledge from various organizational sources such as Salesforce, Jira, Confluence, and Slack. The solution delivers precise answers through customer-facing systems, such as Salesforce CRM, customer portals, and chatbots, ensuring a seamless and efficient user experience.


How It Works

Precision RAG (Retrieval Augmented Generation)

Precision RAG is at the core of ResolveSx/Resolve Assist. it helps with:

  • Collects and organizes data from diverse sources for accurate question-answering.

  • Uses sophisticated retrieval techniques to find the most relevant information.

  • Automatically evaluates queries using Guardrails for relevance and ensures responses are accurate and domain-specific.

This approach minimizes errors related to irrelevant topics or incomplete data, delivering reliable and precise answers to users.



Architecture Diagram - High level





Supported Knowledge Sources

ResolveSx/Resolve Assist supports a wide range of textual knowledge sources, including voice transcriptions. Out-of-the-box integrations include:

  • Customer Support Platforms: Salesforce, Zendesk

  • Knowledge Management Tools:

    • Mindtouch

    • KnowledgeOwl

    • Salesforce Knowledge

    • Zendesk Articles

    • Atlassian (Confluence, Jira)

    • Notion

    • Paligo

    • GetGuru

    • Gitbook

    • Magentrix

    • HigherLogic

    • Doc360

  • Collaboration Tools: Slack, MS Teams

  • Content Management Systems: Sitecore



Note: ResolveSx/Resolve Assist capabilities may vary depending on the package you have purchased.




Was this article helpful?

That’s Great!

Thank you for your feedback

Sorry! We couldn't be helpful

Thank you for your feedback

Let us know how can we improve this article!

Select at least one of the reasons
CAPTCHA verification is required.

Feedback sent

We appreciate your effort and will try to fix the article