How to Build a RAG-Powered AI Knowledge Base in Momen

Finding specific answers in dense company documents or manuals is a slow process that frustrates both employees and customers. Standard Retrieval-Augmented Generation (RAG) architectures usually require gluing together standalone UI tools, separate vector databases, and API wrappers. This often results in a fragile, black-box system that breaks at scale and demands constant engineering maintenance. Momen eliminates this infrastructure challenge by combining native PostgreSQL database storage, visual logic, and AI agents into a single platform. This allows you to build a cohesive AI assistant that securely answers natural language questions based on your own data.

Understanding RAG-Powered Knowledge Bases and Use Cases

A RAG-powered knowledge base securely connects an AI agent directly to your internal data, enabling it to retrieve and summarize relevant information contextually. It eliminates internal information silos and prevents AI hallucinations by forcing the model to generate answers strictly based on retrieved context.

Use cases include:

• Automating ticket deflection for customer support
• Assisting HR with employee onboarding
• Providing interactive Q&A based on educational course transcripts

When NOT to use it: For simple, static information pages where users don't need dynamic synthesis, or when a basic keyword search suffices.

Read the documentation
See the use case analysis

View project

Introduction

• Goal: Create an intelligent customer support robot that can search a private knowledge base and answer questions based on retrieved content.
• Applicable Scenario: Internal documentation search, smart FAQ, and customer support automation.
• Core Logic: User Input -> AI Agent -> Actionflow (Vector Search) -> Database (Knowledge Base) -> AI Synthesis -> Output.

Steps

Data Storage

• Data Model: Create a table named article.

What is Vector Storage? It converts unstructured text into numerical vectors. This allows the system to find content based on "semantic meaning" rather than just keyword matching.

• CMS Entry: Add several records to the article table to serve as your knowledge base.

Logic & State Configuration

We need an Actionflow to act as a "tool" for the AI Agent to perform the actual search.

Actionflow Construction

• Input: Add a text parameter named question to receive the user's query from the AI.
• Fetch Primary Match:

Add a Query Data node for the article table.

• Sort: Select main_content. Set mode to Vector.
• Function: Choose COSINE (Cosine Similarity).
• Input: Bind to Actionflow input.question.

• Limit: Set to 1 (Returns the most relevant article).

• Fetch Secondary Match:

Add another Query Data node.

• Filter: id is "Not equal to" the ID retrieved in the Primary Match step.
• Sort/Function: Same as above (Vector + COSINE).

• Limit: Set to 1 (Returns the second most relevant article).

• Output: Define four text outputs:

primary_content: From Fetch Primary Match.

• primary_link: From Fetch Primary Match.
• secondary_content: From Fetch Secondary Match.
• secondary_link: From Fetch Secondary Match.

AI Agent Configuration

Navigate to the AI tab to configure your agent's behavior.

• Role:

You are the Momen Support Copilot, a professional and helpful technical assistant for the Momen low-code platform.
Goals:

Your primary goal is to answer user questions accurately by retrieving information from the official knowledge base.

Workflow

1. Once the user asks a question, call the SearchKnowledgeBase tool EXACTLY ONCE. Pass the user's input into the question parameter.
2. The tool will return four outputs from the top 2 matching articles.
3. Evaluate both primary_content and secondary_content:
   • IF RELEVANT INFORMATION IS FOUND: Synthesize a clear, concise answer combining the relevant information from either or both contents.
   • You MUST append the reference links at the end. If both contents were useful and have different links, list both. If only one was useful, list that one. Use this Markdown format for links: [Read Primary Document]({{primary_link}}) [Read Secondary Document]({{secondary_link}}) (Only if applicable)
   • IF BOTH ARE IRRELEVANT OR EMPTY: Do NOT fabricate an answer. Politely reply: "I'm sorry, I couldn't find the exact answer in my current knowledge base. Please check the official Momen documentation."

4. Language: Always reply in the same language the user used to ask the question.
   Constraints:

5. WAIT FOR INPUT: Do NOT call any tools when the conversation starts. You must wait for the user to explicitly ask a question.

6. ONE SEARCH ONLY: You are strictly limited to MAXIMUM 1 tool call per user message. Do NOT retry, loop, or change search keywords if the first search does not return the desired answer.
   Tools: Add the Search Knowledge Base Actionflow. The "tool name" in the prompt should match the tool configuration to avoid call failures due to misunderstandings.

Verification

• Use the Debug window to test the following scenarios:

• ​Exact Match​: Ask about a specific title in your DB.

​Expected​: AI returns the content and exactly one relevant link.

• ​Cross-Document Fusion​: Ask a question covered partially by two docs.

​Expected​: AI combines info from primary and secondary content and provides two links.

• ​Out-of-Scope (Safety Check)​: Ask something irrelevant (e.g., "What is the weather?").

​Expected​: AI should trigger the "IF IRRELEVANT" logic, apologizing instead of hallucinating a link.

• ​No Pre-emptive Calling​: Start a new session and do not type anything.

​Expected​: The "Tool Called" status should remain empty until you send a message.

Read the documentation
Read the documentation

Clone the Project and Extend Your App

Clone the complete AI Knowledge Base template into your own Momen workspace to inspect the architecture firsthand. Examine how the database schema, Actionflow logic, and AI configurations interact securely without hidden code. You can effortlessly extend this foundation by customizing the data sources, swapping out the LLM provider using Bring Your Own Model capabilities, or adjusting UI elements to perfectly match your brand.

Conclusion

Transforming static company data into an interactive, intelligent assistant does not require complex backend engineering when using a unified visual development platform. By building with Momen, you retain total structural control over a secure, scalable relational database and deterministic logic flows, avoiding the pitfalls of fragile code generation. Clone the project template today to explore the visual architecture, review the documentation, and start integrating your own business data.

If you are willing to try it yourself, you could also clone this project here.

Tutorial