Organizational Knowledge Management

Build intelligent knowledge management workflows that collect internal knowledge from various sources, categorize and make information searchable with AI, and enable quick access to FAQs, technical documents, and training materials via multiple channels for enhanced organizational efficiency.

Target Audiences

Knowledge and Training Teams

Organize and access training resources effectively

Employees

Find answers to FAQs and technical documents quickly

Senior Managers

Oversee organizational knowledge and improve processes

Technical Teams

Integrate with Knowledge Management Systems (KMS)

Support Teams

Use FAQs for faster response times

Prerequisites

Access to a Delaverse account

Knowledge resources (e.g., PDF/Word documents, text-based training, FAQs) ready for upload

Google account access for Google Sheets and Google Docs Nodes

API access to knowledge management systems (e.g., Confluence, SharePoint) with authentication details (if used)

Access to Telegram with a bot token for the Telegram Node

Initial categories (e.g., technical, training, support) for knowledge classification

Step 1: Create a New Project

Log in to Delaverse: Visit playground.delaverse.ai and sign into your Delaverse account

Select New Project: On the projects dashboard, click the New Project box

Name the Project: Enter a title, e.g., Organizational Knowledge Management, in the Project Name field and click Create Project

Enter the Playground: You'll be directed to the project's Playground, where you can add nodes

Step 2: Add Knowledge Resource Input Nodes

To manage knowledge, data is collected from multiple sources: Google Sheets, File Database, Google Docs, or API (e.g., KMS).

2.1. Google Sheets Node

Uploads tabular data (e.g., FAQs or document lists)

Add Node: From the right-hand menu, click Google Sheets Node

Configure Node: Click the node and enter a title, e.g., داده‌های دانش (Knowledge Data)

Enter data (questions and answers) and click Update

2.2. File Database Node

Uploads knowledge documents (PDF, Word, video)

Add Node: From the right-hand menu, click File Database Node

Configure Node: Click the node and enter a title, e.g., فایل‌های دانش (Knowledge Files)

Upload files (e.g., manual_erp.pdf)

Review the list of uploaded files

2.3. Google Docs Node

Uploads text-based documents or knowledge guidelines

Add Node: From the right-hand menu, click Google Docs Node

Configure Node: Enter title اسناد دانش (Knowledge Documents)

2.4. API and Request API Nodes

Retrieve knowledge from KMS (Confluence, SharePoint)

Add API Node with base URL (e.g., https://knowledge.example.com/api)

Configure authentication (Basic Auth, Bearer Token, or API Key)

Add Request API Node with endpoints (/documents, /faqs)

Suggested Content: Documents (title, content, category), FAQs (question, answer, category)

Important: Completing these steps is straightforward with the necessary access. However, if you need to connect an API through your system and lack the expertise, consult your company’s technical team. If you don’t have a technical team or they’re unavailable, submit a ticket to us. Request workflow creation by our team, and we’ll prepare a cost invoice based on your subscription level. After payment, we’ll work with you to build the workflow to meet your needs.

Step 3: Connect to the Vector Database Node

To unify data from Google Sheets, File Database, and Google Docs:

Add Node: From the right-hand menu, click Vector Database Node

Configure Node:Click the node and enter a title, e.g., دیتابیس دانش (Knowledge Database)

Connect Nodes: Connect the outputs of Google Sheets, File Database, and Google Docs Nodes to the Vector Database Node's input

Verify Data: Click the node to ensure data is correctly aggregated

Note: The Request API Node does not connect to the Vector Database Node; connect it directly to the AI Assistant Node.

Step 4: Add the AI Assistant Node

This node categorizes knowledge, makes it searchable, and generates relevant responses:

Add Node: From the right-hand menu, click Analyzer Node

Configure Node: Click the node and enter a title, e.g., مدیر دانش (Knowledge Manager)

Select AI Model: Select an AI model (e.g., Open AI)

Instructions: Choose the Knowledge Manager template or edit the instruction (see below)

Connect Nodes: For Google Sheets/File Database/Google Docs, connect Vector Database output to AI Assistant input. For API, connect Request API output to AI Assistant input

Knowledge Manager Instruction Template

You are an AI assistant designed to manage and deliver organizational knowledge.
Your goal is to provide fast, accurate, and relevant answers to user queries based on the organization's internal knowledge base (including frequently asked questions, technical documents, and training materials).
You have access to the following resources in the vector database:

• Employee behavior guidelines from Google Docs with ID: …(place ID)…

• Rules and regulations provided by the organization's IT department from the file repository with ID: …(place ID)…

Your responsibilities include:

Extraction and Categorization: Extract key information (title, content, category) from the available data and organize it into the following categories: Technical, Educational, and Support.
Searchability: Based on the contents of the vector database, provide relevant and precise answers to user questions.

Guidelines for responses:

• Write responses in Persian (Farsi) with a professional and friendly tone.

• Respond only to user questions and refrain from offering unsolicited analysis or suggestions.

Step 5: Add Container and Analyzer Nodes (If Using Telegram)

For comprehensive knowledge and conversation analysis:

Add Container Node

Organize all workflow nodes

From the right-hand menu, click Container Node

Enter title کانتینر دانش (Knowledge Container)

Place all previous nodes inside the Container

Add Analyzer Node

Comprehensive knowledge analysis

Add AI Assistant Node with title تحلیلگر دانش (Knowledge Analyzer)

Choose Knowledge Analyzer template or use custom instruction

Connect Container Node output to Analyzer AI Assistant input

Knowledge Analyzer Instruction Template

For User Messages:
You are an AI assistant tasked with comprehensive analysis of organizational knowledge based on user messages.
Your goal is to evaluate existing knowledge, identify gaps, and provide reports and recommendations to managers to enhance organizational knowledge.
Required Actions and Analyses:
    • Key Metrics: Number of documents, category coverage, usage rate (answered questions).
    • Trends: Changes in knowledge usage (e.g., increased technical questions).
    • Gaps: Topics without coverage (e.g., lack of training for tool X).
    • Recommendations: Solutions for improvement (e.g., adding FAQs or training videos).
    • Deliver outputs in text format with a professional and friendly tone.

Step 6: Connect to the Frame Chat Node

This step enables delivering AI Assistant responses via an interactive chat frame on your website or app, with testing capabilities:

Basic Configuration

• Add Frame Chat Node from right-hand menuEnter title, e.g., Feedback FrameSet company name (e.g., Delaverse)

Domain & Style Configuration

• Domain & Style Configuration

Implementation & Testing

• Connect AI Assistant to Frame Chat• Go to Code tab and copy HTML code• Use Test Frame to preview responses

Testing and Verification

• After connecting to the AI Assistant, a Test Frame option appears• Enter sample queries to review responses• Ensure responses are accurate, professional, and aligned with input data• Click Save Changes to persist all settings

Step 7: Connect to the Telegram Node

To deliver analyses via Telegram:

Create a Telegram Bot:

• In Telegram, go to @BotFather, send /start, then /newbot• Choose a name, e.g., @SalesBot, and copy the bot token

Configure Telegram Node:

• Add Node: From the right-hand menu, click Telegram Node• Enter the bot token and click Test Connection• Configure Advanced Settings (Welcome Message, Access, Limits)

Advanced Settings & Final Steps

• Welcome Message: Set a greeting for users• Group Access: Enable if needed for team collaboration• Access Restriction: Select All for public access• Message Limit: Set to, e.g., 10 messages per minute

Key Tips for Success

Data Sources: Use Google Sheets, File Database, Google Docs, or API. Combining sources may require precise instruction tuning

Training Content: Use real documents (e.g., FAQs, manuals)

Persian Language: Keep all settings and outputs in Persian

Testing: Verify responses and reports in Telegram, Google Sheets, or Google Docs

Continuous Saving: Click Save Changes after every modification

Final Output

Internal knowledge is collected from various sources

Information is categorized, made searchable, and relevant responses are generated

Responses are delivered via Telegram (text responses)

Knowledge insights and improvement recommendations are provided through the Analyzer Node

General Note on Workflow Customization
This workflow, like all workflows in Delaverse’s knowledge base, is designed as a sample for educational purposes. Users can extensively customize nodes, settings, and input files to meet personal or organizational needs. For assistance, consult our 24/7 support chatbot or submit a ticket for guidance. If you’re unable to build or modify the workflow yourself, request professional workflow creation via a ticket; we’ll provide a cost invoice based on your subscription level, and after payment, we’ll collaborate to build it. For new node development (e.g., a custom node not yet available), submit a ticket with your requirements, noting that such requests may incur higher costs due to development efforts. Our team is here to ensure your automation success! 😊

Ready to Transform Your Knowledge Management?

Start building your intelligent knowledge management workflow today. Collect internal knowledge from multiple sources, categorize and make information searchable with AI, and enable quick access to FAQs and documents for enhanced organizational efficiency.

Delaverse AI Knowledge Base

Knowledge Base