Our email assistant can now flip through our knowledge base. But what if a customer asks a beyond-knowledge-base question, like: What is in the latest Intellos release? If the knowledge base hasn’t been updated yet, the workflow will be at a loss. To fix this, we need to equip it with a Live Search skill!

​
Tools

Tools
Tools are the superpower for your AI workflow. The Tools section in Intellos is like a Plugin Supermarket. It’s filled with ready-made superpowers—web search, checking the weather, drawing images, or calculating complex math. You just install and plug them into your workflow with several clicks. Now, let’s continue to upgrade on current workflow.

​
Hands-On 1: Upgrade the Sub-process Area in Iteration

We are going to add a new logic to our assistant: Check the Knowledge Base first; if the answer isn’t there, search the web. To focus on the new logic, let’s keep only these nodes: User input, Parameter Extractor, and Iteration.

​
Step 1: Knowledge Query and the Judge

1

Enter the Iteration

  1. Click to enter the sub-process area of the Iteration node.
  2. Keep Knowledge Retrieval node, and make sure the query variable is {x} item.
  3. Delete the previous LLM node.
2

Add the Judge (LLM Node)

Add an LLM node right after Knowledge Retrieval node. Its job is to decide if the Knowledge Base info can actually respond to the questions.
  • For Context session: Select the Knowledge Retrieval / {x} result Array [Object] from Knowledge Retrieval
  • System Prompt:
  • User Message:
LLM Settings
Here’s what it looks like on the canvas.
Workflow Preview

​
Step 2: Setting the Crossroads

1

Add If/Else Node

After LLM node, let’s add If/Else node. Set the rule: If LLM Output Contains Information not found in knowledge base.This means, when we can’t respond with the information in knowledge base.
Add if/Else Node
2

Add Tool for Searching

Let’s connect a search tool after the IF branch. This indicates that when the knowledge base cannot find relevant answer information, we use web search to find the answers.
  1. After the IF node, click plus(+) icon and select the Tools tab.
  2. In the search box, type DuckDuckGo. The DuckDuckGo plugin is available in Intellos out of the box and doesn’t require an API key.
Find the Search Tool
3

Choose DuckDuckGo Search

Expand DuckDuckGo and click DuckDuckGo Search.
Choose DuckDuckGo Search
4

Set the Query

The tool’s settings panel opens right away. Head to the Query string field and select Iteration/{x} item. Keep the other settings at their defaults.
Some search tools (for example, Google via SerpApi) require an API key. You add it once in the tool’s authorization settings; keep the key safe and avoid sharing it with others.
Add Query String
5

Configure the Two Paths

Now, we need different ways to answer depending on which path we’re looking at.The Search Answer PathAdd a new LLM node to answer the question based on the search results. Connect it to the DuckDuckGo Search node.System:
User Message:
Prompt for LLM 2
The Knowledge Searching PathAfter the Else node, add a new LLM node to handle answers based on the knowledge base.System:
User Message:
Prompt for LLM 3
6

Combine the Information

  1. In the sub-process (inside the Iteration box), add a Variable Aggregator node that connects both LLM 2 and LLM 3 at the very end.
  2. In the Variable Aggregator panel, select the variables LLM 2/{x}text String and LLM 3/{x}text String as the Assign Variables.
In this way, we’re merging the two possible answers into a single path.
Variable Aggregator Setup
This is how the current workflow looks.
Workflow Preview 2

​
Step 3: The Final Email Assembly

Now that our logic branches have finished processing, let’s combine all the answers into a single, polished email.
1

Configure Iteration Output

Click on the Iteration node, and set {x}Variable Aggregator/{x}output String as the output variables.
Iteration Output
2

Connect the Summary LLM

After the Iteration node, connect a new LLM node to summarize all outputs. Feel free to use the prompt below.System:
User Message:
Prompt for LLM 4
3

Finalize with the Output Node

After the LLM node, add an End node. Set the output variable as LLM 4/{x}text String.
Output Setup
We have now completed the entire setup and configuration of the workflow. Our email assistant can now answer questions based on the Knowledge Base and use web search for supplementary answers when needed.
Final Workflow Preview
Try sending an email with question that definitely isn’t in the knowledge base. Let’s see if the AI successfully uses web search to find the related answers.

​
Mini Challenge

  1. What are other conditions you can choose in If/Else node?
  2. Browse the Tools section to see if you can add another tool for this workflow?