Kuika's AI Agents feature allows you to integrate more interactive and scenario-based artificial intelligence experiences into your applications. With this feature, you can create artificial intelligence agents that perform different tasks, have specific roles, and can provide dynamic responses based on user input.
Steps to Create an AI Agent
Log in to the Kuika platform and open the project you want to work on.
Go to the Datasources module.
Go to the “AI Agents” section in the left panel.
Click the + icon to create a new AI Agent.
In the window that opens, you will need to fill in the following information:
Agent Name
Give the agent a descriptive name (for example, “JobPostGeneratorAgent”).
Model Selection
There are two different model types available:
All: Used for versatile, general-purpose tasks.
CrewAI: Provides an advanced scenario infrastructure that enables multiple AI agents to work as a team.
In the AI Agent Chat screen, you can move to a new line using the Shift + Enter combination. This allows you to more easily create multi-line messages or enter inputs in a bullet-style format.
AI Agent Templates
You can create an agent using ready-made templates or define a structure from scratch using the Custom option:
Custom
Definition: Allows you to create your own agent from scratch.
Use Case: For developers who want to use unique task definitions, custom user inputs, or different AI models.
Features: You have full control over role prompts, user prompts, models, and parameters.
Sample Input: “Generate a title and description for a podcast episode.”
Employee Researcher
Definition: Gather information about a specific employee from the internet or a database.
Use Case: Human resources, internal communications, and executive dashboards.
Data Source: Typically supported by Serper Tool.
Input: Employee name, position, email.
Output: Structured text or JSON about the employee's history, competencies, and projects.
Company Researcher
Description: Conducts online research on a specified company and provides summary information.
Description: Generates enriched analysis about a specific individual using multiple data sources.
Use Cases: Business development, investor research, executive profiling.
Input: Full Name, Company, Position, Industry
Output: Professional background, Areas of expertise, Media presence
Using Custom Templates
AI Agents can be adapted to different scenarios with their customizable template structure. The system offers a flexible solution thanks to input definitions, user interaction, and background tools.
How to Use
Define Agent Inputs:
Click the “Agent Inputs” button in the upper right corner.
Define the required inputs according to their types:
String: Text information (e.g., candidate name, product name)
Boolean: True/False options (e.g., was the reference check performed?)
Integer: Whole numbers (e.g., years of experience)
Float: Decimal numbers (e.g., expected salary)
Interact with the Chatbot:
The inputs you defined become active in the chatbot interface.
The user enters data into the Chatbot using natural language.
Sample message:
“Candidate name: John Doe, Was a reference check performed? Yes, Years of experience: 6, Expected salary: 85000.”
AI Agent Generates Response:
Creates an automatic response based on the defined inputs.
If necessary, analysis, calculation, or data querying operations are performed.
Results are presented to the user in real time.
Perform Actions Using Tools:
Thanks to the tools you add to the Agent, you can create files, extract data, and perform analysis.
Example Scenario: Candidate Evaluation
Objective: Obtain candidate information, perform suitability assessment, and save the result to a file.
Steps:
Define the following inputs from Agent Inputs:
candidateName (String)hasReferenceChecked (Boolean)yearsOfExperience (Integer)expectedSalary (Float)Write to the chatbot as follows:“Candidate name: John Doe, Has the reference check been completed? Yes, Years of experience: 6, Expected salary: 85,000.”The agent generates the following response:
John Doe
Reference check completed.
With 6 years of experience, he is suitable for the position.
Expected salary: 85,000 TL – This value appears to be in line with the market average.
Evaluation report is being generated..."
FileWriterTool is activated and creates a file named john_doe_evaluation.txt.
What is Agent Response Builder?
It is used to configure what kind of response the agent will give to the user. It enables AI responses to be generated in a dynamic, meaningful, and structured way. This structure allows you to:
Write custom messages based on inputs,
Embed tool outputs into the response,
Generate flexible content with conditional statements (e.g., show if reference check is done, warn if not).
It can be accessed by clicking the view icon (Response) in the Agent panel.
Here, you can call all inputs using the input name in the text and define conditional statements with Jinja-like structures.
Inputs are displayed in the Agent description in {} format.
DTO (Date Time Offset) fields returned in Agent Responses are processed as optional.
When using the Flight Tool, due to library-related limitations, the flight number and/or reservation URL information may not be available; in this case, an informational message is displayed to the user.
Supported Tool Descriptions
Settings for MCP-based integrations (Brave Search, Slack, Github, GoogleWorkspace, GoogleMaps, Youtube, Trello, Airbnb, Office365, Dropbox, Google Flight, LinkedIn, Instagram) are configured through the Configuration Manager module. Once API keys, access permissions, and connection details for the relevant MCP are defined in this module, they become available for use within the AI Agent. Additionally, storing outputs generated via MCP in the database is supported.
Project & Management
Trello Boards
Purpose: Access Trello boards and perform actions on cards.
Usage: Tasks on boards can be read, and card details can be retrieved.
Example Usages:
List all cards on a board
Get information about a specific task
Jira Tasks
Purpose: Manage tasks and tickets on Jira.
Usage: Issues can be listed and their details can be reviewed.
Example Usages:
List open tickets
Check the status of an issue
File & Storage
Dropbox Files
Purpose: Access Dropbox files.
Usage: Files can be listed and their contents can be read.
Google Workspace
Purpose: Work with Google Drive, Docs, and Sheets documents.
Usage: Documents can be opened and searched.
Open File
Purpose: Open uploaded files.
Save File
Purpose: Save created content as a file.
Read Excel
Purpose: Read and analyze Excel files.
Example Uses:
Analyze sales reports
Make list comparisons
Collaboration & Communication
Slack Messages
Purpose: To retrieve data from Slack channels.
Usage:
To read messages
To summarize conversations
Github Repos
Purpose: To review repositories and commits.
Usage:
To view recent changes
To follow up on open issues
Youtube Content
Purpose: To access YouTube videos.
Usage:
Search for videos
Get description information
Airbnb Data
Purpose: Get accommodation information from Airbnb.
Usage:
Search by date
Filter by price
Office365
Purpose: Integration with Outlook, OneDrive, and Office documents.
Usage:
Read emails
Perform file analysis
Data & Analytics
Code Runner
Purpose: To perform data processing, calculation, and automation tasks by running code snippets (e.g., Python, JavaScript, etc.).
Usage:
Performing calculations on data
Testing API output
Performing automatic data conversions
Running small-scale scripts
Web Scraper
Purpose: To extract data from static (HTML-based) websites.
Usage:
To retrieve table data from a specific web page
To extract product lists
To collect content (title, description, etc.)
Dynamic Website Scraper
Purpose: To retrieve data from websites loaded with JavaScript (dynamic).
Usage:
Pull content generated after the page loads
Collect infinite scroll or filtered list data
Get dynamic dashboard data
Serper Dev Tool
Purpose: Perform programmatic web searches via search engine API.
Usage:
List keyword-based results
Conduct quick research on a specific topic
Get search results in JSON format
Search Flight
Purpose: Query and filter flight information.
Usage:
Search for flights for specific dates
Compare prices
Filter by airline and time
Match incorrect entries in the Seat class parameter with the closest valid option (e.g., “econmy” → “economy”)
Due to library limitations, flight number and reservation URL information is not always supported; in this case, the agent informs the user.
Database Auto Sync Tool
Purpose: To provide automatic synchronization between different data sources.
Usage:
Synchronize remote database with local data
Automatically transfer data updates
Perform periodic data transfers
Linkedin Profile Search
Purpose: Search for person profiles on LinkedIn and retrieve basic information.
Usage:
Find profiles by name or position
Retrieve profile summary information
Conduct person research based on industry
Linkedin Company Employees
Purpose: Retrieve a LinkedIn employee list for a specific company.
Usage:
List company employees
Filter by position
Analyze the organizational structure
Instagram Scraper
Purpose: Retrieve public data from Instagram accounts.
Usage:
Pull profile information
Retrieve post details
Analyze engagement data
Search & Maps
Web Search (Brave)
Purpose: To search the internet.
Google Maps
Purpose: To obtain location and venue information.
Test Agent (Pre-Release Test Step)
The Test Agent step in the AI Agent creation process allows you to test your agent before completing it. This step allows you to try out the agent with real scenarios before publishing it and verify your prompt and input settings.
How does it work?
After defining the basic agent settings (name, model, template/prompt, inputs), proceed to the Test Agent step.
On the test screen, provide sample user inputs and instantly view the agent's responses.
If necessary, update the Role Prompt / User Prompt, input types, or tool settings and test again.
Once you are satisfied with the results, you can finalize the agent and publish it.
DB Recording and Environment Requirements
Recording outputs generated via MCP to the Database are supported.
The Test Agent step helps identify faulty or incomplete agents before they go live.
How to Configure Serper Tool Settings?
1. Add Configuration to the Application
Log in to the Kuika platform.
Open the project you will be working on from the Apps screen.
Click on the Configuration Manager module.
On the screen that opens, give the configuration a name and click the CREATE button.
2. Configure Serper Tool Settings
After creating a new configuration, open the App Settings screen.
Go to the AI Settings section.
Click on the Serper Tool option from the drop-down menu.
Click the ADD NEW button.
Configure the following settings in the pop-up window that opens:
Name: Name to be given to the configuration.
API Key: Access key obtained via the Serper API.
Once the Serper Tool becomes available for use by the Agent, it is automatically detected in AI Agent configurations and actively used in tasks involving external data sources.
Using the AI Agent
Go to the UI Design module.
Open the screen where you want to add the Agent.
Click on the +ADD ACTION > AI Agents tab and select the agent you created.
Connect the relevant user inputs and activate the AI-powered scenarios.
