To check today’s weather, KTX timetables, exchange rates and internal company data, you need to switch between multiple apps and systems. AI that only uses information available up to the end of its training can find it difficult to reflect continuously changing circumstances.
Tool Calling enables AI to select external tools suited to a user’s request, retrieve the latest information and carry out tasks. This article explains how Tool Calling works, its range of applications and what to check when designing it.
What is Tool Calling?
Tool Calling is a technology that connects large language models to external functions, APIs, databases and business systems. After analysing a user’s request, AI determines the required tools and input values, then uses the results returned by those tools to provide an answer or perform the next task.
| Category | Training data-based processing | Tool Calling-based processing |
|---|---|---|
| Information timing | Uses information available up to the model’s training date | Uses external data available at the time of the call |
| Calculations | Generates results based on the context | Checks results by calling a calculator or calculation function |
| Internal company data | Uses only information included in the training process | Queries databases and document systems for which access is authorised |
| Task execution | Generates a response | Performs tasks such as making bookings, registering, sending and generating reports |
How a request is processed
What is possible with Tool Calling
Tool Calling connects information retrieval and task execution in a single conversational flow. Users can provide conditions in natural language without needing to know each service’s search method or menu location. Enterprises can configure the tools available for invocation differently according to user permissions and business rules.
| Use cases | Connected systems | Processing examples |
|---|---|---|
| Real-time information | Weather, traffic, foreign exchange and share price APIs | Retrieving current information and comparing it based on conditions |
| Accurate calculations | Calculators, statistical functions and pricing calculation APIs | Calculating taxes, distances, costs and statistical values |
| Internal information | Document repositories, databases and search systems | Searching for policies, contracts and performance data within the scope of permissions |
| Schedule management | Calendars and booking systems | Checking available times and adding appointments |
| Communication | Email, messaging and notification systems | Composing and sending messages after user approval |
| Business automation | Reporting, customer relationship management and enterprise resource planning systems | Collecting data, completing forms and changing statuses |
Considerations to check during design
As connections to external systems increase, the scope of data access and execution permissions also expands. Service operators must define specific validation procedures before and after invocation, error handling methods and cost limits. Users must be able to check what information is being sent to which system.
| Check item | Potential issue | Design approach |
|---|---|---|
| Personal information protection | Personal information may be sent to external systems during invocation | Send only the necessary data and manage encryption, retention periods and conditions for provision to third parties |
| Access permissions | Data or functions that the user is not authorised to access may be accessed | Apply user authentication and role-based permissions, and recheck permissions before invocation |
| Data accuracy | The API may return outdated or incorrect values | Display the data timestamp and source, and apply validation and cross-checking |
| Execution responsibility | Unintended actions may be confirmed during booking, payment or sending | Apply user confirmation and approval steps to actions that are difficult to cancel |
| Cost management | Operating costs may increase due to repeated invocations and large-volume requests | Set invocation limits, result storage and rules to prevent duplicate requests |
| Maintenance | External APIs and input formats may change | Operate version management, automated testing, failure detection and fallback procedures |
- Limit sensitive information to the scope necessary for the purpose of the call.
- Require user approval steps for payment, booking, transmission and deletion tasks.
- Continuously record the tool’s response time, error rate and call costs.
- Display the source and retrieval time of external data in the results.
- When a tool failure occurs, apply retry limits and fallback processing criteria.
CLEVI’s approach to real-world business applications
The usefulness of AI in business depends on model performance, the tools that can be connected, execution accuracy and the level of security controls. Connecting multiple tools to a single request enables everything from information retrieval to organising results and carrying out follow-up tasks on the same screen. Reflecting role-specific permissions and approval procedures can reduce repetitive tasks while maintaining the organisation’s security policies.
- Tool Calling
- Function Calling
- Generative AI
- AI agents
- Business process automation
- API integration