To check today’s weather, the KTX timetable, exchange rates and internal company resources separately, you need to switch between multiple apps and systems. AI that only uses information available up to the point when its training ended finds it difficult to reflect constantly changing circumstances.
Tool Calling enables AI to select external tools suited to the user’s request, retrieve the latest information and carry out tasks. This article explains how Tool Calling works, its range of applications and the considerations 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 the user’s request, the AI determines the necessary 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 date | Uses information available up to the model’s training date | Uses external data available at the time of the call |
| Calculation | Generates results based on context | Checks results by calling a calculator or calculation function |
| Internal company resources | Uses only information included in the training process | Queries authorised databases and document systems |
| Task execution | Generates a response | Performs tasks such as making reservations, registering, sending and generating reports |
How requests are processed
What is possible with Tool Calling
Tool Calling connects information retrieval and task execution within a single conversational flow. Users can provide criteria in natural language without needing to know how to search each service or where its menus are located. Enterprises can configure the tools available for invocation differently according to user permissions and business rules.
| Application areas | Connected systems | Processing examples |
|---|---|---|
| Real-time information | Weather, traffic, exchange rate and stock price APIs | Retrieving current information and comparing it by criteria |
| Accurate calculations | Calculators, statistical functions and fare calculation APIs | Calculating taxes, distances, costs and statistical values |
| Internal information | Document repositories, databases and search systems | Searching regulations, contracts and performance data within the scope of permissions |
| Schedule management | Calendars and booking systems | Checking available times and adding events to the schedule |
| 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 |
Points 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 verification procedures before and after calls, error-handling methods and cost limits. Users must be able to check what information is sent to which systems.
| Check item | Potential issue | Design approach |
|---|---|---|
| Personal data protection | Personal data may be transmitted to external systems during the call | Transmit only the data required, and manage encryption, retention periods and conditions for providing data to third parties |
| Access permissions | Users may access data or functionality for which they do not have permission | Apply user authentication and role-based permissions, and recheck permissions before making calls |
| Data accuracy | An API may return outdated or incorrect values | Display the data timestamp and source, and apply validation and cross-checking |
| Execution accountability | Unintended actions may be confirmed during booking, payment or transmission | Apply user confirmation and approval steps to actions that are difficult to cancel |
| Cost management | Operating costs may increase due to repeated calls and large-volume requests | Set limits on the number of calls, save results and establish rules to prevent duplicate requests |
| Maintenance | External APIs and input formats may change | Operate version management, automated testing, fault detection and fallback procedures |
- Limit sensitive information to the scope required for the purpose of the call.
- Require user approval for payment, booking, transfer and deletion operations.
- Continuously record tool response times, error rates and call costs.
- Display the source and retrieval time of external data in the results.
- If a tool failure occurs, apply criteria for the number of retries and fallback processing.
CLEVI’s approach to applying it to real-world work
The usefulness of AI in the workplace depends on model performance, the tools it can connect to, execution accuracy and the level of security controls. By connecting multiple tools to a single request, you can handle 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 work while maintaining the organisation’s security policies.
- Tool Calling
- Function Calling
- Generative AI
- AI agents
- Workflow automation
- API integration