Async function calling
Also written: Asynchronous function invocation, Async non-blocking function calling, Async tool use, Non-blocking function calls, Asynchronous function calling
Lets AI call external tools or functions without pausing its main task, enabling background operations and complex workflows.
Imagine you ask an AI to write a story and also check the weather. Instead of waiting for the weather report before writing, async function calling lets the AI start writing the story while it simultaneously asks for the weather.
This means the AI can do multiple things at once, or start a long task like searching a database without freezing up. It's like having a helpful assistant who can juggle different requests efficiently, making the AI seem faster and more capable.
Async function calling allows a model to invoke external tools or functions without blocking the execution of its primary generation task. The model identifies a need to call a function, generates the arguments, and sends a request to an external system. The result from the function is then fed back to the model to continue its generation process. This enables parallel execution of AI tasks and tool use, improving responsiveness and allowing for more complex, multi-step operations.
Recent Google Gemini updates highlight faster, real-time voice interactions and more responsive AI applications. This suggests a push towards AI systems that can handle multiple tasks concurrently, improving user experience by not making them wait for operations to complete. The focus is on enabling AI to perform actions in the background while continuing other processes.
- settings_voice Gemini 3.8 LiveGoogle · Gemini Models ·
- settings_voice Gemini 3.8 LiveGoogle · Gemini Models ·
- 🪄 Gemini Live API in actionGoogle · Google for Developers on YouTube ·
- What's new in the Gemini Live APIGoogle · Google for Developers on YouTube ·
- Gemini API Cookbook: feat: add Gemini 3.8 Live quickstarts and model updates (#1378)Google · Gemini API Cookbook ·
- Building real-time voice applications with Live APIGoogle · Google AI: Release Notes ·
- Google Gemini
- Google Gemini's Live API and recent model updates emphasize faster voice interactions and building more responsive AI applications, likely leveraging asynchronous function calling for real-time performance.
- Function calling
- Synchronous function calling waits for a function to complete
- Multithreading
- This is a programming concept for running multiple threads of ex
The concept of asynchronous operations originates from computer science, particularly in programming languages like JavaScript. In the context of AI, function calling emerged as a way for LLMs to interact with external tools, with asynchronous execution becoming a natural extension for efficiency. Source ↗
Ask an AI assistant to tell you a joke and simultaneously find out the current time. Observe if it can deliver the joke while also providing the correct time, indicating it performed these tasks concurrently.
The Playbook: reusable how-tos, prompts, configs and tips pulled out of the news.
- PromptRole-play a student struggling with math for AI tutor simulationSimulate a student's math struggles and uncertainty for AI tutor evaluation. · 5 min
- TemplateReusable workflow templates for healthcare teamsTeams can create and share templates for common workflows like documentation or prior authorizations. · 15 min
- TemplateTemplate for building an AI tool tailored to your workA structured approach to defining and building a custom AI tool for specific business needs. · 15 min
- TemplateEvals CSV prompt list for agent skillsA CSV file template for listing prompts used in evaluating agent skills. · 20 min
- HeuristicDouble coding agent task completion with docs linksProviding coding agents with a documentation link significantly increases their task completion rate. · 2 min
Questions people ask
- How does async function calling make AI better?
- It allows the AI to perform multiple tasks or use external tools without getting stuck, making it faster and able to handle more complex requests.
- Is this the same as multitasking for humans?
- It's similar. For humans, multitasking can mean switching attention quickly. For AI, async function calling means it can initiate a task and continue other work without waiting for the first task to finish.
First seen on Subvolts Sep 15, 2026. Updated Oct 12, 2026. Written by an AI model from the items above and reviewed against them weekly; report an error.