# Agentic interaction using AppFunctions

DevFeed: [Agentic interaction using AppFunctions](<https://devfeed.tech/articles/agentic-interaction-using-appfunctions-26156.md>)

Original publisher: [Read original article](<https://dev.to/tkuenneth/agentic-interaction-using-appfunctions-m8k>)

Author: Thomas Künneth

Published: 2026-04-06T06:49:26Z

Content type: article

Language: en

Sources: [Thomas Künneth](<https://devfeed.tech/sources/thomas-kunneth.md>)

Topics: [Android](<https://devfeed.tech/topics/android.md>), [API](<https://devfeed.tech/topics/api.md>), [Google](<https://devfeed.tech/topics/google.md>), [App](<https://devfeed.tech/topics/app.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [ai](<https://devfeed.tech/tags/ai.md>), [android](<https://devfeed.tech/tags/android.md>), [api](<https://devfeed.tech/tags/api.md>), [app](<https://devfeed.tech/tags/app.md>), [coding](<https://devfeed.tech/tags/coding.md>), [community](<https://devfeed.tech/tags/community.md>), [development](<https://devfeed.tech/tags/development.md>), [engineering](<https://devfeed.tech/tags/engineering.md>), [google](<https://devfeed.tech/tags/google.md>), [inclusive](<https://devfeed.tech/tags/inclusive.md>), [programming](<https://devfeed.tech/tags/programming.md>), [software](<https://devfeed.tech/tags/software.md>)

## AI overview

This article explains AppFunctions as an Android API for making app capabilities discoverable and executable by agents. It contrasts the model with earlier approaches including App Actions, Android Slices, Direct Actions API, and Assist API, describing limitations such as rigid intents, UI maintenance, foreground-app requirements, and difficulty turning screen data into reliable actions.

## Source excerpt

Given the rise of agentic interaction on Android, we need a fast, reliable API to make app capabilities discoverable and executable by agents. Through the years, Google has introduced several native frameworks to bridge the gap between the operating system, its system-level assistants, and apps. App Actions is the long-standing predecessor to AppFunctions. It uses shortcuts.xml and built-in intents to map specific user requests directly to app features. Android Slices were an attempt to surface interactive snippets of an app's UI directly within the assistant or search interface; they have been effectively deprecated since 2021. Then there's the Direct Actions API, a framework introduced to allow voice assistants to query a foreground app for its specific capabilities in real-time. Gone too. Finally, the Assist API: the fundamental system-level hook that allows a native agent to read the screen context, providing the situational awareness necessary for agents to act on behalf of the user. In retrospect, the failure of these predecessors likely wasn't due to a lack of vision, but rather a fundamental mismatch between static engineering and the needs of dynamic intelligence. App Actions relied on a rigid library of built-in intents. If an app feature didn't fit into one of Google's binding categories, it effectively didn't exist to the assistant. Android Slices were killed by the UI maintenance trap. By forcing developers to build and maintain restricted, templated versions of their interface that often felt out of place, Google asked for too much effort for too little user engagement. The Direct Actions API failed because of its requirement that an app is actively running on the screen, which prevents the assistant from performing tasks autonomously. And while the Assist API provided the eyes for the system, it lacked the intelligence. It could scrape a messy tree of text and nodes from the screen, but it couldn't reliably parse that data into meaningful actions with