
xAI shipped a new mode called /goal inside Grok Build, its terminal coding agent. The feature targets long-running, autonomous task execution. You hand the agent a larger implementation task, then step back. Most coding sessions require back-and-forth execution and verification. You prompt, the agent acts, and you verify each step. /goal changes that loop. The agent keeps working until a task is completed and verified. Verification can mean reviewing code, inspecting webpages, or executing
Will xAI's Grok Build /goal feature be listed on the official Grok documentation page by June 30?
Resolves by Jun 30, 2026
/goal is a new mode in Grok Build, a terminal-based coding agent, that lets users hand off multi-step programming tasks to run autonomously without constant back-and-forth prompting. Instead of the typical cycle where a user prompts, the agent acts, and the user verifies each step, /goal allows the agent to plan an approach, execute a checklist of tasks, and verify completion through code review, webpage inspection, or script execution before stopping. The feature is designed for tasks like module migrations, service refactors, and dependency upgrades that span many steps and would otherwise require continuous supervision. Access requires a SuperGrok or X Premium Plus subscription, and users can monitor and steer the autonomous work with commands to check status, pause, resume, or clear the goal entirely.

The all-cash deal gives MoEngage access to technology that assigns AI agents to individual customers.

A new update for Google Home could make it less likely your smart home cameras mistake you for someone else, just because you're facing away from the camera. Starting June 23rd, Google's expanding its facial recognition feature so that people you've tagged in your Familiar Faces library can continue to be identified when their faces aren't clearly visible, using "additional non-biometric signals (body size, clothing color, etc.)." The Familiar Faces library will also begin aut

In this tutorial, we build a speech recognition and translation workflow using NVIDIA Canary-1B-v2. We begin by setting up the required audio, NeMo, NumPy, and SciPy dependencies, then load the Canary model on a GPU-enabled runtime for efficient inference. From there, we prepare audio into a clean 16 kHz mono format, perform English ASR, translate speech into multiple languages, generate word and segment timestamps, export translated subtitles as an SRT file, test long-form transcription, run b
Want to go deeper than the news? Explore live, cohort-based AI courses taught by practitioners.
Browse AI courses on Maven