AGENTIC-SYSTEMSMarch 12, 20261 min read33 views

Perplexity's "Personal Computer" brings its AI agents to the, uh, Personal Computer

Perplexity is moving its AI agent functionality to the desktop with "Personal Computer," an early-access app that gives AI local access to a user's files and applications to complete complex tasks.

Last month Perplexity announced the confusingly named “Computer,” its cloud-based agent tool for completing tasks using a harness that makes use of multiple different AI models. This week, the company is moving that kind of functionality to the desktop with the confusingly named “Personal Computer,” now available in early access by invite only.

Much like the cloud-based version, Personal Computer asks users to describe general objectives rather than specific computing tasks—an introductory video shows Personal Computer’s questions in a sidebar asking things like, “Create an interactive educational guide” and “create a podcast about whales.” But Personal Computer, running on a Mac Mini, also gives Perplexity’s agents local access to your files and apps, which it can open and manipulate directly to attempt to complete those tasks.

That should sound familiar to users of the open source OpenClaw (previously Moltbot), which similarly allows users to let AI agents loose on their personal machines. From the outside, Personal Computer looks like a more buttoned-up, user-friendly version of the same concept, with an easy-to-read, dockable interface that can help users track multiple tasks. Perplexity users can also log in remotely to their local copy of Personal Computer, making it “controllable from any device, anywhere,” Perplexity says.

Source: Ars Technica AI

More in this category

agentic-systems

S1-Omni: A Unified Multimodal Reasoning Model for Scientific Understanding, Prediction, and Generation

Researchers have introduced S1-Omni, a unified multimodal reasoning model designed for AI for Science (AI4S). Outperforming advanced models like GPT-5.5 and Gemini-3.1-Pro on various benchmarks, S1-Omni addresses the fragmentation in modeling complex scientific data.

agentic-systems

NeurOWL: An LLM-Based Neural-symbolic Framework for Incomplete OWL Ontology Reasoning

Researchers have introduced NeurOWL, a novel LLM-based neuro-symbolic framework designed to address reasoning challenges in incomplete OWL ontologies. By unifying subsumption verification and ontology abduction, NeurOWL demonstrates robust performance across multiple domains.

agentic-systems

ToolVerse: Unlocking Massive Environments and Long-Horizon Tasks for Agentic Reinforcement Learning

Researchers introduce ToolVerse, a comprehensive framework designed to scale up agentic reinforcement learning environments and enable LLM agents to perform complex, long-horizon reasoning tasks using thousands of real-world tools.

NOW LET US Related – Neuro-Symbolic AI for LEED compliance: Document-Centric Benchmarking, Deterministic Numeric Checking, and When Multimodal Hurts

agentic-systems

Neuro-Symbolic AI for LEED compliance: Document-Centric Benchmarking, Deterministic Numeric Checking, and When Multimodal Hurts

A new study introduces a local neuro-symbolic AI pipeline to automate LEED v4.1 green building certification screening. The findings reveal that the small 4-billion-parameter Gemma 3 model outperforms larger models, while incorporating multimodal drawing images consistently degrades performance.

agentic-systems

SeerGuard: A Safety Framework for Mobile GUI Agents via World Model Prediction

Researchers have introduced SeerGuard, a proactive safety framework that prevents mobile GUI agents from executing risky actions by predicting consequences beforehand using a Safety-Augmented World Model (SAWM).

NOW LET US Related – MGDT: MLLM-Guided Diffusion Transformer with Relation-Adaptive Mixture-of-Experts for Multimodal Knowledge Graph Completion

agentic-systems

MGDT: MLLM-Guided Diffusion Transformer with Relation-Adaptive Mixture-of-Experts for Multimodal Knowledge Graph Completion

Researchers have proposed MGDT, a novel framework for Multimodal Knowledge Graph Completion (MKGC) that utilizes an align-then-diffuse paradigm. By integrating a frozen MLLM and a Relation-Adaptive Mixture-of-Experts module, MGDT significantly outperforms existing baselines.