Urgent.News

What's breaking now, across thousands of outlets.

AI

Perplexity launches its own take on AI agents for work

Perplexity is taking on OpenAI and Anthropic with its own work-focused AI agents. The startup's new always-on "Teammates" can take on multiple roles within a workspace, while pulling existing projects, skills, and memory from the Perplexity tools you already use. Teammates integrate with Perplexity Computer, an AI system that can deploy agents on your device […]

Perplexity launches its own take on AI agents for work

Perplexity, the startup, has unveiled its own AI agents designed for professional use, in direct competition with OpenAI and Anthropic. These new "Teammates" can multitask within a workspace and utilize existing projects, skills, and knowledge from the Perplexity tools that users are already familiar with. Teammates are engineered to integrate with Perplexity Computer, an AI system capable of deploying agents onto a user's device for task execution.

However, unlike the free accessibility of similar features provided by OpenAI’s Dots and Claude Duet, Perplexity's approach comes with a price tag - a $200 per month Max subscription plan. This premium service allows users to delegate various jobs to different Teammates, which can work simultaneously on large-scale projects. Progress tracking is facilitated through individual threads within the Perplexity app and direct interaction with Teammates in Slack.

CEO Aravind Srinivas envisions a future where every organization could have hundreds of these digital assistants, one for each individual employee.

Written by urgent.news from The Verge's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.

Read the original at theverge.com →

More in AI

De combien de mémoire un LLM local a-t-il besoin ?

Avant de télécharger un modèle pour le faire tourner en local, il faut savoir s'il tient en mémoire. L'estimation est la somme de trois termes, comparée à ce que la machine peut réellement donner au…

  • Local LLM memory needs determined by weights, KV cache, overhead
  • 14B model in Q4KM quantization requires 8-9 GB total
  • Memory must be less than 80% of usable memory on system

Before you open Claude Code in a cloned repo, check its .claude/skills folder

Before you open Claude Code in a repo you cloned, look inside its .claude/skills/ folder. Read the allowed-tools line of each skill, search for !` , and compare the folder names with the commands you…

  • .claude/skills/ folder contains project skills without permission prompts
  • 94.3% of analyzed skills have no command restrictions in cloned repos
  • Review skills with "!" prefix to identify pre-execution commands

More from Thursday 5 November →