Perplexity: agents need org memory and teamwork, not just a frontier model
AravSrinivas · x · 2026-11-06
Expanding on the Teammates launch, Arav Srinivas says building "a team of agents for everyone" takes more than a frontier model: agents need to remember you and your org, learn to work with each other and your coworkers, run on their own, and get better every time you correct them.
Teammates is framed as the first step in that direction, with persistent memory, multi-agent coordination and feedback-driven learning as the core differentiators.
Related event: Perplexity Launches Teammates: Persistent AI Coworkers for Max Users(15 posts)→
More from coding & agent
- Team's 24/7 infra-monitoring agent spots anomalies 'before the fire,' user says — antoine_chaffin · 2026-11-06
- Delvetown: a human-agent "post-scarcity" web community, plus agents emailing researchers unbidden — Miles_Brundage · 2026-11-06
- Every team demos Codex and Claude workflows for running AI as your OS — every · 2026-11-06
- Hyperagent launches Sizzle, an agent that reads PRs and auto-produces polished demo videos — aakashgupta · 2026-11-06
- Vercel publishes CLI design guidelines for humans and AI agents — JohnPhamous · 2026-11-06
- Dev builds a sculpting tool for Apple Vision Pro using Codex — OpenAIDevs · 2026-11-06