Reviewers praise Perplexity for fast, sourced answers, a clean interface, and strong deep-research workflows that often replace traditional search. Makers of
highlight growing accuracy that reduces double-checking. Makers of
emphasize citations, voice, and multi-model flexibility that streamline daily work. Makers of
note reliable, real-time info for daily context. Common drawbacks include occasional hallucinations, missing citations, long-thread context limits, and recent ads. Still, users report faster learning, credible summaries, robust mobile use, and efficient project knowledge bases.
Love the portability angle here - having consistent workflow definitions across different AI tools is a big productivity win. The 19-model support is impressive. How do you handle version conflicts when skill files get updated?
The portable workflow concept here is brilliant - having skills that understand context and fire automatically rather than needing explicit invocation is a game-changer for builder productivity. Curious how the 19-model routing works - is it deterministic based on skill type or more dynamic? Also interested in how team collaboration on shared skill libraries would work.
Computer use is the big next step. Going from "answer my question" to "do this task on my computer" changes everything. I've been waiting for this since Anthropic demoed computer use last year. The repeatable instructions part is what I care about most. I have about 15 things I do every morning that could probably be automated if the AI could just watch me do it once. How reliable is it with apps that change their UI frequently? That's usually where automation breaks.
The portability angle is the real unlock here. Most of us have invested significant time building workflows in one environment - the idea that these become transferable assets across 19 models changes the economics of AI workflow investment entirely. No more vendor lock-in on your institutional knowledge. Curious about the context activation mechanism - how granular is the trigger detection for choosing between similar workflows?
Congrats on the launch! As a heavy user of Gemini, Claude Opus, and Manus, reading through this immediately gave me strong Manus vibes—and I mean that in the best way possible.
Moving from "answering questions" to "executing multi-step workflows" is exactly what makes agentic tools like Manus so powerful. Seeing Perplexity adopt this "Computer" orchestration approach, especially with SKILL.md portability, is a massiveee step forward.
I'm just worried about the costs a bit. Subscription-based is great, as it allows us power users to outpace standard API costs. But since this routes tasks through various sub-models under the hood, I wonder if it might end up being as pricy or even pricier than Manus. I have my largest non-api costs there right now.
Looking forward to tryint it out. Really exciting
Perplexity has quickly become one of my favorite tools for researching things online: getting answers with sources instead of digging through dozens of links is such a better workflow. Congrats on the launch! What feature are you most excited to build next for power users?
This looks really interesting.
Are the repeatable instructions more like automation workflows or closer to scripting for the computer?
Curious how flexible it is for developers.