Aravind Srinivas(@AravSrinivas)

Perplexity Agent API is the best for web search and browsing agents

Aravind Srinivas (@AravSrinivas) — Fri, 14 Aug 2026 02:19:06 GMT

Perplexity Agent API is the best for web search and browsing agents

Perplexity Developers@perplexitydevs

Sonar is moving to the Agent API.

The Perplexity Agent API keeps grounded web search, and adds multi-step research, code execution, built-in tools, and access to multiple models through one API.

On BrowseComp and WideSearch, Agent API more than doubles the best Sonar score.

🔗 View Quoted Tweet

💬19🔄8❤️137👀27665📊25

⚡ Powered by xgo.ing

Congrats to @SpaceXAI on one more amazing model: Grok 4.6. We benchmarked it as an orchestrator on o...

Aravind Srinivas (@AravSrinivas) — Thu, 13 Aug 2026 18:46:02 GMT

Congrats to @SpaceXAI on one more amazing model: Grok 4.6. We benchmarked it as an orchestrator on our Wide-And-Deep-Research benchmark using the Perplexity Computer harness, and it neatly sits on the Pareto frontier of performance vs cost. Available to all Pro and Max users on Perplexity!

Perplexity@perplexity_ai

Grok 4.6 is now available in Perplexity and Perplexity Computer.

On WANDR, it sits on the Pareto frontier of performance and efficiency, matching Fable 5 results at over 60% lower cost.

🔗 View Quoted Tweet

💬42🔄70❤️894👀3832022📊114

⚡ Powered by xgo.ing

Gemini Flash models are great for fast, cost-efficient subagents inside any multi-model harness. We ...

Aravind Srinivas (@AravSrinivas) — Thu, 13 Aug 2026 18:06:22 GMT

Gemini Flash models are great for fast, cost-efficient subagents inside any multi-model harness. We use them a lot inside the Perplexity Computer harness.

Sundar Pichai@sundarpichai

Our Flash models are workhorses that offer performance at a great price. So, we're shipping updates fast to get them in developers’ hands. And now just 3 weeks after launching 3.6 Flash, 3.7 Flash shows significant gains including in coding and agentic work. 

It delivers substantial improvements across software engineering, knowledge work, and web development, all with an introductory price at half the original cost of 3.6 Flash.

We've gotten positive feedback from early users, including our own engineers using 3.7 in @Antigravity, and we’re excited for you to try it there. Also available via Gemini API in @GoogleAIStudio, Gemini Enterprise & more, full list and details here: blog.google/innovation-and…

🔗 View Quoted Tweet

💬20🔄25❤️638👀57416📊63

⚡ Powered by xgo.ing

Nemotron 3.5 Lightning available to all developers on the Perplexity Agent API. Input: $0.0115 pe...

Aravind Srinivas (@AravSrinivas) — Wed, 12 Aug 2026 01:37:26 GMT

Nemotron 3.5 Lightning available to all developers on the Perplexity Agent API.  

Input: $0.0115 per 1M tokens
Output: $0.17 per 1M tokens

Perplexity Developers@perplexitydevs

.@NVIDIA Nemotron 3.5 Lightning is now available in the Perplexity Agent API 🎉

An open 30B MoE model with 3B active parameters, built for the high-volume execution layer of always-on agents: tool calls, validation, and subagent work.

Pair Nemotron Lightning 3.5 with frontier models like Nemotron Ultra for planning, and let Lightning handle the volume.

Start building:bit.ly/perplexity_lig…0

🔗 View Quoted Tweet

💬19🔄12❤️290👀39928📊44

⚡ Powered by xgo.ing

A great American open weights MoE model that can run efficiently on your laptop or local hardware li...

Aravind Srinivas (@AravSrinivas) — Tue, 11 Aug 2026 19:00:43 GMT

A great American open weights MoE model that can run efficiently on your laptop or local hardware like the DGX Spark! You can use the larger Nemotron Ultra on Perplexity!

NVIDIA AI@NVIDIAAI

Introducing NVIDIA Nemotron 3.5 Lightning⚡

An open 30B MoE model with 3B active parameters, built for always-on agents to complete high-volume, specialized tasks faster.

It delivers up to 4x the output speed of similar-sized models.

🔗 View Quoted Tweet

💬25🔄18❤️308👀44712📊46

⚡ Powered by xgo.ing

Compute is the currency

Aravind Srinivas (@AravSrinivas) — Mon, 10 Aug 2026 22:00:43 GMT

Compute is the currency

Jensen Huang@JensenHuang

x.com/i/article/2086…

🔗 View Quoted Tweet

💬43🔄48❤️844👀157311📊118

⚡ Powered by xgo.ing

enjoy US hosted K3 on perplexity agent api!

Aravind Srinivas (@AravSrinivas) — Mon, 10 Aug 2026 19:48:23 GMT

enjoy US hosted K3 on perplexity agent api!

Perplexity Developers@perplexitydevs

Access the power of @Kimi_Moonshot K3 in the Perplexity Agent API. Hosted exclusively on U.S.-based servers.

Try it out today bit.ly/pplx-kimi-k3

🔗 View Quoted Tweet

💬12🔄12❤️239👀37707📊28

⚡ Powered by xgo.ing

Perplexity Computer’s goal is to provide the maximum intelligence for minimum cost with multi model ...

Aravind Srinivas (@AravSrinivas) — Thu, 06 Aug 2026 19:13:47 GMT

Perplexity Computer’s goal is to provide the maximum intelligence for minimum cost with multi model orchestration. We’ve tested GPT 5.6 Terra extensively and found it to be a pretty good model: capable and cost-effective at the same time. We’re making it the default for all subagents inside Perplexity Computer harness. And are also offering it as an orchestrator model for all Computer users. Have fun!

Perplexity@perplexity_ai

GPT 5.6 Terra and Luna are now live in Perplexity Computer.

Terra is the new default model for all Computer subagents, while Luna will serve as the primary model for scheduled automations.

Terra is also available as an orchestrator model in Computer.

🔗 View Quoted Tweet

💬51🔄27❤️313👀49637📊64

⚡ Powered by xgo.ing

Verification is key when using agents for high stakes research!

Aravind Srinivas (@AravSrinivas) — Tue, 04 Aug 2026 17:07:16 GMT

Verification is key when using agents for high stakes research!

Jeff Grimes@jeffgrimes9

Every numerical value in Perplexity Computer finance queries is traceable back to original values, with full calculation trace shown.

🔗 View Quoted Tweet

💬27🔄20❤️246👀39430📊43

⚡ Powered by xgo.ing

Two orders of magnitude improvements are quite rare. This is a big deal.

Aravind Srinivas (@AravSrinivas) — Sat, 01 Aug 2026 21:29:34 GMT

Two orders of magnitude improvements are quite rare. This is a big deal.

Chubby♨️@kimmonismus

DeepSeek V4-Flash isn’t just cheaper per token. 

It reportedly completes the same benchmark tasks as Fable 5 at 105× lower total cost, according to @ArtificialAnlys !

That's precisely why the Flash release is, for me, the DeepSeek 2.0 moment. It will cause a huge stir.

🔗 View Quoted Tweet

💬70🔄90❤️1363👀145790📊179

⚡ Powered by xgo.ing

Follow @kpolley, Perplexity's CISO

Aravind Srinivas (@AravSrinivas) — Fri, 31 Jul 2026 04:37:10 GMT

Follow @kpolley, Perplexity's CISO

Kyle Polley@kpolley

Proud to open source Numbat 

forbes.com/sites/janakira…

🔗 View Quoted Tweet

💬18🔄8❤️274👀82921📊38

⚡ Powered by xgo.ing

And with Computer Brain, every project goes through self-improvement loops on its memory, leading to...

Aravind Srinivas (@AravSrinivas) — Thu, 30 Jul 2026 16:58:43 GMT

And with Computer Brain, every project goes through self-improvement loops on its memory, leading to better contextual understanding over time, thanks to offline compute that Brain performs between tasks and sessions of the collaborators on a Project.

💬3🔄0❤️53👀6924📊8

⚡ Powered by xgo.ing

Introducing Projects on Perplexity Computer. With the launch of Projects, we're turning Computer int...

Aravind Srinivas (@AravSrinivas) — Thu, 30 Jul 2026 16:54:48 GMT

Introducing Projects on Perplexity Computer. With the launch of Projects, we're turning Computer into a multiplayer agentic operating system for work with persistent memory, files, and sessions scoped across hubs and users. Available to all users!

Your browser does not support the video tag.

🔗 View on Twitter

💬54🔄43❤️469👀53032📊113

⚡ Powered by xgo.ing

Perplexity Pro users can now use Model Council with Computer credits. It's a user favorite when it c...

Aravind Srinivas (@AravSrinivas) — Tue, 28 Jul 2026 20:42:06 GMT

Perplexity Pro users can now use Model Council with Computer credits. It's a user favorite when it comes to legal, medical, and financial research, where getting diverse perspectives helps a lot.

Perplexity@perplexity_ai

Model Council is now available inside Computer.

Run independent analysis across multiple frontier models, choose your analysis depth, and get a single cited report on where models agree, where they disagree, and what each found that others missed.

Your browser does not support the video tag.

🔗 View on Twitter

🔗 View Quoted Tweet

💬14🔄14❤️198👀32892📊29

⚡ Powered by xgo.ing

US-hosted Kimi K3 now available on Perplexity for Pro and Max, both in Search and Computer modes. En...

Aravind Srinivas (@AravSrinivas) — Tue, 28 Jul 2026 19:42:31 GMT

US-hosted Kimi K3 now available on Perplexity for Pro and Max, both in Search and Computer modes. Enjoy! It’s a great frontier model!

Perplexity@perplexity_ai

We've added Kimi K3 to Perplexity and Perplexity Computer for Pro and Max subscribers.

Kimi K3 in Perplexity is hosted exclusively on U.S.-based servers.

Your browser does not support the video tag.

🔗 View on Twitter

🔗 View Quoted Tweet

💬24🔄32❤️465👀43797📊57

⚡ Powered by xgo.ing

We look forward to open sourcing a lot more tools and benchmarks that will continue to strengthen th...

Aravind Srinivas (@AravSrinivas) — Tue, 28 Jul 2026 16:44:31 GMT

We look forward to open sourcing a lot more tools and benchmarks that will continue to strengthen the frontier open secure ecosystem, and are glad @nvidia is leading from the front to ensuring we all build a safe ecosystem together.

💬3🔄1❤️21👀5310📊5

⚡ Powered by xgo.ing

And open sourced BrowseSafe, an open benchmark for protecting agents against prompt injection on web...

Aravind Srinivas (@AravSrinivas) — Tue, 28 Jul 2026 16:43:03 GMT

And open sourced BrowseSafe, an open benchmark for protecting agents against prompt injection on websites they access on a web browser session arxiv.org/abs/2511.20597

💬3🔄3❤️50👀7815📊10

⚡ Powered by xgo.ing

When Hugging Face got breached, the closed tools couldn't distinguish attackers from defenders and b...

Aravind Srinivas (@AravSrinivas) — Tue, 28 Jul 2026 16:40:33 GMT

When Hugging Face got breached, the closed tools couldn't distinguish attackers from defenders and blocked the forensic analysis. They ended up running open-weight GLM 5.2 on their own infra to contain it. Perplexity is joining the OSAA to support open tools for security.

NVIDIA@nvidia

The Open Secure AI Alliance is growing, with more organizations contributing expertise to help safeguard software and agents.

nvda.ws/4pD8Fc5

🔗 View Quoted Tweet

💬35🔄82❤️1241👀79066📊133

⚡ Powered by xgo.ing

True

Aravind Srinivas (@AravSrinivas) — Tue, 28 Jul 2026 16:01:00 GMT

True

the tiny corp@__tinygrad__

Yes, but nothing compares to the feeling of knowing the metal box your AI lives in is yours. Forget home ownership, owning a datacenter is the new American Dream.

🔗 View Quoted Tweet

💬15🔄3❤️125👀33261📊20

⚡ Powered by xgo.ing

GLM is such an underrated model considering how intelligent it is at the parameter size it has (700b...

Aravind Srinivas (@AravSrinivas) — Tue, 28 Jul 2026 05:26:25 GMT

GLM is such an underrated model considering how intelligent it is at the parameter size it has (700b). Near Opus grade that can run super efficiently.

💬15🔄4❤️68👀4681📊20

⚡ Powered by xgo.ing

Good observations

Aravind Srinivas (@AravSrinivas) — Mon, 27 Jul 2026 14:37:51 GMT

Good observations

Grady Booch@Grady_Booch

In the fullness of time, LLMs will eventually become commodities and their price will be a race to the bottom. As the competitive advantage of one LLM over another shrinks - particularly as open source models expand - the value proposition will turn to the neuro/symbolic harnesses that use those models, structures that encompass agents, agent orchestration, tooling, and component plugins. Even those from frontier AI organizations will fall to open source frameworks. The last thing standing will be those who command the data centers on which these things run, and even then, that will become a commodity, with the number of players shrinking to just a few survivors. They too will find pressure: as computational power rises, more and more such systems will be run locally.

🔗 View Quoted Tweet

💬11🔄14❤️340👀86739📊41

⚡ Powered by xgo.ing

Perplexity is now available as a CLI that can be used inside any harness. Pretty useful for letting ...

Aravind Srinivas (@AravSrinivas) — Sat, 25 Jul 2026 05:01:20 GMT

Perplexity is now available as a CLI that can be used inside any harness. Pretty useful for letting coding agents use the web.

Perplexity Developers@perplexitydevs

The Perplexity CLI is now available, giving coding agents the ability to search the web.

Copy this to your agent to get set up:

"Read: github.com/perplexityai/a… and install this skill."

Your browser does not support the video tag.

🔗 View on Twitter

🔗 View Quoted Tweet

💬43🔄30❤️559👀73306📊96

⚡ Powered by xgo.ing

today is the most positive i have felt about the future of american ai. the coming together of so ma...

Aravind Srinivas (@AravSrinivas) — Fri, 24 Jul 2026 16:47:33 GMT

today is the most positive i have felt about the future of american ai. the coming together of so many companies in a united manner to fight against regulatory capture is incredible to watch. 🇺🇸

💬48🔄126❤️2141👀156126📊257

⚡ Powered by xgo.ing

“Open weights strengthen competition and competition is what keeps the benefits of AI broadly shared...

Aravind Srinivas (@AravSrinivas) — Fri, 24 Jul 2026 14:41:32 GMT

“Open weights strengthen competition and competition is what keeps the benefits of AI broadly shared rather than concentrated in the hands of few”. We believe this strongly at @perplexity_ai and are co-signing this letter, with @nvidia! Thanks to @a16z for putting this together!

Jensen Huang@JensenHuang

For my first post, I’m sharing a letter @NVIDIA signed on why open models matter.

AI will transform every industry, power every company, and be built by every country.

Open models strengthen safety and cybersecurity, accelerate innovation and diffusion, and enable sovereignty.

The world needs both frontier closed models and frontier open models.

images.nvidia.com/pdf/Open-Weigh…

🔗 View Quoted Tweet

💬38🔄83❤️842👀46253📊103

⚡ Powered by xgo.ing

Everything is a distillation of Schmidhuber.

Aravind Srinivas (@AravSrinivas) — Thu, 23 Jul 2026 19:01:41 GMT

Everything is a distillation of Schmidhuber.

Jürgen Schmidhuber@SchmidhuberAI

I support open-source models distilling what commercial companies distilled for free from the entire internet. I published distillation for free in 1991 in Europe - this was copied in the US and in China (x.com/SchmidhuberAI/…)

🔗 View Quoted Tweet

💬13🔄12❤️214👀35185📊30

⚡ Powered by xgo.ing

Well said!

Aravind Srinivas (@AravSrinivas) — Thu, 23 Jul 2026 18:58:55 GMT

Well said!

Howard Lutnick@howardlutnick

CAISI’s latest report shows that Kimi K3 remains behind America’s leading frontier AI models.

The United States continues to lead in frontier AI because we’re home to the greatest innovators and technologists the world has ever seen.

🔗 View Quoted Tweet

💬9🔄2❤️112👀42639📊15

⚡ Powered by xgo.ing

future: continual learning of the model + harness hosted on hardware you own and control, with full ...

Aravind Srinivas (@AravSrinivas) — Wed, 22 Jul 2026 20:24:30 GMT

future: continual learning of the model + harness hosted on hardware you own and control, with full access to all sensitive context that never leaves your system

Michael Dell 🇺🇸@MichaelDell

Cloud → Multi-cloud → Hybrid → Private/Sovereign

🔗 View Quoted Tweet

💬36🔄39❤️390👀50046📊71

⚡ Powered by xgo.ing

Already the second most used orchestrator model on Perplexity Computer now, only behind Opus 4.8. O...

Aravind Srinivas (@AravSrinivas) — Wed, 22 Jul 2026 03:36:44 GMT

Already the second most used orchestrator model on Perplexity Computer now, only behind Opus 4.8.

Once we secure more compute, we intend to increase usage limits through credits; as well as roll out updated versions of the post-training.

Perplexity@perplexity_ai

We're releasing a research preview of a new orchestrator model in Perplexity Computer.

The model is an adapted version of GLM 5.2, post-trained for the Computer harness. It delivers near-frontier performance at 0.344x of the cost of Opus.

🔗 View Quoted Tweet

💬30🔄12❤️282👀40904📊45

⚡ Powered by xgo.ing

American open source frontier

Aravind Srinivas (@AravSrinivas) — Wed, 22 Jul 2026 01:54:12 GMT

American open source frontier

NVIDIA AI@NVIDIAAI

Congratulations to the students who competed at the International Mathematical Olympiad (IMO) 2026. 👏

We put Nemotron 3 Ultra to the test to take on the same problems in the same time limit, with no internet or external tools.

The IMO team graded its solutions 30/42, above the 29-point gold threshold. 🥇

🔗 View Quoted Tweet

💬5🔄10❤️288👀43962📊28

⚡ Powered by xgo.ing

Worth listening to if you want to understand how to use agents for financial research

Aravind Srinivas (@AravSrinivas) — Tue, 21 Jul 2026 21:06:09 GMT

Worth listening to if you want to understand how to use agents for financial research

Jeff Grimes@jeffgrimes9

Joined @LexSokolin on Fintech Blueprint to discuss:
- Perplexity Computer for managing personal finances
- the importance of traceability in AI financial research
- agent orchestration as a force multiplier for finserv

lex.substack.com/p/podcast-how-…

🔗 View Quoted Tweet

💬11🔄14❤️227👀51696📊44

⚡ Powered by xgo.ing

You can audit the trace of financial data to the source of truth when researching on Perplexity Comp...

Aravind Srinivas (@AravSrinivas) — Tue, 21 Jul 2026 02:52:08 GMT

You can audit the trace of financial data to the source of truth when researching on Perplexity Computer

Jeff Grimes@jeffgrimes9

Quality of life improvement: Perplexity Computer now displays company logos when financial data is cited in an answer.

All data is traceable back to original documents like SEC filings and earnings call transcripts. Derived data is shown with a full chain of formulas and calculations applied.

Your browser does not support the video tag.

🔗 View on Twitter

🔗 View Quoted Tweet

💬23🔄11❤️178👀33684📊32

⚡ Powered by xgo.ing

Well said!

Aravind Srinivas (@AravSrinivas) — Mon, 20 Jul 2026 15:34:19 GMT

Well said!

Bill Gurley@bgurley

The way to think about “open” in software is being a low-cost producer (vs a high margin one). When a company (or 2) achieves record valuations in record time, that rightfully attracts competition (as it should). We need to let the free market work. 

wapo.st/4pvR0mJ

🔗 View Quoted Tweet

💬15🔄16❤️218👀62484📊33

⚡ Powered by xgo.ing

Strong results

Aravind Srinivas (@AravSrinivas) — Sat, 18 Jul 2026 18:44:40 GMT

Strong results

Together AI@togethercompute

We analyzed Kimi K3 vs. Claude Fable 5 for software engineering tasks using DeepSWE.

Kimi K3 gets you the same performance as Fable 5 at ~35% of the price, and it actually pulls ahead at higher pass@k's. More insights in the thread!

🔗 View Quoted Tweet

💬38🔄54❤️969👀256429📊119

⚡ Powered by xgo.ing

Perplexity Agent API now supports custom skills.

Aravind Srinivas (@AravSrinivas) — Fri, 17 Jul 2026 20:47:08 GMT

Perplexity Agent API now supports custom skills.

Perplexity Developers@perplexitydevs

We just added Skills to the Perplexity Agent API. 

Agents aren't defined by a single system prompt. They are assembled from many capabilities that developers extend and compose. 

For example: pair our built-in office/pdf skill with your own inline design skill and your agent produces a finished, custom-formatted PDF research report in one go. 

Try our built-in skills (extended Skills Directory 🔜) or bring your own today.

Docs:docs.perplexity.ai/docs/agent-api…p
Research PDF cookbook:docs.perplexity.ai/docs/cookbook/…b

🔗 View Quoted Tweet

💬15🔄13❤️311👀78498📊38

⚡ Powered by xgo.ing

At its peak, Sun Microsystems was valued at 205B (394B if inflation adjusted). Sold software in ente...

Aravind Srinivas (@AravSrinivas) — Fri, 17 Jul 2026 18:47:54 GMT

At its peak, Sun Microsystems was valued at 205B (394B if inflation adjusted). Sold software in enterprise servers. Got disrupted by Linux, x86, and commodity hardware. Ended up selling to Oracle for 7.4B, losing 96% of its value. 

Open source models running on local hardware can have a similar impact given what’s going on.

💬233🔄590❤️6238👀1105741📊1066

⚡ Powered by xgo.ing

Agents love running on Vera CPUs. And the vertical integration of the sandbox runtime and CPU chip w...

Aravind Srinivas (@AravSrinivas) — Thu, 16 Jul 2026 23:59:07 GMT

Agents love running on Vera CPUs. And the vertical integration of the sandbox runtime and CPU chip will give margin, throughput, and latency advantages when serving cloud agents at scale.

NVIDIA AI Infrastructure@NVIDIAAIInfra

📣 @perplexity_ai launched SPACE, a secure sandbox platform built for agentic AI.

Early tests on NVIDIA Vera CPU showed up to 1.9x faster sandbox starts.

Faster starts = less latency, more parallelism, and agents that scale. Learn more now ⤵️

🔗 View Quoted Tweet

💬8🔄1❤️51👀8979📊10

⚡ Powered by xgo.ing

Interesting. The value is less in the weights but in the RSI harness and the ability to afford and r...

Aravind Srinivas (@AravSrinivas) — Thu, 16 Jul 2026 23:12:24 GMT

Interesting. The value is less in the weights but in the RSI harness and the ability to afford and run the inference on valuable context.

roon@tszzl

the world vision of open weights models running themselves, self replicating, training new versions of themselves (at least the kind of behavioral modifications that won't require massive compute scale), is really not very far away

🔗 View Quoted Tweet

💬6🔄1❤️83👀20206📊12

⚡ Powered by xgo.ing

Incredible

Aravind Srinivas (@AravSrinivas) — Thu, 16 Jul 2026 19:01:23 GMT

Incredible

Kimi.ai@Kimi_Moonshot

Introducing Kimi K3: Open Frontier Intelligence

🔹 2.8 Trillion Parameters, 1 Million Context, Native Multimodal
🔹 Kimi Delta Attention enables up to 6.3x faster decoding in million-token contexts
🔹 Attention Residuals deliver ~25% higher training efficiency at <2% additional cost
🔹 Built for long-horizon agentic coding and self-evolving workflows

Kimi K3 is now live onKimi.comxZUo, Kimi Work, Kimi Code, and the Kimi API.
Open Weights by July 27, 2026.

🔗 platform.kimi.aiXAqMw
🔗 Tech kimi.com/blog/kimi-k3MSNM1f

🔗 View Quoted Tweet

💬32🔄74❤️1889👀174974📊185

⚡ Powered by xgo.ing

Perplexity Agent API is powerful for investment workflows when used inside LangChain

Aravind Srinivas (@AravSrinivas) — Thu, 16 Jul 2026 16:52:27 GMT

Perplexity Agent API is powerful for investment workflows when used inside LangChain

LangChain@LangChain

This agent drafts a cited VC investment memo in ~90 seconds for $0.40.

1️⃣ 4 LangGraph nodes powered by the @Perplexity_AI Agent API research financials, product, and market in parallel
2️⃣ A tool-less synthesizer writes the memo from only what they found

Deep dive:
langchain.com/blog/build-an-…

🔗 View Quoted Tweet

💬17🔄15❤️202👀34179📊33

⚡ Powered by xgo.ing

Computer Artifacts (web apps, docs, slides, sheets, …) managed on one single tab across sessions

Aravind Srinivas (@AravSrinivas) — Thu, 16 Jul 2026 15:09:53 GMT

Computer Artifacts (web apps, docs, slides, sheets, …) managed on one single tab across sessions

Computer@AskPerplexity

The Artifacts page now has a "Created by you" tab, showing you just the artifacts that Computer has made for you in your sessions.

You can also filter by artifact type: reports, documents, spreadsheets, apps, presentations, images, videos, audio, and more.

Live now on the web for all Computer users.

Your browser does not support the video tag.

🔗 View on Twitter

🔗 View Quoted Tweet

💬17🔄8❤️158👀43352📊25

⚡ Powered by xgo.ing

Follow @zbraniecki, the key technical architect of Perplexity Computer agent’s sandbox platform SPAC...

Aravind Srinivas (@AravSrinivas) — Wed, 15 Jul 2026 17:56:07 GMT

Follow @zbraniecki, the key technical architect of Perplexity Computer agent’s sandbox platform SPACE!

Zibi Braniecki@zbraniecki

Our team had to build a novel sandbox solution to handle the needs of Computer.

One Computer session can run for days and pause while it waits for a user. Keeping its VM alive wastes memory and compute and restoring from the filesystem alone also loses running processes and memory.

SPACE uses two kinds of snapshots. Disk snapshots run frequently without pausing the VM and let us roll back filesystem changes. Full checkpoints are less frequent and capture the paused VM, including its memory and process state.

When a session is suspended, we upload its full checkpoint to object storage. We only mark it restorable after every artifact has landed. Any node can then fetch the filesystem delta and VM state, so recovery does not depend on the original machine.

Btrfs makes this cheap enough to run continuously. Templates, snapshots, and forks share the same extents until something writes to them. Creating a sandbox becomes a copy-on-write metadata operation instead of a full image copy.

On production traffic, median creation latency fell from 185 ms to 60 ms. P90 fell from 447 ms to 89 ms.

🔗 View Quoted Tweet

💬21🔄23❤️429👀106983📊62

⚡ Powered by xgo.ing

Check out our research blog for more details! https://t.co/V9wTeXdvPy

Aravind Srinivas (@AravSrinivas) — Wed, 15 Jul 2026 17:12:43 GMT

Check out our research blog for more details! research.perplexity.ai/articles/makin…

💬2🔄1❤️24👀4849📊5

⚡ Powered by xgo.ing

And credentials are never stored in any of the SPACE runtimes directly; which is absolutely essentia...

Aravind Srinivas (@AravSrinivas) — Wed, 15 Jul 2026 17:11:52 GMT

And credentials are never stored in any of the SPACE runtimes directly; which is absolutely essential as agents access sensitive files in long running trajectories

Perplexity@perplexity_ai

Agent infrastructure must be functional, efficient, and secure and traditional sandboxes were built for short-lived code execution.

Agents need to run code, edit files, and run for hours or days. Runtimes must preserve work without leaving credentials inside environments.

🔗 View Quoted Tweet

💬4🔄0❤️23👀8123📊5

⚡ Powered by xgo.ing

The cost advantages are incredible, especially at the scale we operate in. Compared to Vercel, SPACE...

Aravind Srinivas (@AravSrinivas) — Wed, 15 Jul 2026 17:09:14 GMT

The cost advantages are incredible, especially at the scale we operate in. Compared to Vercel, SPACE is 5x cheaper, leading to savings of tens of millions of dollars a year.

💬5🔄2❤️111👀30580📊15

⚡ Powered by xgo.ing

We’ve built our own sandbox lifecycle management platform SPACE to serve all production traffic of P...

Aravind Srinivas (@AravSrinivas) — Wed, 15 Jul 2026 17:06:34 GMT

We’ve built our own sandbox lifecycle management platform SPACE to serve all production traffic of Perplexity Computer. 
When we rolled out Computer in February, we ran it on one of the sandbox providers. Today, we serve 100% of the traffic on SPACE with 5x faster tail latency.

Perplexity@perplexity_ai

Introducing SPACE, the sandbox platform behind Perplexity Computer.

It creates isolated environments for code, files, and long-running agent sessions.

SPACE has handled 100% of Computer production traffic since June.

research.perplexity.ai/articles/makin…

🔗 View Quoted Tweet

💬38🔄24❤️372👀106648📊66

⚡ Powered by xgo.ing

Wide Research is now available in Perplexity Agent API

Aravind Srinivas (@AravSrinivas) — Tue, 14 Jul 2026 22:37:17 GMT

Wide Research is now available in Perplexity Agent API

Perplexity Developers@perplexitydevs

Narrow search is essentially solved. That's why simple browse/search benchmarks are so saturated.

The frontier is wide research: find every qualifying result and back each one with evidence. 

Today we launched WANDR, a 500-task benchmark built on real knowledge work. It's difficult even for today's most powerful models. 

Perplexity Agent API's Search as Code architecture excels on WANDR because it allows the model to design the research once and then deterministically execute it at scale without overwhelming the model’s context.

Using wide research in your existing agent research workflows? Try out our wide-research preset in Agent API: docs.perplexity.ai/docs/agent-api…

WANDR Research Article: research.perplexity.ai/articles/wandr…
Github Repo: github.com/perplexityai/w…

🔗 View Quoted Tweet

💬22🔄26❤️271👀40514📊46

⚡ Powered by xgo.ing

Perplexity has the best (both on cost and performance) deep and wide research harness in Computer. O...

Aravind Srinivas (@AravSrinivas) — Tue, 14 Jul 2026 18:59:59 GMT

Perplexity has the best (both on cost and performance) deep and wide research harness in Computer. One of the contributing factors is strong internal evals and benchmarks. Today, we're open-sourcing WANDR, the benchmark we use internally for measuring research capabilities.

Perplexity@perplexity_ai

We’re open sourcing WANDR.

WANDR is an internal benchmark we built and used for building deep and wide research capabilities inside Perplexity Computer.

research.perplexity.ai/articles/wandr…

🔗 View Quoted Tweet

💬31🔄48❤️540👀63904📊81

⚡ Powered by xgo.ing

Sometimes, the optimal action is no action.

Aravind Srinivas (@AravSrinivas) — Tue, 14 Jul 2026 05:50:08 GMT

Sometimes, the optimal action is no action.

💬64🔄31❤️771👀53469📊134

⚡ Powered by xgo.ing

there are two viable paths to overcome the power botteneck in data center inference: 1) local model...

Aravind Srinivas (@AravSrinivas) — Mon, 13 Jul 2026 19:18:31 GMT

there are two viable paths to overcome the power botteneck in data center inference:

1) local models orchestrating most of the token flow
2) solar powered data centers in space

💬83🔄23❤️498👀52323📊124

Aravind Srinivas(@AravSrinivas)

Perplexity Agent API is the best for web search and browsing agents

Congrats to @SpaceXAI on one more amazing model: Grok 4.6. We benchmarked it as an orchestrator on o...

Gemini Flash models are great for fast, cost-efficient subagents inside any multi-model harness. We ...

Nemotron 3.5 Lightning available to all developers on the Perplexity Agent API. Input: $0.0115 pe...

A great American open weights MoE model that can run efficiently on your laptop or local hardware li...

Compute is the currency

enjoy US hosted K3 on perplexity agent api!

Perplexity Computer’s goal is to provide the maximum intelligence for minimum cost with multi model ...

Verification is key when using agents for high stakes research!

Two orders of magnitude improvements are quite rare. This is a big deal.

Follow @kpolley, Perplexity's CISO

Read more here: https://t.co/ia67hU6q6L

And with Computer Brain, every project goes through self-improvement loops on its memory, leading to...

Introducing Projects on Perplexity Computer. With the launch of Projects, we're turning Computer int...

Perplexity Pro users can now use Model Council with Computer credits. It's a user favorite when it c...

US-hosted Kimi K3 now available on Perplexity for Pro and Max, both in Search and Computer modes. En...

We look forward to open sourcing a lot more tools and benchmarks that will continue to strengthen th...

And open sourced BrowseSafe, an open benchmark for protecting agents against prompt injection on web...

When Hugging Face got breached, the closed tools couldn't distinguish attackers from defenders and b...

True

GLM is such an underrated model considering how intelligent it is at the parameter size it has (700b...

Good observations

Perplexity is now available as a CLI that can be used inside any harness. Pretty useful for letting ...

today is the most positive i have felt about the future of american ai. the coming together of so ma...

“Open weights strengthen competition and competition is what keeps the benefits of AI broadly shared...

Everything is a distillation of Schmidhuber.

Well said!

future: continual learning of the model + harness hosted on hardware you own and control, with full ...

Already the second most used orchestrator model on Perplexity Computer now, only behind Opus 4.8. O...

American open source frontier

Worth listening to if you want to understand how to use agents for financial research

You can audit the trace of financial data to the source of truth when researching on Perplexity Comp...

Well said!

Strong results

Perplexity Agent API now supports custom skills.

At its peak, Sun Microsystems was valued at 205B (394B if inflation adjusted). Sold software in ente...

Agents love running on Vera CPUs. And the vertical integration of the sandbox runtime and CPU chip w...

Interesting. The value is less in the weights but in the RSI harness and the ability to afford and r...

Incredible

Perplexity Agent API is powerful for investment workflows when used inside LangChain

Computer Artifacts (web apps, docs, slides, sheets, …) managed on one single tab across sessions

Follow @zbraniecki, the key technical architect of Perplexity Computer agent’s sandbox platform SPAC...

Check out our research blog for more details! https://t.co/V9wTeXdvPy

And credentials are never stored in any of the SPACE runtimes directly; which is absolutely essentia...

The cost advantages are incredible, especially at the scale we operate in. Compared to Vercel, SPACE...

We’ve built our own sandbox lifecycle management platform SPACE to serve all production traffic of P...

Wide Research is now available in Perplexity Agent API

Perplexity has the best (both on cost and performance) deep and wide research harness in Computer. O...

Sometimes, the optimal action is no action.

there are two viable paths to overcome the power botteneck in data center inference: 1) local model...