Utkarsh Srivastava

Leading engineering at Parallel Web Systems

[Vals AI @ValsAI]

Claude Opus 5.5 with Parallel Fast is now #1 on the Vals Web Search Index, scoring 57.5% overall against 53.8% for the same model with native search a gain of 3.8pp.

[Khushi Shelat @khushi_shelat]

companies make big promises on earnings calls. I built a way to trace each goal through time and see what happened.

it updates regularly as new earnings calls complete. built with @p0's task & monitor APIs.

gh repo in 🧵

[OpenRouter @OpenRouter]

What's better than the highest accuracy web-grounded decisions model? How about a week of free requests?

Try Parallel Decisions to get fast structured answers about the live web with probabilities and citations, free for 7 days exclusively for OpenRouter users!

[Utkarsh Srivastava @utkarsh]

Get started with our grounded decisions API on OpenRouter, try for free for 7 days with your OpenRouter key.

[Models on OpenRouter @ModelsOnOR]

Parallel Decisions is now on OpenRouter. Parallel Decisions delivers the highest accuracy on web-grounded decisions for System One models like Jev. Get web-grounded answers 13× faster at 1/16 the cost of OpenAI’s GPT Luna with native web search.

Ask questions about the live web and get structured answers with probabilities and citations in under a second.

[Utkarsh Srivastava @utkarsh]

Easiest way to get started with Parallel, no auth or key required.

[Parallel Web Systems @p0]

Parallel MCP 2.0 is live.

It's the most powerful web search and retrieval MCP, launching today with four tools for agentic search:

- Web search
- Page extract
- Web-grounded decisions
- Deep research

Parallel MCP is free and keyless by default, with auth for advanced features and higher limits.

It's also the most configurable web data MCP, designed for admins to define web research standards across an entire fleet of agents.

Add it to any MCP client: https://t.co/sla9L3nEib

Learn more: https://t.co/5C2CHSj6IV

[Utkarsh Srivastava @utkarsh]

Parallel's Monitor API is the perfect shape for the coming wave of proactive agents. Excited for this partnership with @browserbase

[Parallel Web Systems @p0]

Personal Agents like BELL should always know what's happening, without you having to ask.

We partnered with @browserbase to add Parallel's Monitor API to BELL.

Monitor is like a web search that's always on. Now your personal assistant can keep track of the web and alert you when something changes 🔔

[Utkarsh Srivastava @utkarsh]

Open sourcing our benchmark to show how much more accurate our grounded decisions API is compared to the other decision models in use.

[Parallel Web Systems @p0]

Parallel Decisions beats Perplexity by 1.5x and OpenAI by nearly 2x on decisions that depend on the live web.

We’re open-sourcing the benchmark: PWS-Decisions, 300 questions whose answers change with the world. Run it on your own model.

Full results: https://t.co/a5VquXmzEH

[Utkarsh Srivastava @utkarsh]

This slack plugin has been such a favorite internally. High precision monitors that proactively tell you what you care about in the context on a particular slack channel is a killer feature.

[Parallel Web Systems @p0]

Introducing Parallel in Slack.

Tell Parallel what to monitor on the web, and the agent posts in the channel when there's a hit.

Or tag it with a question to get a cited answer based on the context in your thread.

Available today on the Slack Marketplace.

[Utkarsh Srivastava @utkarsh]

Announcing frontier performance on Finance for our search API

[Parallel Web Systems @p0]

Announcing Parallel for Finance: universal upgrades that make us the unmatched SOTA web search for Finance AI on the cost-accuracy frontier.

- On FinSearchComp's hardest tier (T3), Parallel is the most accurate search API at up to 2x lower cost than Exa and Perplexity. Parallel Fast comes second, at 10x lower cost than the others.

- On @samaya_AI's FrontierFinance, Parallel ties for the top score at 38% lower cost than Exa, and beats OpenAI, Perplexity, and Tavily on both accuracy and cost.

- On our new private PWS-Finance benchmark, Parallel leads, beating OpenAI's native search at 30% lower cost.

[Utkarsh Srivastava @utkarsh]

Don’t flip a coin on decisions that need the latest data, use our grounded decisions api.

[Parallel Web Systems @p0]

Introducing the Parallel Decisions API: the first web-grounded decisions engine.

Decision models like Jev can answer in an instant, but they lack the recency of current news. Now you can get both in a single call.

Decisions API is live today at $0.001 per request.

Try it with 5,000 free requests: https://t.co/tu4CidUdxV

Here are some examples we've been experimenting with:

- Fact-check content (@Grok is this true?)
- Refresh stale banking records
- Classify companies and leads with fresh signals
- Backtest trading strategies
- Track competitor e-commerce inventory

[Utkarsh Srivastava @utkarsh]

@everythingmeta well put! Inference prices will keep coming down and it'll keep getting faster, web search needs to keep up in both speed, and cost.

[Sid Nanda @sidstronaut]

Not a surprise that Parallel tops the board here, which is why @finchlegal has been excited to partner with @p0 over the last 9 months!

[Parag Agrawal @paraga]

Great to have rigorous independent benchmarking for search that measures end-to-end quality, cost, latency for agents.

Parallel search is
(1) Highest quality
(2) Quality vs. cost Pareto frontier
(3) Quality vs. latency Pareto frontier

[Parallel Web Systems @p0]

Introducing Parallel Search Turbo: the fastest and most affordable way to bring the web to your AI.

[Utkarsh Srivastava @utkarsh]

@p0 So proud of the team’s work on this new architecture that enables a new frontier on cost, quality, latency for web search for agents.

[Parallel Web Systems @p0]

The best web search for AI is now the keyless default in @openclaw

Free, no account, LLM-optimized. Just powerful web search for your claw 🦞

[Redpoint @Redpoint]

The Redpoint InfraRed 100 is now live.

These are the companies building the infrastructure that powers everything happening in AI right now, from world models and agent runtimes to the sandboxes, databases, and security tools agents depend on.

Congratulations to this year's honorees!

Read the full 2026 InfraRed Report: our state of the union on AI and cloud infrastructure 👉 https://t.co/Y1y94ZwI5B

[Rohan Suri @rohansuri_]

Shoutout to the partners who made this possible – @temporalio , @p0 ,@vercel , @elastic , @OpenAI , @AnthropicAI and others whose infra is powering the execution layer underneath.

Building at the frontier means standing on serious technical shoulders.

[Patrick Collison @patrickc]

Cool release from @p0. I think this use-case (agents paying content creators for access via @mpp) will be very big. Micropayment walls haven't worked (as Clay Shirky anticipated many years ago) because of human cognitive overhead, but agents can make arbitrarily granular determinations without decision fatigue.

[OpenRouter @OpenRouter]

Any tool-calling model on OpenRouter can call web search and web fetch agentically.

The model decides when to search, what to search for, and how many times.

We've added @p0 as a new web search provider. Learn more: https://t.co/dDKZ24VcqN