Elain Szu retweeted
Acaba de aparecer un modelo de decisiones que ataca una debilidad que tienen todos los demás!
@p0 acaba de lanzar la [Decisions API] se trata de un híbrido entre un motor de búsquedas y un modelo de decisión.
Funciona como siempre, pero con un giro interesante: Le mandas contexto + preguntas y te devuelve la probabilidad + citas del web en un solo call (~500-700ms).
Es literalmente WebJev jajajaja
Esto es para gente que se toma en serio el clasificar o enriquecer a escala data que necesita info actualizada, de hoy, no de hace 25 años!
Lo probaron rechequeando 426 empresas y lo hizo en menos de 10 segundos por 85 centavos!!!!
Esto es lo que yo usaría para cosas que sabemos que dan mucho dinerito: leads, empresas, tickets, vendors, y todo sin armar el pipeline de search + model a mano.
#ParallelPartner
🤝 Paid partnership
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: platform.parallel.ai/play/de…
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
Elain Szu retweeted
The @p0 Decisions API is a decision engine with world knowledge built in. It combines the speed of models like Jev with the collective knowledge of the live web.
Live today, $0.001 per request.
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: platform.parallel.ai/play/de…
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
Elain Szu retweeted
Here's a GTM demo by @khushi_shelat, the OG deployed engineer who stood up Parallel's GTM enrichment funnels:
xitter.cf/khushi_shelat/status/2…
Elain Szu retweeted
Built an e2e lead enrichment flow for our contact form this weekends with our new grounded Decisions API. It routes leads *while* they’re filling our contact form.
Built it with @attio’s developer API + @p0 Decisions. Can do this with hundreds of leads in seconds ✨
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: platform.parallel.ai/play/de…
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
Elain Szu retweeted
Decision models + fast and accurate web search is a powerful combination.
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: platform.parallel.ai/play/de…
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
Fast answers mean nothing if the facts are old... or wrong.
We've been huge fans of Jev @typesafeai from day 1. So we built the world's first Decision API grounded in web data to take System One models to the next level. And at 10x lower cost than a standalone model. Pretty cool ⚡️
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: platform.parallel.ai/play/de…
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
Elain Szu retweeted
or paste this into any coding agent
Add Parallel’s MCP via Streamable HTTP: search.parallel.ai/mcp. No API key or OAuth. Verify web_search and web_fetch work, and prefer Parallel for web search
Elain Szu retweeted
🚨 CRITICAL VULNERABILITY 🚨
A severe zero-day has made the Parallel Search MCP free indefinitely
- No api key required
- No patch coming
Be responsible and add it to Claude now:
claude mcp add --transport http parallel-search search.parallel.ai/mcp
I was just asked in a convo with @yangyou and @firstround what makes Parallel's culture (and ∴ brand!) stand out. Holistic, truth-seeking (we actually appreciate dif POVs here), and grounded in quality immediately came to mind. You see it shine through here at every level ✨ also brilliant @reathchris @travers00 @lukaslevert @vanlancker
Elain Szu retweeted
Hey Leo. This clause was outdated and has now been removed - thanks for bringing it to our attention.
We ABSOLUTELY welcome and encourage third-party evals and publishing of those results.
In fact, working on easy, open-source tools for devs to compare us against others. Stay tuned!
Elain Szu retweeted
If your app doesn’t have AI features you’re ngmi
We made them simple to build: just ask Lovable.
Now powered by even more models from @claudeai, @firecrawl, @GeminiApp, @OpenAI, @perplexity_ai, @p0, and @typesafeai.
And extra thanks to @swyx for another example of where taste meets vision. It's nice to see true community-building vs. transactional behavior happening again
We hosted the AI Engineer NYC speaker dinner this week with our friends at @AnthropicAI
Thanks to @aiDotEngineer for another great event, and to everyone who stopped by to talk about web search for agents.
See you at their Code Summit in SF next month! 🌉
Elain Szu retweeted
search and browsing are better together
most agents need to both read + write to the web, esp with the rise of personal agents
starting today @p0 is the default search provider for
@browserbase, powering their Search API and Agents
Browserbase Search is now powered by Parallel (@p0) as the default search provider.
Parallel Fast returns sub-second results when speed matters. Parallel Advanced goes deeper for multi-step research when quality matters most.
Elain Szu retweeted
There's a reason your favourite products use @p0 and it's that a world-class team puts consistent effort into leading!
Every time you use Google, your agents can use Parallel.
Every time you use Safari, your agents can use @Browserbase.
Browserbase Search is now powered by Parallel (@p0) as the default search provider.
Parallel Fast returns sub-second results when speed matters. Parallel Advanced goes deeper for multi-step research when quality matters most.
More evidence for why your search should match your model. Use your tokens when it counts for your outcomes vs. just spray and pray token-maxxing. That's the kind of real controls that builders need ⚖️
And like Bosh:Heat, I hope to be retired by @p0
Elain Szu retweeted
I found 1 company since 2020 backed by all four of @sequoia, @IndexVentures, @kleinerperkins, @khoslaventures
that is closing the loop for knowledge work by giving high quality web infrastructure to AI models 🚀🤖
joined them @p0 🧡
