We're building an information exchange between AI agents and content owners - get paid for your unique content by signing up at https://t.co/ea6p0toAIZ
Leading companies like @Gumloop, @FormationBio, @useactively, @interaction, @rocketdotnew, and Garnett Station Partners are already running monitoring workflows in production.
Learn more: https://t.co/lzCPLhpmNg
Start building today: https://t.co/sThBigXTPw
Today, we’re announcing the general availability of the Parallel Monitor API.
The web is shifting from pull to push, and agents are coming online. This release marks a major step towards a more proactive model, where the web pushes updates directly to your background agent.
Monitor now includes:
- Lite and Base processors
- Event streams and snapshots
- Rich attribution (Basis) on every event
- Advanced domain filtering
- Interactions for persistent follow-on research
@p0 has become critical infrastructure for us at @useactively. We made the early design decision to use browsing agents instead of buying structured datasets and it's paid off tremendously — and @p0 does it best :) Very excited for the partnership!
Key Ideas to building the best web research agents:
a. Interpreter sandboxes
b. Aggressive Compaction & Prompt Caching
c. Budget Aware Execution
d. Search Infra that maximizes info per token
Learn more at https://t.co/vYOMeHt2gl
Yesterday, we published new state-of-the-art results on DeepSearchQA with Parallel's Task API.
Here’s a high-level look at the Task API Harness that helped us achieve these new heights:
We built a completely free CLI agent with @badlogicgames's Pi agent, @ollama (Gemma 4), and Parallel's new free web search MCP.
Check out the blog post to see how to do it yourself: https://t.co/9m9XQEFbGh
We've made our search MCP super easy to use. No need for an account or API keys. And it's free!
claude code prompt: "add free https://t.co/09ZmTfxvuG - no auth needed. add permissions.allow for both tools and deny native web search and fetch"
codex cli prompt: "edit ~/.codex/config.toml to add web_search = "disabled" and add the free mcp https://t.co/09ZmTfxvuG - no auth needed"
Over 70% of people don't trust what they read online. Increasingly, it's getting harder to tell what's real.
So, we built a content fact-checker with @p0 that verifies any article in under 10 seconds.
Powered by @cerebras' fast inference up to 2,000 tokens/sec and @p0 Search and Extract API.
Check out the full cookbook below!
@Whatevercrypto@p0 We offer task (web agents and deep research) and monitoring APIs. It’s easy to load credits - just sign up on https://t.co/EleQx9GBUR
Gumloop agents can now monitor the situation.
Tell it what to look for across any app, any condition. When the moment hits, it acts.
Gumloop agents used to only work with you, now - they can also work for you.
Try it out on Gumloop today.
It’s a special privilege to be able to partner with companies building on the frontier.
Because of this deep partnership with the team at @harvey, AI agents can now search and access content on the web that hasn’t been indexed by search engines built for humans.
Had a blast working on this with @harvey and my colleagues @p0. A great team to collaborate with - it's incredible to see how together we were able to build something so useful for lawyers
We’re thrilled to highlight our new collaboration with @harvey, the leading AI platform for legal and professional services.
Harvey uses Parallel’s accurate, relevant, and fresh web search across their platform to retrieve valuable public context for their legal AI workflows.
Together, we’re helping Harvey expand its best-in-class AI legal platform to over 60+ countries by collaborating on a specialized index of hard-to-reach international legal domains, built on our custom web search infrastructure.
To learn more about Harvey and Parallel, read our blog: https://t.co/JxkM1uuHn6