Plurai

The recursive self-improvement layer for AI agents.

[Uri Eliabayev @urieli17]

יום גדול ל Plurai!
יוצאים רשמית עם המוצר ומודיעים על גיוס של 13 מיליון דולר בהובלת Team8.

גאה להיות בצוות Advisory ולקחת חלק מהמסע שלהם.

המוצר שלהם הוא העתיד לדרך שבה חברות יעבדו עם מודלי שפה.

[Ilan Kadar @ilan_kadar]

Big day for us at @pluraiAI ! Plurai Simulation is live and free for every AI engineer.

AI agents look great in demos. Until real users break them.

So we built a world where your agent can fail, learn, and get fixed before your users ever see it.

→ Digital twin: Your real agent, its tools, and environment recreated from your code

→ Simulated users & tasks: Realistic users, tasks, and workflows that push your agent into the edge cases that matter

→ Auto evals: Check what your agent actually did, not just what it said

→ Verified fixes: Every failure comes with the run that exposed it and a fix you can verify

→ Replays: Turn any production failure into a simulation and replay it against every new version of your agent

All inside the coding agent you already use: @claudeai code, @OpenAICodexCli , or @GitHubCopilot .

Start simulating for free: https://t.co/1PNPQdW29S

[Plurai @pluraiAI]

Today we're launching Plurai Simulation, the self-improvement layer for AI agents, free for every AI engineer, and announcing our $13M seed round led by Team8, with U&I, Velocity, and a group of industry leaders.

AI agents deliver incredible demos. But the moment they meet real customers, they enter the long tail: unexpected requests and rare situations no one planned for. Testing more won't catch it. What works is finding the edge cases that matter and learning from them before a single customer runs into one.

So we built Plurai Simulation. It recreates an agent's world with realistic users, tools, and workflows, discovers failures, understands why they happen, and turns them into fixes and training data for specialized models that make agents more accurate, faster, and dramatically cheaper to run. New production failures feed back into simulation, creating a continuous cycle of self-improvement.

Simulation is how Waymo earned trust on the road. Now it's becoming the standard for AI agents.

Our design partners are already seeing it: development cycles cut from months to hours, 82% fewer failures reaching real users, and 97% lower costs.

Starting today, it's free directly from Claude Code, Codex, and GitHub Copilot, with Cursor coming soon.

Start free: https://t.co/Nqire8rpSR

[Ilan Kadar @ilan_kadar]

Check out our latest research, SCOPE, showing how small open models can match frontier models on complex policy checks, at 47x lower cost, with far more consistent results.

A big step toward making AI agents more reliable, explainable and affordable at scale.

We've also made the research paper and benchmark publicly available on @huggingface so the AI community can test new approaches, compare results, and help push the field forward.

Kudos to Elad Levi, Arnon Mazza, and the entire @pluraiAI team for continuing to push the state of the art forward every single day!

[Plurai @pluraiAI]

Small open models can match frontier models on complex policy checks: 9–47x cheaper and way more consistent.

Our new method, SCOPE, turns a plain-language policy into yes/no questions a cheap model can answer.

Paper + open benchmark here -
https://t.co/IKl4vJATSK

[Plurai @pluraiAI]

Small open models can match frontier models on complex policy checks: 9–47x cheaper and way more consistent.

Our new method, SCOPE, turns a plain-language policy into yes/no questions a cheap model can answer.

Paper + open benchmark here -
https://t.co/IKl4vJATSK

[Uri Eliabayev @urieli17]

כמה גאווה!
החבר'ה של Plurai בשיתוף פעולה מדהים עם נביוס ואנבידיה בו הצליחו להוריד את העלות של מודלי AI פי 44 בזכות היכולת שלהם לבנות מודלי שפה קטנים למשימות ספציפיות.

זה העתיד ועכשיו הוא כבר ההווה.

[Ilan Kadar @ilan_kadar]

Excited to announce our collaboration with @nvidia and @nebiusai at @nvidia GTC Berlin!

We post-trained @nvidia 's Nemotron 3.5 Lightning into a specialized model that outperforms @AnthropicAI Claude Haiku 5.5 at 44× lower cost and matches @OpenAI 's GPT-6 Luna at 40× lower cost on a real-world enterprise task, with @nebiusai Token Factory providing the infrastructure to scale.

With @pluraiAI 's vibe-training, any engineer can go from a task description and a few production examples to a post-trained, benchmarked, production-ready model in under 20 minutes.

What excites me most is that this same workflow can be applied to any open-source model, turning it into a specialized, frontier-beating model at a fraction of the cost.

Huge thanks to our incredible partners at @nvidia and @Nebius for the close collaboration and for pushing the boundaries of what's possible together.

This is just the beginning, with much more to come!

Full research: https://t.co/FrlPcUMVCP

[Plurai @pluraiAI]

Excited to announce our collaboration with @nvidia and @nebiusai at NVIDIA #gtcberlin!

We post-trained NVIDIA’s Nemotron 3.5 Lightning into a specialized model that outperforms Claude Haiku 5.5 at 44× lower cost and matches OpenAI’s GPT-6 Luna at 40× lower cost.

With Plurai, any engineer can go from a task description and a few production examples to a post-trained, benchmarked, production-ready model in under 20 minutes.

Works on any open-source model.

Full research: https://t.co/zBcu7NYrpL

[Plurai @pluraiAI]

Excited to announce our collaboration with @nvidia and @nebiusai at NVIDIA #gtcberlin!

We post-trained NVIDIA’s Nemotron 3.5 Lightning into a specialized model that outperforms Claude Haiku 5.5 at 44× lower cost and matches OpenAI’s GPT-6 Luna at 40× lower cost.

With Plurai, any engineer can go from a task description and a few production examples to a post-trained, benchmarked, production-ready model in under 20 minutes.

Works on any open-source model.

Full research: https://t.co/zBcu7NYrpL

[Ofir Ehrlich @OfirEhrlich]

You can’t safely test an enterprise agent on a real company’s data.

So we built a company for it to work in.

Era is live today, and it’s free.

It generates a complete simulated enterprise that behaves like a real one across Salesforce, Slack, Jira, Zendesk, Gong, Deel and more, along with cloud databases and storage. Agents interact with it through live MCP and API interfaces.

People leave. Deals change. Records get duplicated. Permissions differ across systems. And because Era generated the company, it knows the exact ground truth.
Test, benchmark and improve agents against realistic enterprise workloads, use the failures for targeted post-training, then rerun the same environment to measure the impact.

Huge thanks to our research partners @NVIDIA, @Decart, @Composio, @openlayerco, @Deel, @Eragon and @Plurai, with more coming soon.

[Plurai @pluraiAI]

Second @Gartner_inc mention for Plurai.

This time it's "8 Emerging Practices for Testing AI Agents" - citing Plurai #Evals & #Guardrails as an example of building purpose-built small models for scoring, completeness, and safety checks.

Testing can't stop before launch. And you can't grade every production interaction with a frontier model.

https://t.co/dG6o3YbxHh

[Plurai @pluraiAI]

Second @Gartner_inc mention for Plurai.

This time it's "8 Emerging Practices for Testing AI Agents" - citing Plurai #Evals & #Guardrails as an example of building purpose-built small models for scoring, completeness, and safety checks.

Testing can't stop before launch. And you can't grade every production interaction with a frontier model.

https://t.co/dG6o3YbxHh

[Akshay 🚀 @akshay_pachaar]

If you use LLM-as-judge, this one is for you.

(bookmark it)

Most teams validate their agent's outputs by calling a frontier model as the judge. It works, until it doesn't.

Three problems stack up fast:

→ Cost: you're hitting a frontier API on every turn, every tool call, every response. In production that burns millions.

→ Latency: bigger models, remote calls, slow reasoning on every check.

→ Blind spots: frontier models don't actually know your domain. In finance, insurance, or healthcare, they miss the keywords and principles your work depends on.

So I walk through a different approach: train your own small LLM judge.

Instead of a giant model, you start with a small one and let the system generate the training data for you. It decomposes your domain, samples synthetic examples, runs them through a debate arena where judges reach consensus, then trains on the refined set.

The result is a judge that's cheaper, faster, and more accurate on your data than Gemini, Claude, or GPT, with an OpenAI-compatible endpoint you can even deploy on-prem.

I show the whole thing end to end, using a Claude Code plugin and a web interface, with a real insurance RAG grounding evaluator as the example.

You can get the plugin here: https://t.co/uq1RrvBxtI

Here's the full breakdown:

00:00 - Intro
00:12 - Three problems with using frontier LLMs as judges
01:05 - A different approach: train your own small judge
01:31 - How it works (synthetic data and a debate arena)
02:50 - Installing the Claude Code plugin
04:03 - Defining your task with /eval
04:34 - Example: an insurance RAG grounding evaluator
05:51 - Kicking it off and giving early feedback
06:26 - Choosing labels, domain, and strictness
08:30 - The web interface and dashboard
09:52 - Bringing your own example data (optional)
10:26 - The finished model: endpoint, accuracy, and speed
11:16 - Control, on-prem deployment, and interpretability
11:57 - Benchmarks vs frontier models and the GitHub repo
12:30 - Outro

I worked with the @pluraiAI team on this. Thanks for sponsoring the video.

[Plurai @pluraiAI]

We're launching vibe training.
Describe what your agent should and shouldn't do.
We generate the edge cases, build the test set, train a model calibrated to your policies.
In minutes.

[Plurai @pluraiAI]

@fmerian Thank you Florian!

[Plurai @pluraiAI]

Within hours of our launch, thousands of agent builders were already live with vibe training.
Today we're on Product Hunt. An upvote takes 30 seconds.
👉 https://t.co/0DSKjrXv7s

[Ilan Kadar @ilan_kadar]

Yesterday blew past every expectation.
I barely slept (2 hours, if I’m honest)… and now we’re heading straight into our #ProductHunt launch and I need you! 🚀

Because something clicked.
We launched vibe training - and within hours, thousands of agent builders started creating evals and guardrails for their own use cases!

It’s moving fast.
Because the truth is simple:
Building agents is easy.
Making them reliable in production is not.
That’s what vibe training fixes.

If you’ve been following, building with us, or just rooting from the sidelines — we need your support ❤️
• Open the link
• Hit upvote
• Drop a quick comment

This takes 30 seconds and directly impacts our ranking.
Let’s push this to the top today
https://t.co/Np5GbG2xWm

[Plurai @pluraiAI]

@kunalstwt Thanks @kunalstwt !

[Plurai @pluraiAI]

@mimu_ai1 Thank you!

[Plurai @pluraiAI]

@aaliya_va Thank you!

[Kunal Kushwaha @kunalstwt]

Air Canada’s chatbot once literally made up its own refund policy in court and won a lawsuit for the customer, not the airline.

There’s a new term being coined right now called vibe training by the company @pluraiAI, and they’ve basically built a way to use tiny, fast models as guardrails to catch hallucinations in sub-100ms and the cost is over 8x lower than GPT-5-mini.

🔥👉 They’re live on Product Hunt today: https://t.co/oCrSIlcaMH

If you’re building agents, go check them out, grab the free trial, and show them some love on the launch! 🫶

The best part? You don’t need a PhD in AI. Sponsored by Plurai.