Two Team8 Infra Village stages this week, Palo Alto + NYC. Same takeaway from @ilan_kadarโs talks: models are a commodity. Knowing how your agent behaves isnโt.
Next: @AWSreInvent , Nov 30โDec 4, booth #1519.
Find your agentโs long tail before your users do.
5
108
Plurai retweeted
#GTA6 drops today. AI agents deserve a world to crash in too.
Last week we put Plurai Simulation in the hands of every AI engineer. Today weโre excited to launch our first new feature: Replay. It takes a failure from production and brings it back into the simulation, so you can fix it at the exact moment it broke.
The problem: agents donโt fail the same way twice. An agent breaks on turn 7 of a production conversation. You rerun it from turn 1, and by turn 2 the wording has drifted. By turn 4 itโs calling a different tool, and it never gets back to the failure. So teams patch what they think went wrong and ship without proof.
Replay fixes that:
โ Take a failure straight from your production traces (LangSmith by @LangChainAI, @arizeai, @braintrustdata, or your own format)
โ Rebuild the world it happened in: same records, same tool responses
โ Freeze everything before it and re-run only the turn that broke
โ Get a suggested fix, apply it in one click, and test it against the exact moment it failed
โ Save it as a regression scenario so it never comes back quietly
The goal isnโt a deterministic agent. Itโs a deterministic world, so the only thing that changes between runs is your fix.
Hold the world still, and the bug has nowhere to hide.
Connect your traces and replay your first failure: simulation.plurai.ai/connect
The story behind it is in the replies
Free in Claude Code, Codex and Copilot ๐
plurai.ai/blog/production-buโฆ
Share your feedback or questions in our Discord - discord.gg/KBwQFnNYJ
1
2
56
Connect your traces and replay your first failure: simulation.plurai.ai/connect
3
10
Plurai Simulation is the #1 Product of the Day on Product Hunt ๐
Thousands of builders showed up, not just to test their agents, but to break them on purpose, before their users do.
Because agents don't fail in the demo. They fail on the 10,000th conversation, in the case nobody thought to test.
That's why we built Plurai Simulation the Waymo way: simulate real-world scenarios at scale, find where your agent breaks, and fix it before production.
Until recently, this was available only to a handful of enterprise teams. Now every engineer can run it on their own agent, right from their coding agent.
Thank you to everyone who upvoted, tried it, shared it and pushed us with feedback. This is just the beginning!
Try it for free: simulation.plurai.ai/connect
What a launch!
Yesterday, we opened Plurai Simulation to every AI engineer. Within hours, thousands of builders were already simulating their own agents, uncovering edge cases, and fixing failures before they ever reached real customers.
The feedback has been incredible. Builders discovering and fixing in minutes what manual testing would have missed entirely.
And we wrapped up the day at the @nebiusai x @nvidia event, sharing how our partnership is pushing the boundaries of what AI agents can do.
A huge thank you to everyone who tried Plurai, pushed it to its limits, and shared feedback. And to our incredible team and partners for making this possible. โค๏ธ
Self-driving cars earned our trust one simulated mile at a time. Now it's time for AI agents.
Start simulating for free: simulation.plurai.ai/connect
Agent evals need to feel more real-world.
Pretty cool to see @pluraiAI ship Plurai Simulation today. You get a digital twin of your agent's world and can test it there instead of in front of users.
Live now and free to get started.
๐ค Paid partnership
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.
โ Digital twin: Your real agent, its tools, and environment recreated from your code
โ Simulated users & tasks: Realistic users, tasks, and workflows that push your agent into the edge cases that matter
โ Auto evals: Check what your agent actually did, not just what it said
โ Verified fixes: Every failure comes with the run that exposed it and a fix you can verify
โ 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: simulation.plurai.ai/connect
Plurai retweeted
ืืื ืืืื ื Plurai!
ืืืฆืืื ืจืฉืืืช ืขื ืืืืฆืจ ืืืืืืขืื ืขื ืืืืก ืฉื 13 ืืืืืื ืืืืจ ืืืืืืช Team8.
ืืื ืืืืืช ืืฆืืืช Advisory ืืืงืืช ืืืง ืืืืกืข ืฉืืื.
ืืืืฆืจ ืฉืืื ืืื ืืขืชืื ืืืจื ืฉืื ืืืจืืช ืืขืืื ืขื ืืืืื ืฉืคื.
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.
โ Digital twin: Your real agent, its tools, and environment recreated from your code
โ Simulated users & tasks: Realistic users, tasks, and workflows that push your agent into the edge cases that matter
โ Auto evals: Check what your agent actually did, not just what it said
โ Verified fixes: Every failure comes with the run that exposed it and a fix you can verify
โ 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: simulation.plurai.ai/connect
Plurai retweeted
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.
โ Digital twin: Your real agent, its tools, and environment recreated from your code
โ Simulated users & tasks: Realistic users, tasks, and workflows that push your agent into the edge cases that matter
โ Auto evals: Check what your agent actually did, not just what it said
โ Verified fixes: Every failure comes with the run that exposed it and a fix you can verify
โ 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: simulation.plurai.ai/connect
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: simulation.plurai.ai/connect
Plurai retweeted
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!
Small open models can match frontier models on complex policy checks: 9โ47x 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 -
plurai.ai/papers/scope-compiโฆ
Small open models can match frontier models on complex policy checks: 9โ47x 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 -
plurai.ai/papers/scope-compiโฆ
Small open models can match frontier models on complex policy checks: 9โ47x 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 -
plurai.ai/papers/scope-compiโฆ
Plurai retweeted
ืืื ืืืืื!
ืืืืจ'ื ืฉื Plurai ืืฉืืชืืฃ ืคืขืืื ืืืืื ืขื ื ืืืืก ืืื ืืืืื ืื ืืฆืืืื ืืืืจืื ืืช ืืขืืืช ืฉื ืืืืื AI ืคื 44 ืืืืืช ืืืืืืช ืฉืืื ืืื ืืช ืืืืื ืฉืคื ืงืื ืื ืืืฉืืืืช ืกืคืฆืืคืืืช.
ืื ืืขืชืื ืืขืืฉืื ืืื ืืืจ ืืืืื.
Excited to announce our collaboration with @nvidia and @nebiusai at NVIDIA #gtcberlin!
We post-trained NVIDIAโs Nemotron 3.5 Lightning into a specialized model that outperforms Claude Haiku 5.5 at 44ร lower cost and matches OpenAIโs GPT-6 Luna at 40ร 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: plurai.ai/blog/vibe-post-traโฆ
Plurai retweeted
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 44ร lower cost and matches @OpenAI 's GPT-6 Luna at 40ร 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: plurai.ai/blog/vibe-post-traโฆ
Excited to announce our collaboration with @nvidia and @nebiusai at NVIDIA #gtcberlin!
We post-trained NVIDIAโs Nemotron 3.5 Lightning into a specialized model that outperforms Claude Haiku 5.5 at 44ร lower cost and matches OpenAIโs GPT-6 Luna at 40ร 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: plurai.ai/blog/vibe-post-traโฆ









