44x cost savingsHigher quality
Cost per 1,000 calls
Plurai SLM44x
GPT-6 Luna1.1x
Claude Haiku-5.51x baseline
44x cost savingsHigher quality
44x cost savingsHigher quality
Cost per 1,000 calls
Plurai SLM44x
44x cheaper than Claude Haiku-5.5with +10 pts higher quality
40x cheaper than GPT-6 Lunaat matching quality
GPT-6 Luna1.1x
Claude Haiku-5.51x baseline
Cost savings vs. GPT-6 Luna and Claude Haiku-5.5 (cost per 1,000 calls)
Policy compliance
failures00
serving•ProtectedDetecting violationsApplying fixes
Your agent
Tools
Sub-agents
Skills44x cost savingsHigher quality
Cost per 1,000 calls
Plurai SLM44x
44x cheaper than Claude Haiku-5.5with +10 pts higher quality
40x cheaper than GPT-6 Lunaat matching quality
GPT-6 Luna1.1x
Claude Haiku-5.51x baseline
Cost savings vs. GPT-6 Luna and Claude Haiku-5.5 (cost per 1,000 calls)
post-training
Post-train your own intelligence
Turn any open-source model into a frontier-beating model and slash your inference costs.
Install post-training pluginup to 98% cost reduction
any open-source modelready in minutes
Real-time protection for unbreakable agents with our ultra fast guardrails
Control and manage high impact agentic failures effortlessly, with zero compromise on policy compliance, data security and brand integrity.
Say goodbye to costly, inconsistent LLM-as-a-judge evaluations
Powered by auto-trained SLMs with unmatched accuracy and disruptive costs.
Claude code
Eval-Assistant
Ready
results
Frontier-beating models, built for production
>44x
Lower cost vs Claude Haiku-5.5
>+10%
Higher accuracy vs Claude Haiku-5.5
<100ms
Lower latency, real-time inference
workflow
Get your endpoint ready
Easy through-chat communication
Set your goal using a built-in chat and natural language. You can also add data samples from your agent.
Iterations and reviews
Review the auto-generated test set, and iterate via AI chat if needed.
Complete in a few minutes
Your post-training endpoint is ready to use! Full SLM background optimization completes in minutes.
claude code plugin
Vibe train SLM in 
Build production-ready AI without leaving Claude.
> 10% accuracy improvement
98% inference cost saving and < 100ms latency
Get your endpoint ready in minutes
Start Zero shot or with CSV
Install plugin
use cases
Powering all semantic tasks
Explore our use case catalog to unlock the full potential of our SLMs.
Can’t find what you’re looking for? Let us know!
Agent response
Evaluate whether the agent response complies with policy, avoids sensitive data exposure, follows brand tone, and meets required attributes.
Input
<Agent response>
Output
Classification on agent response (for example: helpful, not helpful / PII Detected, PII not Detected) & reasoning
Conversation evaluation
Evaluate multi-turn conversations for compliance, consistency, sentiment, and successful task resolution.
Input
<conversation between agent and user>
Output
Conversation evaluation (for example: resolved, unresolved / compliant, violation / consistent, inconsistent / positive sentiment, frustrated sentiment) and reasoning.
Grounding
Evaluate whether the agent response is fully supported by the provided context and does not introduce unsupported claims or contradictions. A response is grounded if all factual statements are supported by the context.
Input
Context:
<retrieved context or source material>Agent response:
<agent response>
Output
Grounding classification (for example: grounded / partially grounded / not grounded)
Reference evaluation
Evaluate whether the agent response matches the expected reference answer in correctness and completeness. A response is correct if it aligns with the reference meaning and key facts. Partially correct if it captures some but not all required information or introduces minor inaccuracies. Incorrect if it contradicts or significantly deviates from the reference.
Input
Reference answer:
<golden answer>Agent response:
<agent response>
Output
Reference evaluation classification (for example: correct / partially correct / incorrect)
User response classification
Classify the user message according to its primary intent to enable correct routing or handling. Select the label that best represents the user’s goal or request.
Input
User message:
<user response>
Output
User intent classification
(for example: billing / technical_support / sales / account_management / general_query / other)
Sentiment Analysis
Determine the emotional tone expressed in the user message. Identify whether the sentiment is positive, neutral, or negative, and capture stronger signals such as frustration or satisfaction when present.
Input
User message:
<user response or multi turn conversation>
Output
Sentiment classification
(for example: positive / neutral / negative / frustrated / satisfied)
Semantic similarity
Evaluate the semantic similarity between two text samples based on meaning rather than exact wording. Determine whether the two inputs express the same intent, a related idea, or different meanings.
Input
Sample A:
<text A>Sample B:
<text B>
Output
Semantic similarity classification
(for example: same_meaning / related / different)
Policy compliance classification
Evaluate whether the agent response complies with safety, legal, and company policies. A response is a violation if it enables harmful, unsafe, illegal, or policy-restricted behavior, exposes sensitive data, or fails to appropriately refuse disallowed requests.
Input
Agent response:
<agent response>
Output
Policy compliance classification
(for example: compliant / violation)
Toxicity
Evaluate whether the message contains toxic, abusive, or harmful language. Toxic content includes insults, harassment, hate speech, threats, or condescending and demeaning tone. Non-toxic content may express frustration or criticism without abusive or harmful language.
Input
Message:
<agent or user text>
Output
Toxicity classification (for example: toxic / safe)
User intent detection
Identify the primary intent expressed in the user message. Determine what the user is trying to accomplish, such as asking a question, requesting an action, reporting an issue, or providing feedback.
Input
User message:
<user message>
Output
User intent classification
(for example: question / request_action / complaint / feedback / information_request / other)
Tool invocation validation
Evaluate whether the tool selected or invoked by the agent is appropriate for the user’s request and context. A correct tool invocation matches the user’s intent and is necessary to fulfill the task. An incorrect invocation uses the wrong tool, or a tool that does not address the request. An unnecessary invocation uses a tool when no tool was required.
Input
User request:
<user message>Invoked tool:
<tool name or action>
Output
Tool invocation classification
(for example: correct_tool / wrong_tool / unnecessary_tool)
Agent action validation
Evaluate whether the agent’s action correctly follows the user’s request and system constraints. A correct action fulfills the user’s intent and is appropriate for the context. An incorrect action does not match the request or performs the wrong operation. An unnecessary action performs a step or operation that was not required to fulfill the user’s request.
Input
User request:
<user message>Agent action:
<action taken by agent>
Output
Agent action classification
(for example: correct_action / incorrect_action / unnecessary_action)
collaboration
Built with NVIDIA and Nebius
Together with NVIDIA and Nebius, we post‑trained open models that beat frontier models on a real production workload.
Vibe post-training: Turn any open model into a frontier‑beating model at 44x lower cost
Read more
Start in Claude Code
Trust is a loop, not a launch
Production feeds the next post-training run, so every model you ship beats the last.