Use this file to discover all available pages before exploring further.
In the previous guide, you instrumented your chatbot and explored its traces. That works for a handful of test queries - but you can’t read every response yourself.Evaluations solve this. An evaluation is an automated check - either an LLM judging another LLM’s output, or a deterministic code check - that runs on your production data continuously. By the end of this guide, every response will be automatically scored and you’ll be able to filter to find the ones that need attention.
This is Part 2 of the Arize AX Get Started series. You should have completed the Tracing guide first, with traces flowing into your skyserve-chatbot project.
Use Arize Skills to have your coding agent run evaluations from your editor, Alyx for a conversational approach inside the Arize platform, the UI for a hands-on step-by-step experience, or Code to run them programmatically.
By Arize Skills
By Alyx
By UI
By Code
Use Arize Skills with your coding agent to create an evaluator, run it on traces as a task, and export spans to inspect failures. Install the skills plugin and follow Set up Arize with AI coding agents for authentication and CLI setup. Then, follow the flow below.
arize-evaluatorThe skill covers LLM-as-a-Judgeevaluators only. In your prompt, say which template you need (for example Hallucination) and which project the evaluator is for. For example, you might say:
Create a groundedness-check evaluator using the Hallucination template for skyserve-chatbot. The input column is question, the output column is response, and the context column is retrieved_documents.
Note that templates are a starting point - most teams customize the prompt criteria to match their specific rubric. Once the evaluator is created, you can ask your agent to revise it, such as:
Update the groundedness-check evaluator to only flag hallucinations when the claim contradicts a retrieved document, not when it’s just unsupported.
arize-traceAfter an eval task has written labels to spans, export failures for triage. See Viewing results for where scores appear in the UI.For example, you might say:
Export spans from skyserve-chatbot where groundedness-check failed this week
Open Alyx anywhere in the Arize platform and describe what you want in plain text. Alyx will guide you through each step - creating evaluators, setting up tasks, and analyzing results - conversationally.
Describe what you need in plain text for an LLM-as-a-Judgeevaluator (for example a Hallucination template), including eval name, judge model, and which span columns map to input, output, and context. For code-based evaluators, use Evaluators → New Evaluator → Code in the UI or see Code evaluations. For example, you might say:
Create a groundedness-check hallucination evaluator using GPT-4o as the judge. The input column is question, the output column is response, and the context column is retrieved_documents.
Note that templates are a starting point - most teams customize the prompt criteria to match their specific rubric. Once the evaluator is created, you can ask Alyx to revise it, such as:
Update the groundedness-check evaluator to only flag hallucinations when the claim contradicts a retrieved document, not when it’s just unsupported. The input column is question, the output column is response, and the context column is retrieved_documents.
Arize AX supports two kinds of evaluators. LLM-as-a-Judgeevaluators use an LLM to assess quality - great for subjective dimensions like helpfulness or groundedness that are hard to check with code. Code-basedevaluators are deterministic Python checks, ideal for objective conditions like empty responses or keyword presence. We’ll focus on LLM-as-a-Judge for this example. For code-based evaluators, see Create evaluators.
This example uses LLM-as-a-Judge only. In the left sidebar, click Evaluators, then New Evaluator. Select LLM-as-a-Judge and choose the Hallucination template — this checks whether the response contains claims not supported by the retrieved context.
Give it a name: groundedness-check
Select your LLM provider and model (e.g., OpenAI GPT-4o)
Review the template and customize the criteria to match your rubric — or leave it as-is to get started quickly
Wait a couple of minutes, then go back to your skyserve-chatbot project. You’ll see evaluation scores on each trace. Filter by score to find failures and click into any trace to see the evaluator’s label, score, and explanation.
Run this workflow from the Python SDK, TypeScript SDK, or ax CLI. Some features are in alpha or beta - please check individual reference pages for details.
Every response your chatbot generates is now automatically scored for quality. You’ve gone from “I think it’s working” to “I can measure exactly how well it’s working.” Instead of manually reviewing traces, you can filter to just the ones that failed — and you have an explanation of what went wrong.Your evaluations have probably revealed a pattern: some responses score poorly because the chatbot makes claims that aren’t in the policy documents. The system prompt says “be helpful,” but it doesn’t say “only use information from the provided documents.” That’s a prompt problem — and it’s exactly what we’ll fix next.Next up: We’ll walk through how to improve your agent using Arize’s Prompt Playground and Experiments features.
