> ## Documentation Index > Fetch the complete documentation index at: https://arize-ax.mintlify.site/docs/llms.txt > Use this file to discover all available pages before exploring further. # Alyx Learn More > Reference for Alyx: the surfaces it runs on, its full capabilities, supported models and providers, settings, chat features, and how your data is handled. ## Where Alyx works | Surface | What Alyx does there | | - | - | | Arize AX home | Everything, across observe, evaluate, and improve | | [Traces page](/docs/ax/observe/tracing/view-and-manage-traces) | Multi-trace analysis, patterns, aggregations, custom metrics, custom views | | Trace detail | Trace troubleshooting, span analysis, annotations, evaluations | | Traces search bar | Turns plain language into filter syntax | | [Prompt Playground](/docs/ax/prompts/prompt-playground) | Optimize prompts, build evals, run experiments | | [Eval and task builder](/docs/ax/evaluate/create-evaluators) | Build evals, configure tasks | | [Datasets and Experiments](/docs/ax/develop/datasets-and-experiments) | Manage datasets, analyze experiments | | Sessions | Inspect interactions across traces, build session views | | [Labeling queues](/docs/ax/observe/take-action/labeling-queue) | Set up queues, build reviewer views | | Dashboards | Create, edit, or explain widgets with the open dashboard or widget attached as context | | [Signal](/docs/ax/observe/signal) | Investigate an issue with its context attached | ## What Alyx can do | Area | Example | | - | - | | Trace search and investigation | "Find traces where the search tool failed, then group the error messages." | | Aggregations and custom metrics | "Show the five models with the highest total cost this week." | | Evaluators and human-label alignment | "Build a code evaluator that checks whether the response is valid JSON." | | Evaluation tasks | "Configure this session evaluation and preview the data its variables will receive." | | Agent-as-a-judge (Enterprise, needs an Anthropic integration) | "Create an agent-as-a-judge evaluator for this project using my rubric." | | Datasets | "Add these failure spans to my regression-test dataset." | | Prompts and experiments | "Run these variants on 50 rows and compare them with the previous experiment." | | Annotations and labeling queues | "Create a labeling queue for reviewing failed responses from this project." | | [Custom views](/docs/ax/observe/create-custom-views) | "Build a session view showing the conversation and tool calls in order." | | [Signal insights](/docs/ax/observe/signal#investigate-issues-with-alyx), for one project or the whole space | "What issues has Signal found for this project? Help me investigate one." | | Dashboards | "Create a dashboard with latency per model and a label distribution for each live evaluator." | | Setup and docs | "Help me set up Arize tracing with my coding agent." | ## Models and your own providers Alyx runs on an Arize-managed model by default. To use your own, add the provider under **Settings** → **Account Settings** → **Integrations** and pick its model in Alyx's model selector. Supported: OpenAI, Anthropic, Gemini, Azure OpenAI, Vertex AI, AWS Bedrock, NVIDIA NIM, and OpenAI-compatible custom endpoints. Only models with enough tool-use capability appear. See [AI provider integrations](/docs/ax/security-and-settings/integrations-playground/overview). ## Settings Open **Settings** from the menu at the top right of the Alyx chat: * **Keyboard shortcut:** any modifier plus a key, saved per browser. * **Auto Accept:** skip confirmation for eval and task updates, annotations, datasets, prompt changes, and experiment runs. Labeling queues and custom views always ask. * **Profile:** see [add your own context](#add-your-own-context). * **Documentation:** allow the docs skill, which uses RunLLM. See [third-party integrations](#third-party-integrations). * **Tips:** show or hide tips above the chat input. ## Chat features * **Edit & resend** a message to rewrite the conversation from that point. Alyx confirms first if the message created a dataset, evaluation, or experiment. * **Queue** a message while Alyx is working. **Send Now** sends it right away. * **Progress** shows a plan that updates as each task finishes. * **History** on Alyx home reopens past conversations. ## Long-term memory Alyx remembers durable context between conversations, so you don't re-explain the background: how you work, your goals and progress, what it learned about your projects and assets, and your team's conventions and corrections. It keeps what stays useful, rather than a transcript or values it can look up again. ### Add your own context * **Tell it in chat.** For example, "Remember that `support-regression` is our release-gating dataset." What you state directly is stored as a high-confidence entry, and a correction replaces the stale one. Memory is written once the turn finishes, so it's in place for your next message. * **Fill in your profile** under **Settings** → **Profile**: your name, your role, and instructions Alyx keeps in mind, then **Save profile**. Instructions are screened for safety when saved. A profile holds up to 10,000 characters, and roughly the first 8,000 go into each conversation, so lead with what matters most. | | Your profile | Learned memory | | - | - | - | | Who writes it | You, in Alyx Settings | Alyx, from your conversations | | What it holds | Who you are, your role, standing instructions | Goals, project and asset learnings, conventions, corrections | | Where it applies | Every space you work in | The space where you learned it | | How you change it | Edit or clear it in Settings | Tell Alyx in the chat | ### Long-term memory FAQ Only you. Memory is stored per user, so a teammate in the same space builds their own memory and never reads yours. It is deleted along with your account or the space it belongs to. No. Learned memory is scoped to the space where the conversation happened, so work in one space does not leak context into another. Your profile is the exception: it is tied to your user and applies everywhere you chat with Alyx. No. Memory holds a short, curated set of notes rather than a log. An entry is kept only if it is still true next month, cannot be recovered with a fresh query, and shapes more than one request. Your conversation history is separate and available from Alyx home. Anything it can look up again: evaluator and task configurations, IDs, URLs, filter strings, and live values such as today's error count or current p99 latency. It does store results that mark progress toward a goal, like "prompt v4 reached 74% accuracy against a 90% target," because later results get compared against them. Tell Alyx in the chat. Say what is wrong or no longer relevant, such as "we are not tracking latency on that project anymore," and it replaces or deletes the entry on the next update. There is no manual memory editor today, so corrections go through the conversation. The profile wins, because it is the context you set yourself. If learned memory still carries something stale, say so in the chat as well so Alyx updates the entry instead of working around it. Yes. Memory and your profile are included in the conversation like any other context, so they go to the model provider selected for that chat. See [Data privacy](#data-privacy) for how Arize-managed and bring-your-own integrations handle that data. ## Experience awareness Alyx adapts its help to your familiarity with each part of Arize AX. Based on your experience level, Alyx can be an onboarding buddy that teaches as it works or an advanced, focused agent that concentrates on completing your tasks. The experience is catered to you and treated separately by product area, so Alyx can move quickly when you are working with tracing while providing more guidance when you try evaluations or dashboards for the first time. | When you are newer to an area | When you are experienced in an area | | - | - | | Explains unfamiliar concepts and connects your goal to the relevant AX workflow. | Skips introductory explanations and focuses on completing the request. | | Teaches while it works, describing important choices and where to find the result. | Uses AX terminology, field names, filters, and configuration details directly. | | Suggests one useful next step and can guide you through it. | Surfaces technical caveats, alternatives, and optimization opportunities without repeating basics. | Long-term memory and experience awareness work together: Alyx can remember your goals and preferences while adjusting how much guidance it provides in the part of AX you are using now. ## Data privacy Alyx sends requests to the model provider selected for your conversation. Arize-managed options include Azure OpenAI and Anthropic. With your own integration, that provider's configuration and data-handling terms apply. * **Azure OpenAI and Anthropic act as data processors** for the prompts Alyx sends and the outputs it generates, depending on which Arize-hosted model is used, and help Arize meet industry-standard security and compliance measures. Processing and retention depend on the service and its configuration, and each provider describes its training and data-use commitments in its own documentation: see [Azure OpenAI data, privacy, and security](https://learn.microsoft.com/en-us/legal/cognitive-services/openai/data-privacy?tabs=azure-portal) and [Anthropic's trust and privacy documentation](https://trust.anthropic.com/). * **Azure OpenAI** is fully controlled by Microsoft and hosted in Azure. It doesn't interact with any other OpenAI-operated services, such as ChatGPT or the OpenAI API. * **Claude** requests run on Anthropic infrastructure under Anthropic's enterprise API security and data commitments, separate from unrelated consumer products. ![Diagram of Alyx data flow: customer data processed through Arize-hosted Azure OpenAI or Anthropic without exposure to unrelated third-party consumer services](https://storage.googleapis.com/arize-phoenix-assets/assets/images/arize-copilot-1.avif) ### Third-party integrations Alyx's support skill sends the questions you ask it to RunLLM. Only that question is shared, with no model information or user data. You acknowledge a one-time disclaimer before first use, and can manage authorization in **Alyx Settings** → **Documentation**. Questions about data handling: [support@arize.com](mailto:support@arize.com).