Add AgentQ Integration
AgentQ uses the AI provider configured for your deployment. You can select the Qualytics-managed provider (Beta) without supplying a separate model or API key, or connect a supported external provider with your organization's credentials. This guide covers both options.
AgentQ Configuration Fields
The setup below opens the AgentQ Configuration dialog. Use this reference to understand what each field expects before going through the steps:
| # | Field | Description |
|---|---|---|
| 1 | Provider (required) | Select Qualytics (Beta) or a supported external provider. When it is available, Qualytics sits at the top of the list above a divider that separates it from the external providers, and it is already selected when you open a new configuration. |
| 2 | Model (external providers, when shown) | Choose an available model or type a custom model name when the provider supports it. The field is hidden for the Qualytics provider. |
| 3 | API Key (most external providers) | Enter the credential required by the selected provider. The field is hidden for the Qualytics provider and for provider authentication methods that do not use an API key. |
| 4 | Base URL (external providers, optional) | Provide a custom endpoint for a compatible provider, such as Ollama, OpenRouter, or LiteLLM. The field is hidden for the Qualytics provider. |
| 5 | Business Context (required) | Describe your organization's data quality focus, responsibilities, and domain. AgentQ uses this context to make its suggestions and answers more relevant to your organization. Up to 2000 characters. |
| 6 | Provider-specific fields (when shown) | Complete any additional fields required by the selected provider or authentication method. Azure OpenAI needs an Azure OpenAI Endpoint and an API Version, Google Vertex AI needs a GCP Project ID and a GCP Location, Snowflake Cortex needs a Snowflake Account Identifier, and Amazon Bedrock needs an AWS Region plus whatever its selected Authentication Method calls for. Save stays unavailable until the required fields are filled in. |
The form displays a data-processing notice for whichever provider you select, naming who processes the data AgentQ sends. For Qualytics the notice explains that the data is processed on Amazon Web Services (AWS), which acts as a data processor; for an external provider it names that provider and points to its own data use and privacy policies. Review the notice and your organization's data-handling requirements before saving the configuration.
Prerequisites
- A Qualytics account with Manager role or higher to configure the LLM integration.
- If you choose an external provider, the credentials and provider-specific configuration it requires.
Setup
The AgentQ Configuration dialog can be opened from two places. Both paths lead to the same form. Pick the one that matches where you are in the app.
Step 1: Click the Settings icon in the bottom-left sidebar.
Step 2: The Settings page opens on the Connections tab.
Step 3: Click the Integrations tab.
Step 1: Click AgentQ in the left sidebar to open the AgentQ page.
Step 2: The No LLM Integration Configured page appears.
Step 3: Click Configure LLM. You are redirected to Settings > Integrations.
Configure the LLM Provider
Once you are on the Integrations tab, continue from this step regardless of which path you took above.
Step 4: The Integrations page lists every integration available in Qualytics, grouped by category. The AgentQ section is at the top with the AI Provider entry.
Step 5: Click Connect next to AI Provider.
Step 6: The AgentQ Configuration dialog opens. Select a provider and complete the fields that appear. The Qualytics provider does not require a model, API key, or Base URL.
Step 7: Click Save to complete the configuration.
Info
Qualytics sends a minimal request to the selected provider to test the connection before storing the configuration. For an external provider, this test also validates the supplied credentials. If the test fails or the provider is unreachable, an error appears.
Step 8: A confirmation message appears and the AgentQ entry shows a Connected badge with the active provider. External providers also show the selected model; the Qualytics provider shows Managed.
Once saved, AgentQ is ready to use. See AgentQ Overview for next steps.
How It Works
The AI provider configuration is a single, deployment-wide setting, not a per-user choice. A Manager or Admin selects the provider and completes any required credentials once. AgentQ then becomes available to users with the Member role or higher. Only one provider configuration is active at a time.
AgentQ uses the Business Context with each user's conversation context to make responses and suggestions more relevant to your organization's domain. Do not include secrets or information that your configured AI provider should not process.
Supported LLM Providers
The table below covers which providers you can connect. For the models each one currently offers, open the Model dropdown in the dialog after selecting the provider: that list comes from the platform itself and stays current as providers release and retire models. Where a provider accepts any model, you can also type a model name that is not in the list.
| Provider | Models |
|---|---|
| Qualytics (Beta) | Managed by Qualytics; no model selection required |
| OpenAI | gpt-5.4, gpt-5.4-mini, gpt-5.4-nano |
| Anthropic | claude-opus-5, claude-sonnet-5, claude-haiku-4-5 |
| Google Gemini | gemini-3.6-flash, gemini-3.1-pro-preview, gemini-3.5-flash-lite |
| Google Vertex AI | gemini-3.6-flash, gemini-3.1-pro-preview (via Google Cloud Vertex AI) |
| Amazon Bedrock | Region-specific model IDs |
| Azure OpenAI | OpenAI models via Azure deployments |
| Groq | openai/gpt-oss-120b |
| Mistral | mistral-large-latest, mistral-small-latest |
| Cohere | command-r-plus, command-r |
| DeepSeek | deepseek-chat, deepseek-reasoner |
| xAI | grok-4.5 |
| Ollama | Any locally-hosted model (requires Base URL) |
| OpenRouter | Any model via OpenRouter |
| LiteLLM | Any model via LiteLLM proxy (requires Base URL) |
| Perplexity | sonar-pro, sonar |
| Heroku | Claude, GPT-OSS, Nova, and other models via Heroku Managed Inference |
| Fireworks | Any Fireworks-hosted model |
| GitHub Models | GitHub-hosted models |
| Hugging Face | Inference endpoint models |
| Together AI | Any Together AI model |
| Cerebras | gpt-oss-120b, qwen-3-235b-a22b-instruct-2507, zai-glm-4.7 |
| Moonshot AI | kimi-k3, kimi-latest, kimi-thinking-preview |
| Snowflake Cortex | claude-opus-4-8, claude-opus-4-7, claude-sonnet-4-6 (requires an account identifier) |
| Alibaba Cloud | qwen-max, qwen-plus, qwen-turbo |
| Nebius AI | Qwen/Qwen3-235B-A22B, meta-llama/Llama-4-Maverick-17B-128E-Instruct |
| OVHcloud AI | Any OVHcloud AI endpoint model (free-text Model field) |
| SambaNova | Llama-4-Maverick-17B-128E-Instruct, Qwen3-235B-A22B |
| Vercel AI | Any model via the Vercel AI gateway (free-text Model field) |
| Zai | GLM 5 generation models |
Note
The Qualytics provider does not require your organization to supply an LLM API key. For an external provider, your organization supplies the credentials and is responsible for that provider's usage and commercial terms.
When the Qualytics Provider Is Not Listed
The Qualytics provider appears only on deployments that carry a Qualytics-issued deployment identifier. Where that is missing, the provider is simply absent from the list: there is no greyed-out entry and nothing on the form explaining why. If you expect to see it and do not, contact Qualytics support, or configure an external provider instead. Selecting it through the API on such a deployment is refused with a message saying the same thing.
What Beta Means
The Beta badge marks this provider in every place it turns up: beside it in the provider list, beside the Provider field once it is selected, beside the connected entry on the Integrations page, and in the disconnect confirmation dialog. Beta here means capacity is still being expanded while feedback is gathered, so its behavior may change. Everything else about it works the way the other providers do: you connect it, change it, and disconnect it from the same place.
File Uploads in Chat
When the active provider supports file attachments, the chat input shows an Attach icon for sending PDFs, Word, Excel, CSV, TSV, JSON, XML, plain text, and Markdown files. The button is shown for Qualytics, Anthropic, Google Gemini, Google Vertex AI, Amazon Bedrock (Claude models), OpenAI, Azure OpenAI, and Heroku. Other providers can still receive document content via the Paste Large Content flow. See Attach a File for limits and supported formats.
The Qualytics provider reads a narrower set of formats
The Qualytics provider accepts PDF, Word .docx, Excel .xlsx, and text-based files (CSV, TSV, plain text, JSON, XML, Markdown). It cannot read the legacy .doc and .xls formats, PowerPoint, or images, so the file picker leaves those out while this provider is selected. Dragging one onto the chat instead of picking it is turned away right away, with a notice listing the formats that do work. Save the file as .docx or .xlsx, export it as CSV or PDF, or paste its content as text.
A PDF has to be text-searchable. A scanned or image-only PDF is still accepted, but no text can be read from it, so AgentQ answers that it found no readable content rather than returning an error. Very long documents are truncated.
Using Azure API Management (APIM) with Azure OpenAI
If you front your Azure OpenAI endpoint with Azure API Management (APIM), you can point the Azure OpenAI integration at the APIM gateway instead of the Azure OpenAI endpoint directly. APIM acts as an OpenAI-compatible proxy. Two configuration details have to line up.
1. Base URL
Enter the APIM Gateway URL host the same way you would a native Azure OpenAI endpoint. Use only the host, without a trailing /openai:
The Azure OpenAI client appends /openai/deployments/{deployment}/...?api-version=... on its own, so adding /openai yourself doubles the path and causes 404s. On the APIM side, the Azure OpenAI API should be imported with its URL suffix set to openai so the gateway path mirrors a native Azure OpenAI endpoint (an APIM admin setting, not entered in Qualytics).
2. API Key / header name
Use the APIM subscription key as the API Key. The Azure OpenAI client sends its credential in the api-key HTTP header, but APIM expects the subscription key in Ocp-Apim-Subscription-Key by default. In APIM, go to API → Settings → Subscription → Header name and change it from Ocp-Apim-Subscription-Key to api-key. After that change, the subscription key flows through in the header the client already uses, making it a clean drop-in.
Note
Confirm the deployment name and api-version match what's deployed behind APIM (the standard Azure OpenAI import passes these through). APIM handles authenticating to the real Azure OpenAI backend on its side, so the backend model credentials are never exposed to Qualytics.
For more detail, see the Azure API Management documentation on authenticating and authorizing to LLM APIs, importing an Azure OpenAI API, and subscriptions and custom header names.
What's Next?
Want to connect external AI clients like ChatGPT, Claude Desktop, Cursor, or VS Code directly to the Qualytics MCP server? See Connecting External AI Clients for step-by-step setup guides.