From cba81e85f5efd74e07745586b64e6e8effd9727a Mon Sep 17 00:00:00 2001 From: Eric Simmerman <325330+ets@users.noreply.github.com> Date: Sat, 13 Jun 2026 19:16:05 +0000 Subject: [PATCH] docs(agent-q): rename Agentic API to Agentic Endpoints Drop the "Agentic API" name, which implied a branded API separate from the Qualytics API. Use "Agentic Endpoints" as the section label and lowercase "agentic endpoints" in prose, framing them as Qualytics API endpoints that use an agent (and are therefore non-deterministic). Generated with [Linear](https://linear.app/qualytics/issue/QUA-1683/rename-agentic-api-in-userguide#agent-session-bb313531) Co-authored-by: linear-code[bot] <222613912+linear-code[bot]@users.noreply.github.com> --- docs/agent-q/deep-dive/agentic.md | 14 +++++++------- docs/agent-q/faq.md | 4 ++-- docs/agent-q/overview.md | 6 +++--- docs/glossary.md | 4 ++-- mkdocs.yml | 2 +- 5 files changed, 15 insertions(+), 15 deletions(-) diff --git a/docs/agent-q/deep-dive/agentic.md b/docs/agent-q/deep-dive/agentic.md index fcbc55585b..54f41a527a 100644 --- a/docs/agent-q/deep-dive/agentic.md +++ b/docs/agent-q/deep-dive/agentic.md @@ -1,21 +1,21 @@ -# Agentic API +# Agentic Endpoints -The Qualytics Agentic API brings the same conversational AI capabilities available through [MCP](./mcp.md){:target="_blank"} directly into your applications and workflows. Using your own LLM API key, you can integrate natural language data quality management into custom tools, scripts, automation pipelines, and internal platforms. +The Qualytics agentic endpoints bring the same conversational AI capabilities available through [MCP](./mcp.md){:target="_blank"} directly into your applications and workflows. Using your own LLM API key, you can integrate natural language data quality management into custom tools, scripts, automation pipelines, and internal platforms. ## Overview -While the MCP integration is designed for interactive AI assistants like Claude Desktop, the Agentic API enables you to: +While the MCP integration is designed for interactive AI assistants like Claude Desktop, the agentic endpoints enable you to: - Build custom applications that leverage natural language for data quality tasks - Integrate AI-powered data quality into existing automation workflows - Create internal tools and chatbots that interact with your data infrastructure - Use your preferred LLM provider and manage your own API costs -The Agentic API provides the same capabilities as MCP—datastore exploration, data transformations, quality check creation, and anomaly investigation—accessible through standard REST endpoints. +The agentic endpoints provide the same capabilities as MCP—datastore exploration, data transformations, quality check creation, and anomaly investigation—accessible through standard REST calls. ## Authentication -All Agentic API endpoints require authentication using your Qualytics Personal API Token (PAT) or a designated service account token. +All agentic endpoints require authentication using your Qualytics Personal API Token (PAT) or a designated service account token. Include the token in the `Authorization` header: @@ -27,11 +27,11 @@ For instructions on generating a token, see [Tokens](../../settings/access-token ## LLM Configuration -Before using the Agentic API, you must configure your LLM provider credentials. This allows Qualytics to use your API key when making calls to the language model. +Before using the agentic endpoints, you must configure your LLM provider credentials. This allows Qualytics to use your API key when making calls to the language model. ### Supported Providers -The Agentic API supports 22+ LLM providers. For the full list, see [Supported LLM Providers](../managing/add-integration.md#supported-llm-providers){:target="_blank"} in the Add Integration guide. +The agentic endpoints support 22+ LLM providers. For the full list, see [Supported LLM Providers](../managing/add-integration.md#supported-llm-providers){:target="_blank"} in the Add Integration guide. Common providers include: diff --git a/docs/agent-q/faq.md b/docs/agent-q/faq.md index db40eb2606..b2ebe49e6d 100644 --- a/docs/agent-q/faq.md +++ b/docs/agent-q/faq.md @@ -179,13 +179,13 @@ Any other MCP-compatible client that supports **Streamable HTTP** transport can External MCP clients share the same tool set as AgentQ — they connect to the same MCP server and have access to the same tools for exploration, quality checks, transformations, anomalies, operations, and integrations. However, features specific to the Qualytics UI (context injection, smart suggestions, session management, PDF export) are only available in the built-in AgentQ chat. -### What is the difference between AgentQ, the MCP server, and the Agentic API? +### What is the difference between AgentQ, the MCP server, and the agentic endpoints? | Component | Purpose | |-----------|---------| | **AgentQ** | The built-in chat UI inside Qualytics. Full session management, context injection, streaming, PDF export. | | **MCP Server** | An open-protocol endpoint. External clients (Claude Desktop, ChatGPT, Cursor) connect to it directly with your API token. | -| **Agentic API** | REST endpoints for integrating AgentQ capabilities into custom applications, scripts, and automation pipelines. | +| **Agentic endpoints** | REST endpoints that use an agent to service the request, for integrating conversational AI capabilities into custom applications, scripts, and automation pipelines. | All three use the same underlying MCP tools and capabilities — they differ only in how you access them. diff --git a/docs/agent-q/overview.md b/docs/agent-q/overview.md index 64ca99e89b..49067def0a 100644 --- a/docs/agent-q/overview.md +++ b/docs/agent-q/overview.md @@ -57,13 +57,13 @@ You can interact with AgentQ in several ways: through the **full-page chat** ope [:octicons-arrow-right-24: Limits](deep-dive/limits.md) -- :material-api:{ .lg .middle } **Agentic API** +- :material-api:{ .lg .middle } **Agentic Endpoints** --- - Building custom applications with the Agentic API — integration patterns, best practices, and code examples. + Building custom applications with the agentic endpoints — integration patterns, best practices, and code examples. - [:octicons-arrow-right-24: Agentic API](deep-dive/agentic.md) + [:octicons-arrow-right-24: Agentic Endpoints](deep-dive/agentic.md) diff --git a/docs/glossary.md b/docs/glossary.md index 6079b5798a..c6d63d92d7 100644 --- a/docs/glossary.md +++ b/docs/glossary.md @@ -258,9 +258,9 @@ An AI assistant or agent (like Claude Desktop, ChatGPT, Cursor, or AgentQ) that A discrete capability exposed by an MCP server that an AI assistant can call. Each tool has a name, description, input schema, and structured output. Examples include `list_datastores`, `create_quality_check`, and `anomaly_describe`. -### __Agentic API__ +### __Agentic Endpoints__ -REST API endpoints that bring AgentQ's conversational AI capabilities directly into custom applications and automation workflows. Provides the same capabilities as MCP through standard REST calls. Learn more in [Agentic API](agent-q/deep-dive/agentic.md). +Qualytics API endpoints that use an agent to service the request, bringing conversational AI capabilities directly into custom applications and automation workflows. Because they delegate to an agent, they are non-deterministic. They provide the same capabilities as MCP through standard REST calls. Learn more in [Agentic Endpoints](agent-q/deep-dive/agentic.md). ### __LLM (Large Language Model)__ diff --git a/mkdocs.yml b/mkdocs.yml index ebc4d6b69a..e54bcd4a70 100644 --- a/mkdocs.yml +++ b/mkdocs.yml @@ -483,7 +483,7 @@ nav: - Conversations, Responses & Context: agent-q/deep-dive/conversations.md - Best Practices: agent-q/deep-dive/best-practices.md - AgentQ Limits: agent-q/deep-dive/limits.md - - Agentic API: agent-q/deep-dive/agentic.md + - Agentic Endpoints: agent-q/deep-dive/agentic.md - Managing: - Connecting External AI Clients: agent-q/managing/connecting-external-ai-clients.md - Add Integration: agent-q/managing/add-integration.md