38 docs tagged with "ai"

Understand the key design decisions behind each context agent—why descriptions are verbose, what READMEs are optimized for, how SQL Intelligence works today, and where it's headed.

Establish robust AI governance frameworks that maintain compliance, mitigate risks, and drive trust through visibility, lifecycle management, and policy enforcement

Configure AI asset access in personas: control who can view, edit, or manage AI models, model versions, applications, and governance properties.

Integrate, catalog, and govern Amazon SageMaker AI assets in Atlan.

What metadata the Atlan MCP server can return for an asset, including refresh and freshness, usage, access, quality, and governance attributes, and where to find the full attribute list for each asset type.

Atlan AI is the intelligence layer of the Enterprise Context Layer. Context Agents enrich your data estate at scale; the Remote MCP server makes that context callable by every AI agent your organization runs.

Security and compliance information for Atlan AI, including AI architecture, data handling, encryption, model management, and compliance frameworks.

Atlan MCP is a hosted server that lets AI clients (Claude, Cursor, ChatGPT, Gemini, Copilot) and automation platforms (Python, n8n, LangChain) use Atlan as a context layer through the Model Context Protocol.

Reference for the error envelope returned by Atlan MCP tools—code, category, is_retryable, message, and guidance—plus what each category means and whether retrying can help.

Reference for every tool available in the Atlan MCP server—search, lineage, metadata, governance, glossary, data quality, knowledge, and more. Filter by category or access level.

Connect Confluence to Atlan through Atlassian's Rovo MCP server so agents can read spaces and pages as context.

Connect your own MCP server to Atlan so agents can read the knowledge it serves, for sources Atlan doesn't connect to natively.

Connect GitHub to Atlan so agents can read repository READMEs, docs, and markdown files as context.

Connect SharePoint to Atlan through OneLake shortcuts or Microsoft Graph so agents can read your document libraries as context.

Automate metadata enrichment at scale using AI-powered context agents that generate descriptions, READMEs, and SQL intelligence across your most important data assets.

Assemble and ship the business context every AI agent needs to produce accurate, trustworthy answers.

Step-by-step guide to creating a context agent from a template in Atlan, from picking the template through to your first preview run.

How to scope which assets to enrich, choose the right bulk mechanism, sequence enrichment so it grounds AI reliably, and answer the overwrite, quality, and security questions.

Step-by-step guide to triggering AI-powered metadata enrichment using context agents in Context Agents Studio.

Common questions about agent templates in Atlan, covering access, security, cost, run behaviour, and what's currently in the works.

Common questions about the Asset ↔ Term Linker agent template in Atlan, covering which terms it links, what it writes, review and undo, cost, and what's in the works.

Put a collection on a schedule so its AI-written descriptions and READMEs are filled in for new assets and regenerated when an asset changes.

Connect the wikis and repositories your teams already write in, so Atlan agents can read them and turn them into governed context.

Step-by-step guide to creating an Asset ↔ Term Linker agent in Atlan, running a sample, reviewing the proposed term links, and publishing them.

Answers to common questions about Context Agents Studio—covering enrichment behavior, collections, agent support, processing time, and Flexi Credit usage.

Query Lakehouse metadata using natural language in AI coding agents like Claude Code. Install the atlan-lakehouse skill, which detects your platform and generates appropriate SQL queries.

Learn how to run a context agent, read its output, change its settings, put it on a daily, weekly, or monthly schedule, and delete it.

Learn how agent templates connect Atlan to your knowledge sources over MCP and turn what's written there into governed context, one outcome per template.

Learn how the Asset ↔ Term Linker agent template decides which glossary terms belong on which tables, views, and columns, what it writes, and the guardrails that keep a human in the loop.

Understand the collections available in Context Agents Studio—curated groups of data assets automatically surfaced from usage signals to help you prioritize metadata enrichment.

Learn about the AI-powered context agents available in Context Agents Studio—specialized agents that generate descriptions, READMEs, and SQL intelligence.

Learn where Atlan stores the three kinds of asset description, which one appears in the UI, and what happens when you accept or edit an AI-generated description.

Atlan AI enriches your glossary with summaries, automated enrichment, and conversational search, so business context stays current for every user and agent.

Point an Atlan agent at the knowledge files already uploaded to your workspace, with no connector and no credentials to set up.

Learn what AI assets and metadata Atlan crawls from Amazon SageMaker.

Context Engineering Studio (CES) generates the semantic layer AI agents need to answer questions accurately. CES assembles a context repository for one use case from the governed context in your Atlan catalog and glossary, then renders it as a semantic view for Snowflake Cortex Analyst, metric views for Databricks Genie, MetricFlow models for dbt, and context Claude reads over MCP.

Learn how to write custom instructions that help Context Agents Studio generate accurate, business-relevant metadata descriptions for your organization.

Learn how to write run instructions that tell a context agent template exactly which terms to extract from your documentation.