🎉 What's new

Introducing Knowledge Folders and Knowledge Files to close the gap between your structured data context and the procedural knowledge that actually governs how your business works.

Before this, your SOPs, policies, and compliance docs lived scattered across SharePoint, Confluence, and Google Drive, invisible to agents at the point of use. 

Now you can upload the definitive versions directly into Atlan as governed, first-class catalog assets. 

A Knowledge Folder is a domain-scoped container (e.g., "Finance SOPs"). 

A Knowledge File is the individual document inside it. 

Context agents process each file automatically, extracting glossary terms, attaching business rules, and generating skill files with full lineage back to the source. 

That output flows into Context Repos via Context Engineering Studio, making your unstructured knowledge available to your MCP-connected agents, Atlan's native conversational search, and anything you deploy downstream.

Consider a customer support agent. It knows the order schema, the churn model, the interaction history. But it guesses when a VIP customer asks about a refund outside standard policy because none of the escalation path, the tier-specific SLA, the product defect window live in a database. They live in a PDF or shared doc.

Upload that PDF as a Knowledge File. Context agents extract the rules and make them available downstream. Now the answer is grounded and cites the source.

✨ Let's dig deeper

• Upload once, governed forever: Drag and drop your PDF or Markdown files into a Knowledge Folder. They become searchable catalog assets with lineage, metadata, and access control.
• Context agents extract automatically: After upload, context agents process knowledge files and synthesize glossary terms, business rules, and skills. Everything traces back to the source document.
• Flows into your Context Repos: Extracted knowledge becomes available via Context Engineering Studio. It feeds your Context Repos, conversational search, and any MCP-connected agent downstream.
• You decide what governs agent behavior: You choose which document is the definitive version. Nothing governs agents without your sign-off.

👏 Give it a shot

If your team has SOPs, policy docs, or compliance guidelines that your AI agents should know about, this is where to start.

Click + New > Knowledge Folder from the top right of Atlan. Create or select a folder, drag and drop your PDF or Markdown files, and upload. Open any file's profile page to preview content, review extracted terms, and trace lineage to downstream skill files and context repos.

Admin access is required to upload; all roles can preview and search

See more at Knowledge Folders | Context Engineering Studio

🎉 What's new

As a security admin managing Snowflake access, you'll want this integration because it eliminates shared credentials and centralizes authentication through your existing identity provider.

Previously, users had to manage separate Snowflake credentials or rely on service accounts. Now, Atlan connects to Snowflake using PingFederate OAuth, letting your team authenticate with their corporate identity while you maintain centralized control over access policies.

✨ Let's dig deeper

This integration uses OAuth 2.0 with PingFederate as your authorization server:

• Users authenticate once through PingFederate and access Snowflake resources without storing passwords in Atlan
• Scope-based permissions determine what each user can see and query, aligned with your existing access policies
• Token refresh happens automatically in the background, so sessions stay active without manual re-authentication
• All authentication events flow through PingFederate, giving you a single audit trail for compliance reporting
• You can revoke access instantly at the identity provider level without touching Snowflake directly

🚀 Give it a shot

Go to Governance > Connections > Snowflake and choose Snowflake OAuth and External Oauth as your authentication method. You'll need admin access in both Atlan and PingFederate to complete the setup, refer the setup guide for more information.

Verify the integration by following the below steps:

1. Open an Insights worksheet on the configured Snowflake connection.
2. Run any query. Atlan opens a Login with Snowflake (PingFederate) modal.
3. Click the login button. A new browser tab opens to your PingFederate authorization endpoint.
4. Sign in with your usual SSO credentials. The tab closes and the modal flips to Login successful.
5. Once login is successful, run your queries inside Atlan. Queries authenticate as the PingFederate-authenticated user, not as a shared service account.

📘 Refer to the to setup guide here.

🎉 What's new

If you use AWS, your AI/ML teams may be building together in AWS SageMaker Unified Studio. And your context layer lives in Atlan.

As of today, those two are the same thing.

The AWS SageMaker Unified Studio (SMUS) connector is now generally available - built jointly with the AWS team. Every published asset, data product, project, and glossary term from SMUS now flows into the Atlan Context Layer, and the context you govern in Atlan flows back into SMUS automatically. Business stewards and AI/ML teams work on the same governed context, without leaving the tools they already use.

This is what it looks like when a hyperscaler builds natively on the Context Layer for AI.

✨ Let's dig deeper

🔁 Context flows both directions - not just into Atlan Crawl SMUS domains, data products, projects, published & subscribed assets, glossaries, terms, and key column metadata into Atlan. Reverse-sync descriptions you enrich in Atlan back to SMUS projects, published assets, and columns — so the governed context your data stewards define surfaces automatically in the workspace where your AI/ML teams build.

🔗 See how data products are reused across teams Lineage from any published asset surfaces every project that subscribes to it. Cross-team dependencies that were previously invisible become discoverable in a single view, making impact analysis and reuse decisions far easier.

🧭 Fits the domain model you already operate Attach SMUS projects and assets to your existing Atlan Data Domains. No parallel taxonomy, no duplicate ownership, no forced rework of how your business is organized.

🛡️ Enterprise-ready out of the box IAM-based authentication, a supplied CloudFormation template, preflight checks, and on-demand or scheduled crawls — built for production from day one.

🚀 Give it a shot

Setup is self-serve and most teams are connected in a single session.

In Atlan, head to New Workflow → AWS SageMaker Unified Studio. 

Deploy the supplied CloudFormation template in your AWS account, paste the IAM role ARN into Atlan, run the preflight check, and trigger your first crawl!

For more information, see

• 📘 Connector documentation for setup, supported assets, and reverse-sync configuration
•  📝 Joint AWS + Atlan blog for architecture and design rationale

Why Atlan + AWS:
SageMaker Unified Studio gives your AI/ML teams the workspace. Atlan gives them the context that makes the work trustworthy.

The definitions that drift, the lineage that goes untracked, the governance that gets bypassed — that gap is where AI projects lose credibility before they reach production. With SMUS as a first-class citizen in the Atlan Context Layer, the governed context your stewards maintain is the same context your AI/ML teams build on. It doesn't drift, because it only lives in one place.

Atlan is not just another connector in your AWS stack. SMUS connects to Atlan because the Context Layer for AI is where enterprise context compounds — and compounded context is what makes AI work at scale.

Have setup questions or want to talk through scoping? Reach out to your Atlan CSM or Account Manager. For product-related questions, you can also reach out to Bindu Neeharika at bindu.reddy@atlan.com to help you get from CloudFormation template to your first crawl ⚡

We're excited to announce that the SAP BW/4HANA connector is now available in Private Preview. This release extends Atlan's SAP coverage into the modeling and reporting layer, making it possible to trace a single number on a BEx query all the way back to the SAP application table it originated from.

What's new

The SAP BW/4HANA connector brings the InfoObjects, providers, transformations, and queries that turn raw SAP transactional data into BW models into Atlan for the first time.

Combined with the existing SAP ECC, SAP S/4HANA, and SAP HANA connectors, customers can now extend lineage and discovery into the BW/4HANA modeling layer — tracing data from source SAP application tables, through Transformations, ADSOs, and CompositeProviders, into the BEx queries that consume them. Coverage of the full SAP analytics estate — including legacy BW landscapes, SAP Datasphere, and the SAC consumption layer — will land as those connectors ship over the coming weeks and months.

Supported capabilities

Discovery

Catalog the core building blocks of your BW/4HANA environment:

• InfoAreas — hierarchical organization of BW objects
• InfoObjects — Characteristics and Key Figures, including attributes, texts, and hierarchies
• Advanced DataStore Objects (ADSOs) — standard, staging, and direct-update types
• CompositeProviders — with union and join definitions across underlying providers
• Open ODS Views — virtual access layer to external sources
• BEx Queries and Query Elements — calculated key figures, restricted key figures, filters, variables, exceptions, and conditions
• Transformations and Data Transfer Processes (DTPs) — including rule types (direct mapping, formula, routine) and source/target object references
• DataSources — extraction sources from SAP and non-SAP systems
• Process Chains — orchestration metadata and step dependencies

Lineage

End-to-end traceability across the BW/4HANA stack:

• Source-to-target lineage through Transformations and DTPs
• Provider composition lineage showing how CompositeProviders union and join underlying ADSOs and Open ODS Views
• Query lineage connecting BEx Queries to the InfoProviders they consume and the InfoObjects they reference
• Field-level lineage through Transformation rules — including direct assignments, formula rules, and ABAP routine-based rules
• Cross-connector lineage linking BW/4HANA assets to upstream SAP ECC, SAP S/4HANA, and HANA sources already cataloged in Atlan

The practical outcome within BW/4HANA: a business analyst can trace a BEx query key figure back through every Transformation to its originating SAP table, and a data steward can see exactly which queries depend on a given ADSO before approving a change.

For the full list of supported objects, lineage paths, and configuration requirements, see the SAP BW/4HANA connector documentation.

What's coming next

BW/4HANA is the first milestone in a broader rollout that will bring the entire SAP analytics estate into Atlan. Three connectors are already in active development:

• SAP BW on HANA — the classic NetWeaver BW deployment on HANA, for the many customers who haven't yet migrated to BW/4HANA. Extends BEx query and InfoProvider lineage to the existing BW landscapes still running in production today.
• SAP Datasphere — discovery and lineage for SAP's next-generation data fabric, including Spaces, Local Tables, Views, Data Flows, and Analytic Models.
• SAP Analytics Cloud (SAC) — Story, Model, and Dataset metadata with upstream lineage to Datasphere, BW, and HANA Live Data Models.

Together with the existing SAP ECC, SAP S/4HANA, and SAP HANA connectors, these four upcoming releases will complete the picture: a navigable view of SAP data from raw application tables, through every modeling and warehousing layer — classic SAP BW, SAP BW/4HANA, and SAP Datasphere — into the SAC dashboards and stories where business users consume it. BW/4HANA opens the modeling layer today; BW on HANA extends it to classic deployments; SAP Datasphere covers the next-generation fabric; and SAC closes the loop by bringing the consumption layer into the lineage graph. End-to-end SAP analytics lineage is the destination, and BW/4HANA is the next step.

Getting access

The SAP BW/4HANA connector is available to a limited set of design partners during Private Preview. To request access or learn more, reach out to your Atlan account team.

View the SAP BW/4HANA connector documentation →

Your AI agents are only as smart as the context they can reach.

Over the last few months, Atlan MCP has matured into the production bridge between your governed context layer and every AI tool your team uses, and is already powering AI analysts, internal GPTs, and Cursor workflows with early adopters.

🎉 Your context, natively in more tools

Atlan MCP now ships native in Claude (Desktop, Web, Code), ChatGPT, Cursor, Windsurf, VS Code, n8n, Microsoft Copilot Studio, Glean, and Databricks. Connect once with OAuth or API key. No local install, no replicated setup.

Meanwhile, inside Atlan's UI, Conversational AI is now Generally Available!

✨Remote MCP, production-ready

Hosted per-tenant at https://mcp.atlan.com/mcp.

🔧 A deeper toolbox — 28+ tools and growing every day

- Read: semantic search, column-level lineage, SQL on connected sources, docs with citations
- Write: descriptions, owners, tags, certificates, custom metadata
- Create: glossaries, terms, domains, data products, DQ rules
- Govern: archive, restore, purge; schedule and update DQ rules

📝 Policy-aware by default

New partner integrations such as with Cyera (classification) and Immuta (enforcement) mean sensitivity and access rules can travel with every agent query.

Every agent reads from the same governed context layer. One shared brain. Context stays yours.

🚀 Give it a shot!

Explore the MCP docs

🎉 What’s new

Conversational AI in Atlan lets everyone explore their data estate in plain language instead of hunting through filters and asset pages. Ask questions like “What powers our revenue dashboard?”, “How do we define active customer?”, or “Who owns this table?” and get grounded answers with lineage, glossary, ownership, and quality signals surfaced for you — inside Atlan, your data tools, and collaboration apps.

✨ Let’s dig deeper

Find and understand assets in natural language  

Search across tables, columns, dashboards, schemas, and glossaries by describing what you’re looking for, not its exact name. Conversational AI returns the most relevant assets plus key context like descriptions, usage, and tags.

Trace lineage and assess impact without leaving chat  

Ask “What feeds this dashboard?” or “What breaks if I change this column?” to see upstream sources, downstream consumers, and critical dependencies before you make changes.

Summarize definitions, docs, and signals in one place  

Get quick explanations of metrics and business terms, along with summaries of table readmes, column definitions, and data quality or freshness signals so you can decide if a dataset is safe to use.

Find owners and subject-matter experts instantly  

Use ownership metadata to identify who’s responsible for a table, dashboard, or term, so you know exactly who to tap when you need deeper context or approvals.

Use it where you already work  

Start a conversation from the Atlan homepage or Copilot on any asset page, use the browser extension in tools like Snowflake and Databricks, or ask questions directly from Slack or Microsoft Teams once they’re connected.

Stay in conversation, with answers you can verify  

Refine results with follow-up questions; Conversational AI remembers context within the session. Every answer comes with citations that link back to source assets in Atlan so you can quickly inspect and trust what you see.

 👏 Give it a shot

Configure it in Labs: Conversational AI is being rolled out in phases. Once it has been rolled out to your tenant, users can start using it right away. If you’re an admin, you’ll also see the Conversational AI option in Admin settings → Labs → Atlan AI, where you can configure its behavior and add custom instructions.

Ask your first questions: Open Chat from the Atlan homepage to search across your catalog, or use Copilot on any asset page to ask context-aware questions scoped to that asset.

Use it where your team already works: After Slack or Microsoft Teams is integrated with Atlan, you can ask questions directly in those tools too.

Start with something simple like “Show me trusted tables for MAU”, “How do we calculate ARR?”, or “What’s upstream of the customer 360 view?” — and let Conversational AI handle the rest.

🎉 What’s new

The Atlan Lakehouse is the context store underneath your AI agents — the open, Iceberg-native layer where your enterprise's context lives, gets governed, and ships to any agent platform.

We're excited to announce that Atlan Lakehouse is now generally available – the foundation of the Context Layer for AI, enabled by default for all Atlan tenants. You can run SQL queries, create dashboards, and build AI applications directly on your Atlan context, using any Iceberg REST–compatible client, without managing separate pipelines or exports.

✨ Let’s dig deeper

• Make your context queryable by anyone — not just Atlan users. Connect Lakehouse to your existing BI tools – Tableau, Power BI, Looker – and build governance scorecards, domain coverage heatmaps, and enrichment dashboards that update automatically as your catalog changes. No manual data maintenance, no exports, no staleness: the people who need to see governance progress can see it in the tools they already use.
• Decommission your extraction pipelines – your context layer is already running. Teams that previously built custom pipelines on top of Atlan APIs – with multiple components, failure points, and API rate-limit concerns – have migrated to Lakehouse and decommissioned those pipelines entirely. Instead of engineering a context layer from scratch, you get a stable, always-current store you can query directly.
• Score your assets for AI-readiness, in a single query. Lakehouse combines asset-level context — enrichment coverage, data quality scores, certifications, lineage — with Atlan's own usage signals: which users are active, which assets are being queried, which features are driving adoption. Teams have used this to score assets for AI-readiness, track governance progress over time, and understand whether the context their teams are creating is actually being used — all in a single query layer, without stitching together separate exports.

👏 Give it a shot

• Connect to the Atlan Lakehouse from your preferred Iceberg REST–compatible client, explore the context that resides in the Lakehouse, and run a few starter queries (e.g., counting assets by connector, surfacing verified assets, or listing active users).
• Plug Lakehouse into your existing reporting or AI stack – connect your BI tool to build context dashboards, or wire it into your AI agents so they can reason over your catalog, governance, and usage data using SQL instead of custom integrations.

Lakehouse is the foundation. Over the coming weeks, work with your Atlan team and look for more updates here on how Context Engineering Studio, Conversational AI, and MCP connect to it – so you have a full picture of what the Context Layer for AI looks like end to end.

Check out the documentation for more:

• Atlan Lakehouse overview
• Enable agents to query the Atlan Lakehouse using the /atlan-lakehouse agent skill

🎉 What's new 

Put your most important metadata front and center!

With Featured Custom Metadata, you can now pin custom metadata properties to the top of any asset profile, so critical context like governance status, ownership, or compliance info is always visible at a glance.

✨ Let's dig deeper 

Until now, finding a specific custom metadata value meant scrolling through the full details section even if it was the one property you checked every single time. That changes today.

📌 Pin What Matters
Governance Admins and Admins can now toggle Show as Featured on any custom metadata property. Once enabled, that property appears in a dedicated "Featured Custom Metadata" section at the top of every linked asset's profile.

Go to any Custom Metadata group → select a property → enable Show as Featured (right next to the existing Show in Filters and Overview options).

✏️ Edit Inline
Click edit on any featured property and update it directly. The changes sync instantly across the full custom metadata panel and the featured section. No need to navigate elsewhere.

📄 Rich Text Support If your featured property is a rich text field, it renders in an expanded view with the option to open in full, perfect for detailed governance notes or documentation.

📚 Works Across Glossaries Too
Featured Custom Metadata isn't limited to data assets. It's available on glossary categories and glossary terms as well — so business context stays visible wherever your team is working.

🌍 Where does this work? Featured Custom Metadata is supported on:

✅ Tables, columns, and other data assets ✅ Glossary categories ✅ Glossary terms ⏳Coming soon on data products

Why it matters: The metadata that drives decisions lke governance approvals, ownership, compliance status should never be buried. This feature ensures your most important context is always one glance away.

👏 Give it a shot
Head to any custom metadata property, flip on the Show as Featured toggle, and see it appear on your asset profiles instantly.

No more digging through details panels. Your key metadata now lives where it belongs: right at the top ✨

Let us know how you're using featured metadata. We'd love to hear what you're pinning!

🎉 What’s new

The Atlan Lakehouse makes all of your Atlan context available through an open, Iceberg REST–compatible catalog so you can easily build AI applications and drive analytical reports on your data estate. Today, it stores detailed metadata about all assets across your data estate, as well as usage analytics data on how users interact with Atlan.

We're excited to announce a new gold namespace in the Atlan Lakehouse – a curated namespace in the Lakehouse catalog that consists of standardized, refined tables that make it easier than ever to build AI apps and reports on asset metadata.

✨ Let’s dig deeper

• The Lakehouse namespace that contains asset metadata today (entity_metadata) is effectively a bronze layer for Atlan metadata: comprehensive and highly detailed, but harder to work with when you just want to analyze asset metadata.
• The new catalog-native gold namespace gives you a small set of refined, analytics-ready tables with just the fields you need, making it much easier to build AI apps and reports on asset metadata.
• The entity_metadata namespace remains the raw, bronze source of truth for catalog metadata, while the gold namespace is the curated consumption tier you use for reporting, dashboards, and AI.
• The gold namespace follows a star schema design, with:
  • A core assets table (fact table) that lists every asset in the data estate along with common attributes like name, type, status, owners, and certification, and
  • Complementary domain-specific tables (dimension tables) that contain detailed columns for specific areas such as data quality, data products, and glossary analytics.

👏 Give it a shot

Make sure the Atlan Lakehouse is enabled in your workspace, and then connect to it from your preferred Iceberg REST–compatible client. You'll be able to see a new gold namespace alongside the existing namespaces in the catalog!

Check out the documentation for more:

• Atlan Lakehouse overview
• gold namespace reference
• Best practices for querying the gold namespace efficiently
• Enable agents to query the Atlan Lakehouse using the /atlan-lakehouse agent skill

Note: Ensure your users can view and select from the tables in the gold namespace by granting them the correct platform-native RBAC permissions.

🎉 What’s new

As a data steward, you'll want governance coverage for nested fields because it helps you enforce PII and compliance policies across all your data not just top-level columns.

Until now, Atlan only synced tags for top-level (Level 1) BigQuery columns. While nested columns were visible, their Policy/IAM tags were not  leaving governance incomplete.

With this update, Atlan now supports tag ingestion, propagation, and policy enforcement for nested BigQuery columns (Level > 1) with support for nested structures up to 15 levels deep.

✨ Let’s dig deeper

Here’s what this means in practice:

• Tags applied in BigQuery (Policy/IAM) are now ingested for nested fields

• Nested columns can now be used in:

  • Tag propagation workflows
  • Policy creation → Select assets
• Governance workflows now treat nested fields as first-class assets

• You can identify sensitive data in structures like:

  • user.address.zipcode
  • event.payload.device.id

This eliminates gaps where sensitive data was previously hidden in nested JSON and ensures governance rules apply consistently across all levels.

👏 Give it a shot

• Go to Governance → Policies
• Create or edit a policy
• In Select assets, include nested columns from BigQuery
• Use tag propagation to automatically extend governance to nested fields

Make sure:

• Your BigQuery connector is active
• You have appropriate governance permissions

📘Refer to the BigQuery set up guide for nested tags.