Your brokers are solely pretty much as good because the data they will entry — and solely as secure because the permissions they implement.
We’re launching ACL Hydration (entry management record hydration) to safe data workflows within the DataRobot Agent Workforce Platform: a unified framework for ingesting unstructured enterprise content material, preserving source-system entry controls, and imposing these permissions at question time — so your brokers retrieve the proper data for the proper consumer, each time.
The issue: enterprise data with out enterprise safety
Each group constructing agentic AI runs into the identical wall. Your brokers want entry to data locked inside SharePoint, Google Drive, Confluence, Jira, Slack, and dozens of different programs. However connecting to these programs is barely half the problem. The tougher downside is making certain that when an agent retrieves a doc to reply a query, it respects the identical permissions that govern who can see that doc within the supply system.
At this time, most RAG implementations ignore this totally. Paperwork get chunked, embedded, and saved in a vector database with no document of who was — or wasn’t — speculated to entry them. This can lead to a system the place a junior analyst’s question surfaces board-level monetary paperwork, or the place a contractor’s agent retrieves HR information meant just for inner management. The problem isn’t simply how you can propagate permissions from the information sources through the inhabitants of the RAG system — these permissions must be constantly refreshed as individuals are added to or faraway from entry teams. That is important to maintain synchronized controls over who can entry varied varieties of supply content material.
This isn’t a theoretical threat. It’s the rationale safety groups block GenAI rollouts, compliance officers hesitate to log off, and promising agent pilots stall earlier than reaching manufacturing. Enterprise prospects have been express: with out access-control-aware retrieval, agentic AI can’t transfer past sandboxed experiments.
Present options don’t remedy this nicely. Some can implement permissions — however solely inside their very own ecosystems. Others assist connectors throughout platforms however lack native agent workflow integration. Vertical functions are restricted to inner search with out platform extensibility. None of those choices give enterprises what they really want: a cross-platform, ACL-aware data layer purpose-built for agentic AI.
What DataRobot offers
DataRobot’s safe data workflows present three foundational, interlinked capabilities within the Agent Workforce Platform for safe data and context administration.
1. Enterprise knowledge connectors for unstructured content material
Hook up with the programs the place your group’s data truly lives. At launch, we’re offering production-grade connectors for SharePoint, Google Drive, Confluence, Jira, OneDrive, and Field — with Slack, GitHub, Salesforce, ServiceNow, Dropbox, Microsoft Groups, Gmail, and Outlook following in subsequent releases.
Every connector helps full historic backfill for preliminary ingestion and scheduled incremental syncs to maintain your vector databases present. You management entry and handle connections by APIs or the DataRobot UI.
These aren’t light-weight integrations. They’re constructed to deal with production-scale workloads — 100GB+ of unstructured knowledge — with strong error dealing with, retries, and sync standing monitoring.
2. ACL Hydration and metadata preservation
That is the core differentiator. When DataRobot ingests paperwork from a supply system, it doesn’t simply extract content material — it captures and preserves the entry management metadata (ACLs) that outline who can see every doc. Consumer permissions, group memberships, function assignments — all of it’s propagated to the vector database lookup in order that retrieval is conscious of the permissioning on the information being retrieved.
Right here’s the way it works (additionally illustrated in Determine 1 under):
- Throughout ingestion, document-level ACL metadata — together with consumer, group, and function permissions — is extracted from the supply system and endured alongside the vectorized content material.
- ACLs are saved in a centralized cache, decoupled from the vector database itself. It is a important architectural choice: when permissions change within the supply system, we replace the ACL cache with out reindexing your entire VDB. Permission modifications propagate to all downstream shoppers routinely. This consists of permissioning for domestically uploaded information, which respect DataRobot RBAC.
- Close to real-time ACL refresh retains the system in sync with supply permissions. DataRobot constantly polls and refreshes ACLs inside minutes. When somebody’s entry is revoked in SharePoint or a Google Drive folder is restructured, these modifications are mirrored in DataRobot on a scheduled foundation — making certain your brokers by no means serve stale permissions.
- Exterior identification decision maps customers and teams out of your enterprise listing (by way of LDAP/SAML) to the ACL metadata, so permission checks resolve accurately no matter how identities are represented throughout totally different supply programs.
3. Dynamic permission enforcement at question time
Storing ACLs is critical however not ample. The true work occurs at retrieval time.
When an agent queries the vector database on behalf of a consumer, DataRobot’s authorization layer evaluates the saved ACL metadata in opposition to the requesting consumer’s identification, group memberships, and roles — in actual time. Solely embeddings the consumer is permitted to entry are returned. All the things else is filtered earlier than it ever reaches the LLM.
This implies two customers can ask the identical agent the identical query and obtain totally different solutions — not as a result of the agent is inconsistent, however as a result of it’s accurately scoping its data to what every consumer is permitted to see.
For paperwork ingested with out exterior ACLs (reminiscent of domestically uploaded information), DataRobot’s inner authorization system (AuthZ) handles entry management, making certain constant permission enforcement no matter how content material enters the platform.
The way it works: step-by-step
Step 1: Join your knowledge sources
Register your enterprise knowledge sources in DataRobot. Authenticate by way of OAuth, SAML, or service accounts relying on the supply system. Configure what to ingest — particular folders, file varieties, metadata filters. DataRobot handles the preliminary backfill of historic content material.
Step 2: Ingest content material with ACL metadata
As paperwork are ingested, DataRobot extracts content material for chunking and embedding whereas concurrently capturing document-level ACL metadata from the supply system. This metadata — together with consumer permissions, group memberships, and function assignments — is saved in a centralized ACL cache.
The content material flows by the usual RAG pipeline: OCR (if wanted), chunking, embedding, and storage in your vector database of alternative — whether or not DataRobot’s built-in FAISS-based answer or your individual Elastic, Pinecone, or Milvus occasion — with the ACLs following the information all through the workflow.
Step 3: Map exterior identities
DataRobot resolves consumer and group data. This mapping ensures that ACL permissions from supply programs — which can use totally different identification representations — could be precisely evaluated in opposition to the consumer making a question.
Group memberships, together with exterior teams like Google Teams, are resolved and cached to assist quick permission checks at retrieval time.
Step 4: Question with permission enforcement
When an agent or utility queries the vector database, DataRobot’s AuthZ layer intercepts the request and evaluates it in opposition to the ACL cache. The system checks the requesting consumer’s identification and group memberships in opposition to the saved permissions for every candidate embedding.
Solely licensed content material is returned to the LLM for response technology. Unauthorized embeddings are filtered silently — the agent responds as if the restricted content material doesn’t exist, stopping any data leakage.
Step 5: Monitor, audit, and govern
Each connector change, sync occasion, and ACL modification is logged for auditability. Directors can observe who related which knowledge sources, what knowledge was ingested, and what permissions had been utilized — offering full knowledge lineage and compliance traceability.
Permission modifications in supply programs are propagated by scheduled ACL refreshes, and all downstream shoppers — throughout all VDBs constructed from that supply — are routinely up to date.
Why this issues on your brokers
Safe data workflows change what’s attainable with agentic AI within the enterprise.
Brokers get the context they want with out compromising safety. By propagating ACLs, brokers have the context data they should get the job executed, whereas making certain the information accessed by brokers and finish customers honors the authentication and authorization privileges maintained within the enterprise. An agent doesn’t grow to be a backdoor to enterprise data — whereas nonetheless having all of the enterprise context wanted to do its job.
Safety groups can approve manufacturing deployments. With source-system permissions enforced end-to-end, the chance of unauthorized knowledge publicity by GenAI isn’t simply mitigated — it’s eradicated. Each retrieval respects the identical entry boundaries that govern the supply system.
Builders can transfer sooner. As an alternative of constructing customized permission logic for each knowledge supply, builders get ACL-aware retrieval out of the field. Join a supply, ingest the content material, and the permissions include it. This removes weeks of customized safety engineering from each agent challenge.
Finish customers can belief the system. When customers know that the agent solely surfaces data they’re licensed to see, adoption accelerates. Belief isn’t a function you bolt on — it’s the results of an structure that enforces permissions by design.
Get began
Safe data workflows can be found now within the DataRobot Agent Workforce Platform. When you’re constructing brokers that must cause over enterprise knowledge — and also you want these brokers to respect who can see what — that is the potential that makes it attainable. Strive DataRobot or request a demo.
