---
title: "Field-Level RAM Redaction for Workday AI Responses — Kiweely"
description: "Legitimate Workday domain access still pulls SSNs, bank routing numbers, and compensation into broad API payloads. Strip sensitive fields in RAM before LLMs…"
url: https://kiweely.com/blog/field-level-redaction-for-workday-ai-national-id-compensation
---

# Stripping National IDs, Bank Details, and Peer Pay in Memory Before AI Sees Them

Even with per-user Workday OAuth, broad roles like HR Partner or Payroll Administrator legitimately hold access to Social Security Numbers, bank elections, and compensation. Deterministic in-memory field stripping prevents sensitive fields from ever entering LLM context windows.

-   By Kiweely
-   November 15
-   6 min read

Enforcing per-employee Workday OAuth guarantees an employee cannot pull records Workday denies them, yet it leaves a critical second gap wide open: **privileged users accidentally pulling sensitive fields they *are* allowed to see into an external LLM context window**. Deterministic **in-memory field stripping** closes that gap by dropping high-risk Workday attributes—such as `nationalIdentifiers`, bank `paymentElectionsCurrent`, and peer compensation fields—in RAM before the payload ever reaches Claude, ChatGPT, or Gemini.

Think about what happens when an `HR Partner`, `Payroll Administrator`, or `Benefits Partner` asks an AI assistant a routine question like *“Summarize the active staffing roster for Supervisory Organization Warehouse 4.”* If the assistant calls a shared custom [RaaS report, SOAP `Get_Workers`, or broad WQL query](https://kiweely.com/guides/workday-raas-wql-rest), Workday faithfully checks that HR Partner’s security groups, sees legitimate `View` / `Get` permissions on `Person Data: ID Information` and `Worker Data: Compensation`, and returns every column in the payload. Without field-level redaction at the connector boundary, Social Security Numbers, IBANs, and base salaries land directly inside a chat transcript for a question that only needed names and job titles.

## Why Workday Domain Security Alone Cannot Solve Context Over-Collection

In Workday’s [domain security model](https://kiweely.com/guides/workday-domain-vs-business-process-security-policies), a user’s permission to a report field or REST subresource is binary per target constraint: if your security group has `View` / `Get` access on the securing domain, Workday returns the value whenever an API call or shared RaaS report requests it.

You cannot solve AI over-collection simply by stripping permissions inside Workday, for three operational reasons:

1.  **Breaking day-to-day Workday UI work:** Revoking `Person Data: ID Information` (Personal Data functional area) or `Worker Data: Payroll (Payment Elections)` (Core Payroll functional area) from your Payroll and HR administrators prevents them from fixing tax IDs (`Edit IDs`) or resolving direct-deposit errors inside the Workday browser UI.
2.  **Coarse-grained SOAP and RaaS payloads:** Legacy Workday Web Services (`Human_Resources` `Get_Workers` with `Include_Personal_Information` or `Include_Compensation`) and multi-purpose [shared custom RaaS reports](https://kiweely.com/guides/workday-custom-report-sharing-security-empty) bundle dozens of fields into a single response document. An assistant calling an existing RaaS endpoint receives every column that the caller’s security groups permit.
3.  **LLM exploration in ad-hoc WQL:** When an AI assistant dynamically composes WQL against `allWorkers` to answer an analytical question, it may select extra columns (`totalBasePay_Amount`, `disciplinaryActionsInProgress`) “just in case” unless the gateway blocks those fields both in the query AST and in the returned JSON buffer.

## High-Risk Workday Domains and Fields That Rarely Belong in Chat

Before connecting any AI assistant to a tenant—even [after auditing over-permissive security groups](https://kiweely.com/guides/workday-security-audit-before-enabling-ai-agents)—map the exact Workday domains and WQL/RaaS fields that should be blocked at the AI connector layer across all personas:

| Data Category | Workday Securing Domain (Functional Area) | Example `allWorkers` WQL / API Fields | Recommended AI Connector Rule |
| --- | --- | --- | --- |
|  **National & Tax IDs** | `Person Data: ID Information` (Personal Data) | `nationalIdentifiers`, `nationalIdentifiersDisplayedWithIDOnly` |  **Block globally** in RAM for all personas |
|  **Bank & Direct Deposit** | `Worker Data: Payroll (Payment Elections)` (Core Payroll) | `paymentElectionsCurrent`, `paymentElectionOptionLines` |  **Block globally** in RAM (keep boolean status only if needed) |
|  **Disciplinary & PIPs** | `Self-Service: Disciplinary Action` / Talent review domains | `disciplinaryActionsInProgress`, `cf_DisciplinaryActions_Completed` |  **Block globally** or restrict strictly outside general chat |
|  **Base & Bonus Pay** | `Worker Data: Compensation` / `Worker Data: Compensation by Organization` (Core Compensation) | `totalBasePay_Amount`, `totalBasePayAnnualized_Amount`, `bonusAndOne_TimePayments` |  **Allow self-only** or **block** unless explicitly enabled for comp workflows |
|  **Home Contact Details** | `Person Data: Home Contact Information` (Personal Data) | Home street address, personal phone, personal email |  **Allow self-only**; strip from multi-worker roster reads |

## How Deterministic In-Memory Field Stripping Works

Unlike prompt rules (*“Do not repeat Social Security Numbers to the user”*)—which still transmit the raw SSN to the AI provider’s servers—deterministic gateway redaction intercepts the response inside volatile RAM **before** the MCP tool result leaves the connector.

A defense-in-depth Workday AI gateway applies redaction at two stages of the same request:

### Stage 1: WQL and SOAP Request Projection Pruning

Before sending an ad-hoc WQL query to `POST /wql/v1/data` or a SOAP `Get_Workers` envelope to Workday, the gateway inspects the requested field list and response groups. If an admin rule blocks `nationalIdentifiers` or `paymentElectionsCurrent`, the gateway rejects or strips those selectors from the outbound Workday query so Workday doesn’t even serialize them.

### Stage 2: Schema-Aware JSON/XML Stream Stripping in RAM

Custom RaaS reports (`?format=json`) and fixed REST endpoints return preset schemas where the caller cannot pick individual columns on the URL. As the upstream HTTP stream arrives in memory, the gateway walks every object node and drops blocked keys and nested structures deterministically:

**Raw Upstream Workday Payload (In Gateway RAM Only — Never Sent to LLM):**

Fails

```
{
  "Report_Entry": [
    {
      "Employee_ID": "21097",
      "Worker": "Gail Bradley",
      "Business_Title": "Warehouse Supervisor",
      "Supervisory_Organization": "Warehouse 4",
      "National_ID": "999-01-4421",
      "Bank_Account_Number": "0048291044",
      "Total_Base_Pay_Amount": "94500.00"
    }
  ]
}
```

**Filtered Tool Output Returned to Claude, ChatGPT, or Gemini:**

Works

```
{
  "Report_Entry": [
    {
      "Employee_ID": "21097",
      "Worker": "Gail Bradley",
      "Business_Title": "Warehouse Supervisor",
      "Supervisory_Organization": "Warehouse 4"
    }
  ]
}
```

Notice why **removing the key cleanly** (or replacing it with a compact policy notice `"_redacted_fields": ["National_ID", "Bank_Account_Number", "Total_Base_Pay_Amount"]` at the envelope level) outperforms regex masking:

-   A numeric salary like `"94500.00"` or a 10-digit bank account number looks identical to a cost center code or requisition number to a regex; key-path and Workday schema matching never misfires.
-   Dropping blocked keys across 500 RaaS rows shrinks token consumption in the LLM context window while guaranteeing zero sensitive digits leave RAM.
-   If the LLM asks why pay wasn’t returned, the `_redacted_fields` metadata tells it clearly *“Blocked by tenant admin field policy”* so it stops retrying alternative queries.

## Testing Your Field Redaction Rules Before Production Rollout

Run these three verification checks in your Workday Sandbox before publishing an AI connector to HR or finance staff:

1.  **Test as your highest-privilege persona, not your lowest:** Sign in to Sandbox as an `HR Partner` or `Payroll Administrator` who holds unconstrained `View` access on `Person Data: ID Information` and `Worker Data: Compensation`.
2.  **Trigger both structured and custom report paths:** Ask the assistant to fetch a worker profile via REST, run a WQL query against `allWorkers`, and execute a shared custom RaaS roster report containing compensation and ID columns.
3.  **Inspect the raw MCP tool-result JSON in the client inspector:** Verify that the raw JSON payload delivered to the AI client omits every blocked field—proving redaction happened in gateway memory rather than inside the LLM’s final prose response.

## How Kiweely Bridge Automates Field-Level Redaction

[Kiweely Bridge](https://kiweely.com/bridge) (coming next) pairs user-delegated Workday OAuth with deterministic in-memory field rules configured alongside an **AI admin agent** ([see Bridge security details](https://kiweely.com/bridge/security)):

-   **Guided field lockdown in Sandbox:** During setup, Bridge’s AI admin agent inspects your tenant’s API client scopes and RaaS schemas, sets field-level redaction rules for National IDs, bank details, and sensitive HR fields, and tests prompts across real personas (`Employee`, `Manager`, `HR Partner`) before anyone in Production connects.
-   **Stripped in RAM, zero stored payloads:** Bridge strips admin-blocked fields in memory and writes zero Workday records, prompts, or answers to disk, databases, or logs.
-   **Simple company pricing:** Flat monthly plans by licensed Workday employee count ($499/mo up to 1,000 employees, $1,499/mo for 1,001–5,000, $3,999/mo for 5,001–20,000, Enterprise by quote above 20,000 or for dedicated/self-hosted VPC containers, and free for one person on a personal Workday developer tenant).

## Frequently asked questions

### If user-delegated OAuth already enforces Workday security, why do we still need field-level redaction for AI?

Workday security governs what a human role is allowed to see inside Workday—not what should flow into an external LLM context window. An HR Partner or Payroll Partner legitimately needs Person Data: ID Information in Workday for I-9 or tax fixes, yet never needs raw SSNs or bank account numbers sent to Claude, ChatGPT, or Gemini.

### Why can't we just remove Person Data: ID Information from HR Partners in Workday?

Editing a core Workday domain security policy affects the Workday web UI, delivered reports, and business processes simultaneously. Removing that domain breaks the HR Partner's day-to-day Workday job. Gateway-level field rules narrow AI exposure without breaking native Workday tasks.

### Why is regex PII masking unreliable for Workday compensation and HR data?

Regexes catch formatted US Social Security Numbers, not unformatted foreign national IDs, IBAN/routing numbers, annualized salary integers like 162000, bonus percentages, or disciplinary status codes. Schema-aware field stripping drops exact WQL aliases, SOAP XML nodes, and RaaS JSON keys deterministically.

### Does stripping fields in RAM store anything on the gateway server?

No. Streamed JSON/XML payloads are parsed in volatile memory, blocked keys are removed or replaced with a redaction marker, and the filtered structure is returned directly over TLS with zero disk or log writes.

## Read next

[All posts](https://kiweely.com/blog)

-   [November 15 ### Clearing EU GDPR and Works Council Reviews with Pass-Through Workday Architecture](https://kiweely.com/blog/eu-gdpr-works-council-review-pass-through-workday-ai)
-   [November 15 ### Employee Chatbots vs. Custom Workday Screens: When a Chat Thread Isn’t Enough](https://kiweely.com/blog/employee-chatbots-vs-custom-workday-screens-moveworks-leena)
-   [November 15 ### Every Way to Connect Claude to Workday for Your Whole Company, Compared](https://kiweely.com/blog/claude-enterprise-workday-connector-options-compared)

### More guides on More Workday guides

[All 46 guides](https://kiweely.com/guides#more)

-   [Resolving SSO Redirect Loops on the Workday OAuth Authorize Endpoint](https://kiweely.com/guides/workday-sso-saml-oidc-loop-external-oauth-authorize-endpoint)
-   [Managing Workday OAuth Refresh Token Expiration, Rotation, and Revocation](https://kiweely.com/guides/workday-oauth-refresh-token-expiration-rotation-revocation)
-   [Fixing Workday OAuth invalid\_client, unauthorized\_client, and Redirect URI Errors](https://kiweely.com/guides/workday-oauth-invalid-client-unauthorized-client-redirect-uri)
-   [Handling Hourly vs. Salaried Workday Absence Plans: Hours, Days, and Partial-Day Requests](https://kiweely.com/guides/workday-hourly-vs-salaried-absence-balances-hours-vs-days)
-   [How to Configure User-Delegated OAuth 2.0 Authorization Code Grant in Workday](https://kiweely.com/guides/workday-authorization-code-grant-user-delegated-oauth-setup)
-   [Why Workday Absence Balances or Time Calculations Don’t Update After a Retro Job Change](https://kiweely.com/guides/workday-time-tracking-absence-retro-recalculation-errors)
-   [Troubleshooting Workday Compensation Cycle Eligibility, Proration, and Bonus Rounding Mismatches](https://kiweely.com/guides/workday-advanced-compensation-eligibility-bonus-rounding-errors)
-   [How to Fix Workday ACA 1095-C Code 2C Mismatches and Update Annual Affordability Thresholds](https://kiweely.com/guides/workday-aca-1095c-errors-affordability-setup)

## Your Workday work, done by AI.

Kiweely Vine is the AI agent that builds, deploys and tests Extend apps as real people, makes changes in any Workday task screen, answers from your real tenant and builds reports.

[Start for free](https://kiweely.com/download) [See how it works](https://kiweely.com/vine/how-it-works)

## Get the next one in your inbox.

One email a month for Workday teams: what’s changing in Workday and what to retest, one tip tried in a real tenant, and what’s new at Kiweely.
