JDE Digital Workforce

What if your ERP could talk back? Not through a dashboard. Not through a report. Through a conversation — where you ask a question in plain English and an AI agent opens the real JDE application, navigates the business rules, and comes back with the answer. Or creates the transaction. Or runs the audit.

That's what the JDE Digital Workforce does. It's a multi-agent platform built by Fusion5 that gives AI agents native, real-time access to JD Edwards EnterpriseOne — not as a read-only query tool, but as a full participant in the ERP. Create sales orders. Enter vouchers. Complete work orders. Monitor server health. Run 22-section module audits. All through conversation.

---

Object Explorer — Full CRUD on Your ERP

Every expert agent knows its core business objects and can open, navigate, create, update, and delete records in real time. Not read-only. Full transactional capability through every JDE application.

You don't think about P-codes, QBE fields, or form navigation. You ask a question — or request a transaction — in plain English. The expert opens the real JDE application, finds what you need, creates or modifies records, and comes back with results.

Sales Order 4102 was created via AppStack on P4210. Address Book 81171 was created via AppStack on P01012. Work Order 47264 was created via P17714. Full Create, Read, Update, Delete on any JDE form.

Every action flows through JDE's own business rules. Required fields, validation, processing options, security — all enforced by the ERP, not the AI. The atomic FSREvent pattern sends header fields, grid rows, and OK in a single request — ensuring transactional integrity.

This works across all 25 module experts and any JDE application. Each agent discovers forms, fields, and actions at runtime. No hardcoded mappings. No version-specific code. If a form exists in your environment, the agent can navigate it.

---

Three MCP Servers. Total JDE Coverage.

The Digital Workforce connects to JD Edwards through three purpose-built Model Context Protocol servers — giving AI agents native access to every layer of the ERP.

Server	What It Does	Tools
JDE AIS Server	Query any table, execute BSFNs, run reports with custom data selections, interact with forms via AppStack, file attachments, processing options	50+
JDE Orchestrations	Discover, inspect, and execute orchestration workflows. Retrieve report PDFs, chain multi-step automations across modules	7
JDE Server Manager	Real-time infrastructure monitoring and control. Instance health, user counts, memory, kernel processes, start/stop with confirmation	30

---

Agentic Intelligence for JDE

Beyond simple queries — the Digital Workforce reasons, plans, and executes multi-step workflows autonomously.

Agentic Reverse Engineering

Point the system at any JDE environment and it autonomously maps your configuration: tables, security rules, processing options, UBE schedules, customisations, and data volumes. It discovers custom objects, maps security role structures, analyses PO configurations across versions, and generates comprehensive audit documentation.

Specification to Autonomous Agent

Hand the system a business requirement — a delivery docket spec, a month-end checklist, an onboarding workflow — and it creates an autonomous agent that executes it. The agent knows which JDE applications to open, which reports to run, which fields to populate, and which business rules apply. Upload a spec, get back a working digital worker. No developer maintenance required.

Autonomous Audit Execution

A state-machine orchestrator drives 22-section module audits from initialisation to final document assembly — executing live MCP queries, validating every section, and producing a Fusion5-branded Word report with 5,000+ words of findings. Every query logged to an immutable audit trail. A validation gate blocks document generation until all sections pass.

Knowledge Base (RAG)

114 Oracle JDE implementation guides vectorised with Voyage AI and indexed in Azure AI Search. 103,000+ searchable chunks spanning 16 modules — available per-chat with a single toggle. Experts can reference official Oracle documentation alongside live JDE data in the same conversation.

Query Intelligence

Every JDE query passes through a discipline layer that prevents common errors before they reach AIS. Mandatory column verification via jde_table_columns, zero-row validation with aggregation count proof, and a cookbook of 65 verified query patterns from live testing.

---

25 Expert Agents. Every JDE Module.

Each agent carries deep domain knowledge of its module — tables, business processes, audit patterns, common issues, and best-practice configurations.

Category	Modules
Financial	General Ledger, Accounts Payable, Accounts Receivable, Fixed Assets
Distribution	Sales Orders, Procurement, Inventory, Warehouse Management, Transportation
Manufacturing	Work Orders & BOMs, Quality Management, Capital Asset Management
Human Capital	Payroll & Time Entry, HCM & Benefits
Services & Projects	Service Management, Project/Job Cost, Real Estate, Environmental H&S, Grower Management
Technical	CNC Administration, Development, Address Book, System Constants, Diagnostics

---

Create Autonomous Digital Workers

Anyone can build a JDE expert tailored to their industry, plant, or business unit. Define what it knows, what it can access, and the quick actions it surfaces — then deploy it as an autonomous digital worker.

1. Define the Role — Give the agent a name, personality, and expertise. Describe its purpose in plain language. Add workflow steps with step markers for multi-stage business processes. No code required.
2. Governance Controls — Set the compliance temperature (Strict to Creative) and grant tools via the allowlist. The platform auto-detects required capabilities from your workflow instructions.
3. Deploy & Operate — The agent appears in the portal instantly. Users interact through natural language. The agent discovers JDE forms, fields, and actions at runtime.

Examples already in production: Livestock Procurement (tracking POs across plants), Plant & Equipment (monitoring work orders and PM schedules), Supplier Payments (vouchers, payment proposals, ageing), and Yield & Production (actual vs standard yields, WIP tracking).

---

Compliance Temperature + Tool Allowlist

Hard boundaries enforced in code. Soft boundaries that shape behaviour. Full control over what each agent can do and how it does it.

5-Level Compliance Slider: Set the compliance temperature from Strict (confirm every action, zero improvisation) to Creative (full autonomy, maximum initiative). The slider shapes the agent's system prompt — a soft boundary that governs behaviour. Default is Balanced.

Tool Allowlist: Granular checkboxes control which MCP tool categories each agent can access — Data Queries, AppStack, Reports, Orchestrations, BSFNs, Form Service, and Attachments. This is a hard boundary enforced in code. An agent without AppStack permission physically cannot open a JDE application, regardless of what the user asks.

Deviation Logging: When an agent operates outside its expected pattern — using a tool it rarely calls, querying a table outside its module — the action is logged with a [DEVIATION] marker in the audit trail. Hard boundary (tools) + soft boundary (temperature) = defence in depth.

---

Real-Time AI. Your Way.

Every agent streams responses as they're generated. You see each tool call fire, each query complete, and the answer stream back token by token — no loading spinners, no black box.

Users pick the model that suits the task. Quick stock check? Haiku answers in under a second. Deep month-end investigation? Sonnet reasons across multiple modules. Complex audit? Opus goes the distance.

Personal preferences let each user inject their context — plant, role, output style — so the agent already knows who it's talking to before the first message. After each response, three contextual follow-up action chips appear for one-tap continuation.

---

From Question to Answer in Seconds

1	Understand — Natural language request is parsed, context resolved, and the right expert agent is selected.
2	Plan — The agent determines which MCP tools, tables, and queries are needed — resolving aliases and DD items automatically.
3	Execute — MCP calls are made to the live JDE environment. Every query is logged. Results are validated.
4	Deliver — Results returned in plain language, or assembled into branded documents, audit reports, and executive summaries.

---

Why It Matters

90% Reduction in audit preparation time

24/7 Always-on environment monitoring

100% Query audit trail coverage

0 Manual console logins required

---

By the Numbers

• 3 MCP Servers (AIS, Orchestrations, Server Manager)
• 25 Expert Agents across every JDE module
• 90+ MCP Tools for direct ERP interaction
• 3 AI Models — Haiku (fast), Sonnet (balanced), Opus (deep)
• 114 Oracle JDE guides vectorised (103,000+ chunks)
• 65 Verified query patterns in the cookbook
• 22 Sections in the autonomous audit pipeline

---

Your Digital Workforce Is Ready

AI agents that talk to your ERP as objects — full CRUD, every module, live streaming. Built on Anthropic Claude and the Model Context Protocol.

Speak to Fusion5 about bringing this to your JD Edwards environment.

Fusion5 Business Solutions · Australia & New Zealand · © 2026

More videos on the digital platform

Our JDE Digital Workforce Platform is a real force, and continue to get better.  We own every line of source code.  We have created the MCP servers and we can connect your JDE!  Read more about the functions we are exposing, this is just the beginning

What you're seeing in the demo is a chat interface sitting on top of JD Edwards — built by Fusion5. Instead of navigating menus, running reports, or calling your JDE consultant every time you need a number, you just ask it a question in plain English. The system is broken into expert agents for each module — General Ledger, Accounts Payable, Sales Orders, Procurement, Inventory, Manufacturing, and more — so when you ask about an open purchase order or a supplier's outstanding balance, it knows exactly which JDE application to go to, which tables to query, and what those field names actually mean.

Under the hood it's using Claude to translate your question into real AIS calls — the same Application Interface Services that JDE exposes for programmatic access. When you ask "show me all open vouchers for this supplier," it's not scraping a screen or doing a keyword search. It's constructing a proper data service query against F0411 — the AP ledger — filtering on the right document type, payment status, and supplier address number, then returning those records in a format you can actually read. The same goes for more complex questions. Ask about sales order activity for a branch plant and it'll hit F4211, group by order type, join back to the item master in F4101 if it needs descriptions. It knows the difference between a DD item and a SQL column name, which matters a lot in JDE because the AIS layer only accepts one of them.

For transactional work it goes further than just reading data. The platform uses JDE's Form Service to create, update, and delete records — the same way the JDE web client does. So in the video when you see it entering a journal entry or updating a supplier record, that's a real write operation going through AIS, hitting the same business function validation that a user at their keyboard would hit. Mandatory fields, UDC validation, processing option security — all enforced. And because it authenticates as the logged-in user, your existing JDE security profile applies throughout. Row security, application security, column security — if you can't see it in JDE, the agent can't see it either.

For more complex multi-step workflows — navigating a work order through multiple forms, drilling down from a sales order header into its lines and then into shipment detail — it uses AppStack, which is JDE's stateful form navigation API. That's what lets it behave like someone actually sitting at a JDE session, opening forms, clicking Find, selecting rows, and moving through the form stack. The agent manages the session, knows which form it's on, and can describe what's on screen and what actions are available at each step.

What makes it more than a search tool is that it can aggregate and visualise on the fly. In the video you can see it pulling transaction history, grouping it by period or cost centre or document type, and rendering a bar chart directly in the chat. That's not a canned report — it constructed that aggregation query from scratch based on what you asked, using JDE's aggregation service with the correct column names and grouping logic. No BSVW, no BI tool, no waiting for IT to build a report. You asked, it built it, it showed you.

This part of the demo is showing something a bit different — instead of querying or navigating JDE interactively, it's using orchestrations to do bulk work. Orchestrations in JDE are pre-built workflows that expose a defined input and output contract. They sit on top of business functions and form service calls, and they're designed to be triggered programmatically. What the platform does is give you a conversational way to drive them — so instead of building an integration, writing an BSFN call, or manually entering records one by one, you just describe what you want to do. The spreadsheet mapping example in the video is a good one to focus on. A user drops in a file — maybe a list of new suppliers, a batch of purchase order lines, or a set of price updates — and the agent works out how to get that data into JDE. It reads the column headers, figures out what they map to in the relevant JDE tables, and then calls the appropriate orchestration for each row. That mapping isn't hardcoded. The agent understands that "Supplier Name" maps to Alpha Name in the address book, that "Order Qty" maps to UORG on the purchase order detail, that a date column needs to be in Julian format before it goes anywhere near F4311. It handles the translation so the user doesn't have to think about any of it. Because it's going through orchestrations rather than directly poking tables, it respects all the business rules that are baked into those workflows. Orchestrations run through the AIS layer which means they go through the same processing option security, the same UDC validation, the same approval logic that a normal JDE transaction would. You can't use this to bypass anything — if the orchestration requires a valid branch plant, a valid item number, an authorised user, it'll fail the same way a manual entry would fail. That's intentional. The platform isn't replacing JDE's rules, it's making them accessible through a better interface. For bulk deletions or updates the same principle applies. The agent doesn't run a SQL DELETE against the database — it calls the correct orchestration or form service action for each record, which means soft deletes go through the right logic, audit fields get stamped, and any downstream triggers fire the way they're supposed to. In JDE that matters, because a lot of tables have cascading relationships. Deleting a sales order header without closing its lines correctly will cause problems. The platform handles that by using the same mechanisms JDE itself uses, not by going around them. What this ultimately means for business users is that processes that used to require a developer — writing an interop transaction, building a custom orchestration, setting up a scheduled batch — can now be done conversationally. You describe the task, the agent works out the orchestration to call and the data to pass, and it executes. For IT teams it means less one-off scripting work. For end users it means they can automate their own repetitive tasks without raising a ticket.  

This section of the demo is showing the part of the platform that sits above the individual tools — the agent layer. Not just "ask a question and get an answer," but fully autonomous workers that can be given a task, break it down, and execute it across multiple JDE systems without being hand-held through each step.

The agents themselves are defined as structured markdown documents. Each one has deep knowledge of its module — the relevant tables, the key business objects, the orchestrations it can call, the form service actions it knows how to use, the UBEs it can submit. An AP agent knows the F0411 ledger, the voucher entry process, payment terms, supplier master fields in F0401. A manufacturing agent knows work orders in F4801, bill of material structure in F3002, routing in F3003, how to read job status and move quantities between operations. That knowledge isn't generic AI knowledge — it's embedded directly in the agent definition, tuned specifically for how JDE works and how this business uses it. When you deploy a new agent for a specific team or process, you're giving it a standard operating procedure it will actually follow, written in terms of the JDE objects it will be touching.

The custom agent builder in the web portal is what makes this scalable. Historically, building an agent like this would mean a developer sitting down to write the specification from scratch — mapping out the tables, the orchestrations, the edge cases, the validation rules. What the builder does is take existing material and reverse-engineer a functional specification from it. Feed it a process transcript, a design document, a screen recording transcript, even a set of meeting notes from a requirements session — and it produces a structured agent definition that a developer can review, refine, and deploy. The AI does the heavy lifting of extracting the intent, identifying the relevant JDE objects, and structuring the logic. What would have taken days of analysis takes minutes.

Each agent run is tracked. The platform logs what was executed, what data was touched, how long it took, and whether it succeeded — and you can assign a financial value to each successful execution. If an agent that handles inventory receipting replaces a task that used to take a warehouse user fifteen minutes per GRN, and it processes forty GRNs a day, that's a number. You can see it building over time in the portal. That's not just useful for reporting — it's what makes the conversation with the business about AI adoption concrete. Instead of talking about capability, you're talking about hours saved and cost per transaction.

The inventory receipting example in the video is a good illustration of how this works end to end. A user says in plain English that they've received a shipment — gives a PO number, a quantity, maybe a location. The agent takes that, finds the purchase order in F4311, checks what's outstanding, calls the receipt entry orchestration with the right parameters, and records the GRN against the order. It handles the branch plant, the item number, the receipt date, the unit of measure. If there's a discrepancy — if the quantity received doesn't match what's on the order — it flags it and asks rather than assuming. That's not a scripted workflow. That's an agent reading the context, making decisions, and calling the right JDE processes in the right sequence.

The broader point is that the gap between "we want to automate this process" and "we have an agent running in production" has shrunk significantly. You don't need a six-month integration project. You don't need custom middleware. You need a clear description of what the process does, the right JDE objects mapped out, and an agent definition that puts it all together. The platform handles the authentication, the API calls, the error handling, and the audit trail. The business just needs to describe what it wants done.

Our JDE digital workforce platform

fusion5

MCP Servers Capabilities Expert Agents CNC & Server Manager How It Works Contact

JDE Digital Workforce

An AI-powered multi-agent system that understands your JD Edwards EnterpriseOne environment end-to-end — querying data, running reports, managing servers, and delivering audits autonomously.

Explore the Platform ↓

3

MCP Servers

24

Expert Agents

80+

MCP Tools

22

Audit Sections

Built on Anthropic Claude · Model Context Protocol

Enterprise AI Foundation

Infrastructure

Three MCP Servers. Total JDE Coverage.

The Digital Workforce connects to JD Edwards through three purpose-built Model Context Protocol servers, giving AI agents native access to every layer of the ERP.

◆

JDE AIS Server

Full access to Application Interface Services — query any table, execute business functions, run reports with custom data selections, and interact with JDE forms programmatically via AppStack.

50+ ToolsData QueriesBSFNsAppStackReportsFile AttachmentsProcessing Options

◈

JDE Orchestrations Server

Discover, inspect, and execute orchestration workflows. Retrieve report outputs as PDFs, run end-to-end business processes, and chain multi-step automations across modules.

7 ToolsDiscoverExecuteFile I/OPDF RetrievalOpenAPI Catalog

◉

JDE Server Manager

Real-time infrastructure monitoring and control. Check instance health, user counts, memory, kernel processes — and start or stop servers with confirmation safeguards.

30 ToolsHealth ChecksUser ActivityMemoryStart/StopLogsCache Ops

AI Capabilities

Agentic Intelligence for JDE

Beyond simple queries — the Digital Workforce reasons, plans, and executes multi-step workflows autonomously.

Agentic Reverse Engineering

Point the system at any JDE environment and it autonomously maps your configuration: tables, security rules, processing options, UBE schedules, customisations, and data volumes.

• Discover custom objects and modifications
• Map security role structures and user provisioning
• Analyse processing option configurations across versions
• Identify unused or redundant customisations
• Generate comprehensive audit documentation

Agentic Creation from Design

Provide a design document or requirements specification and the agents translate it into executable JDE artefacts — orchestrations, data selections, processing option configurations, and validation logic.

• Parse functional design documents
• Generate orchestration workflows
• Configure report data selections and PO values
• Create AppStack interaction sequences
• Produce unit-test validation queries

Autonomous Audit Execution

A state-machine orchestrator drives 22-section audits from initialisation to final document assembly — executing live MCP queries and producing a branded Word report.

• 22-section audit framework with persistent state
• Every query logged to audit trail (SUCCESS/ERROR)
• Validation gate blocks until all sections pass
• Document assembler — never summarises — all content

Conversational ERP Access

Ask questions in plain English. The agents resolve aliases and return meaningful answers — no JDE jargon required.

• Natural language to AIS query translation
• Conversational UBE execution with overrides
• Interactive AppStack form navigation
• Real-time server health in plain language

Agent Network

24 Expert Agents. Every JDE Module.

Each agent carries deep domain knowledge of its module — tables, business processes, audit patterns, common issues, and best-practice configurations.

Financial

• General Ledger
• Accounts Payable
• Accounts Receivable
• Fixed Assets

Distribution

• Sales Orders
• Procurement
• Inventory Management
• Warehouse Management
• Transportation

Manufacturing

• Work Orders & BOMs
• Quality Management
• Capital Asset Management

Human Capital

• Payroll & Time Entry
• HCM & Benefits

Services & Projects

• Service Management
• Project / Job Cost
• Real Estate & Leasing
• Environmental H&S

Technical

• CNC Administration
• Development & Customisation
• Address Book
• System Constants

Spotlight

CNC Expert + Server Manager

Real-time infrastructure intelligence — monitor every instance, every user, every byte of memory, without ever opening Server Manager Console.

• ⇅

  Instance Lifecycle Control

  List, start, and stop servers — with mandatory user confirmation for destructive actions.

• ☷

  Live User Monitoring

  See who’s logged in right now, sessions, and login status across every running instance.

• ⚙

  Memory & Performance

  Heap analysis, GC triggers, call-object/BSFN performance stats, and instance uptime.

• ⚖

  Security & User Provisioning

  Audit users, role assignments, row/column security, sign-on policies, and access.

• ⌨

  Enterprise Server Insight

  Kernel process monitoring, server group topology, batch queue status, and config.

Server Manager MCP
by the Numbers

30

MCP Tools

5

Instance Types

6

Core Workflows

0

Manual Logins

"How many users are online?"
Instantly answered via sm_instance_metrics — no console, no clicks, no waiting.

How It Works

From Question to Answer in Seconds

Whether it's a quick data lookup or a full module audit, the same agentic pipeline applies.

1

Understand

Request parsed, context resolved, expert agent selected.

2

Plan

Chooses MCP tools, tables, queries — resolves aliases.

3

Execute

MCP calls made; results validated; queries logged.

4

Deliver

Plain language answers or assembled branded outputs.

Audit Engine

22-Section Audit Pipeline

A state-machine orchestrator that drives comprehensive module audits from initialisation to branded document delivery.

Step 1

Initialise

Create state file, identify expert agent, configure environment

Step 2

Execute

Worker agents run each section, writing to individual files

Step 3

Query & Log

All MCP queries through Query Executor with full audit trail

Step 4

Validate

Validation gate blocks until all 22 sections pass checks

Step 5

Assemble

Assembler concatenates — never summarises — all content

Step 6

Deliver

Fusion5-branded Word document with full findings

Impact

Why It Matters

The Digital Workforce transforms how consultants and administrators interact with JD Edwards.

⏱

90%

Reduction in audit preparation time

🔎

24/7

Always-on environment monitoring

✅

100%

Query audit trail coverage

⚡

0

Manual console logins required

Ready to Meet Your
Digital Workforce?

See how Fusion5's AI agents can transform your JDE operations — from daily queries to full module audits.

Introducing the JDE Digital workforce

 Phew, after many late nights and early mornings, we have our JD Edwards digital platform at version 1.0.

We developed complete MCP servers for JD Edwards orchestration and AIS and then needed to wrap them up with some more prescriptive functionality, so our container based AI powered digital workforce is here.

You can drill down to any JD Edwards expert from the front page, or just start talking...  Each expert has been trained on everything that the internet has to offer and the solution also has a RAG based knowledge system which you can add your custom documentation too - or just rely on the standard JDE doco that we have vectorised for you.

You can see that once you choose and expert there are some intuitive (and configurable) operations that are available immediately.  In my example I chose the AP expert - it's book smart and connected to my JD Edwards!

Critical Setup Tables and Configuration for Accounts Payable Module

Based on my analysis of the live JDE system, here are the essential setup requirements for the AP module:

1. CRITICAL AAI (Automatic Accounting Instructions) - F0012

PC - Trade Accounts Payable (MANDATORY)

• Purpose: Controls the liability account for all vouchers
• Standard Account: 4110 (Trade Accounts Payable)
• Critical Configuration: Must be set for each company
• Failure Impact: Voucher posting will fail without PC AAI

From the system data, I can see PC AAI is configured across multiple companies (00001, 00028, 00050, etc.) primarily using account 4110.

Other Critical AP AAIs:

AAI	Description	Purpose	Account Type
PCM	AP Clearing	Matching/clearing account	Asset
RT	Cash Account	Payment posting	Asset
4310	GRNI (Received Not Invoiced)	Purchase receipt liability	Liability

2. AP Constants Table - F04001 (If Available)

⚠️ CRITICAL SETUP FIELDS:

Field	Description	Setup Requirement
DCAN8	Company Address Number	Valid address book number
DCPST	Default Pay Status	Match approval workflow (blank/A/#)
DCDPF	Duplicate Checking	MUST BE 'Y' (Error or Warning)
DCEDI	Allow EDI Override	Security control
DCGLBA	Default Bank Account	Valid GL bank account
DCEDIT	Edit Supplier	MUST BE 'Y'
DCPTC	Default Payment Terms	Standard terms code
DCTXA	Default Tax Area	Correct tax jurisdiction
DC1099	1099 Processing	'Y' for US companies

3. Supplier Master Configuration - F0401

MANDATORY FIELDS FOR EACH VENDOR:

Category	Fields	Critical Settings
Payment Control	HDPY, HOLD	Payment holds ('Y'/'N')
Payment Method	PYIN	Check/EFT/Wire/ACH
Tax Reporting	TRAP, A61099	Tax ID + 1099 code
Default Terms	PTC	Payment terms code
Banking	GLBA	Bank account for payments

4. Payment Terms Master - F04575

REQUIRED TERMS SETUP:

Field	Description	Business Rule
PTPTC	Terms Code	Unique identifier
PTDSC	Discount %	Early payment discount
PTDDD	Discount Days	Days to earn discount
PTNDD	Net Due Days	Payment due days
PTDP	Date Pattern	Due date calculation method

5. UDC Codes (F0005) - CRITICAL CONFIGURATIONS

UDC 00/DT - Document Type

PV - Standard Voucher
PM - Manual Payment  
PW - Automatic Payment
PD - Debit Memo
PP - Prepayment

UDC 00/PS - Pay Status

(blank) - Pending Entry
# - Pending Manager Approval
% - Pending Reapproval  
A - Approved (ready to pay)
H - Hold
P - Paid
D - Draft
V - Void

UDC 00/PY - Payment Instrument

C - Check
D - Draft
E - EFT
W - Wire Transfer
A - ACH

UDC 00/1099 - 1099 Reporting Types

M - 1099-MISC
N - 1099-NEC
I - 1099-INT
D - 1099-DIV

6. Processing Options - CRITICAL SETTINGS

P0411 - Standard Voucher Entry

• Duplicate Invoice Checking: Error or Warning (not Bypass)
• Supplier Validation: Error level
• Auto Next Number: Enabled
• Default Pay Status: Match workflow

P04575 - Create Payment Groups

• Pay Status Selection: 'A' (Approved)
• Bank Account: Valid account
• Payment Format: Match bank requirements

7. MANDATORY TABLE RELATIONSHIPS

F0401 (Supplier Master) → F0101 (Address Book)
F0411 (AP Ledger) → F0401 (Supplier Master)  
F0411 (AP Ledger) → F04575 (Payment Terms)
F0012 (AAIs) → Chart of Accounts

8. VALIDATION CHECKLIST

✅ MUST VERIFY:

1. PC AAI exists for every company - Voucher posting fails without it
2. Supplier Master completeness - Payment method, terms, tax setup
3. Payment Terms accuracy - Discount rates and days
4. UDC code completeness - All status codes defined
5. Processing Options alignment - Match business rules
6. 1099 compliance - Tax IDs for reportable vendors

🚨 FAILURE POINTS:

• Missing PC AAI = Voucher posting failure
• Missing payment method = Payment processing failure
• Missing 1099 setup = Tax compliance failure
• Incorrect terms = Cash flow impact

This configuration framework ensures proper AP module operation, financial accuracy, and regulatory compliance.

So a simple prompt get's a comprehensive result!

You can discover and call orchestrations, call BSFN's run reports AND interpret the PDF results with AI!  And more and more and more.

You can see how simple questions get comprehensive answers...

The functionality is incredible and drives productivity.

The enxt view we have is the custom agent builder:

This allows our customers to create individual, purposeful and proactive agents to process JD Edwards transactions autonomously.  We have provided the tools for you to create your agentic workforce.  Choose the module, discover the data and orchstrations and then define the business rules!

You can then export your agent definitions to claude or copilot and get them working for you.

My favourite feature is creating the agents from a functional specification:

You can see I am able to drag a functional specification into this portal and it will reverse engineer all of the JDE tables, reports and orchestrations needed to support the agent definition!  Pretty cool.

Let me know what you think, we are carefully choosing the first round of customers and the demand is  high!  People can see the potential.  This has been amazing for AI literacy too, enabling people to chat with JDE and build out complex automations over time.