JD Edwards World AI Assistant Sizing and Value Calculator
This calculator sizes an on-prem AI assistant for JD Edwards World and turns the numbers into a monthly value and a simple payback. Enter users, usage, document volume and GPU cost and read off peak load, GPU count and index size.
Your numbers
Users with a login to JD Edwards World who could use the assistant.
Share of named users who ask at least one question on a typical day. 10 to 30 percent is common after launch.
Includes retrieved context sent to the model. 2,000 to 6,000 is typical with retrieval.
For World, count spooled reports kept for reference, PDFs on the IFS and shared-drive documents you will index.
Be conservative. Count only time that would otherwise be spent searching or running a report.
Hardware amortised over 36 months plus power, hosting and support for one data-centre GPU.
Aggregate batched throughput for your model and GPU. Measure it; 500 to 3,000 is a wide range.
Your results
Planning model. Peak hour share (20 percent) and 20 seconds per answer are fixed assumptions. Hours saved is the most uncertain input: measure it in a pilot before relying on the value figures. Excludes implementation, licences, staff and storage costs.
Monthly value and GPU cost vs named users
Sweeps Named users from 50 to 5000, holding your other inputs fixed.
Optional: validate these numbers in a pilot
We can run a small pilot on your hardware to measure real questions per user, tokens per answer and minutes saved for JD Edwards World.
Optional. The tool and every export work without this. No spam.
How to use it
Start with named users and the share who will ask questions on a typical day. Then estimate questions per active user and tokens per question (a retrieval-based answer often uses 2,000 to 6,000 tokens including context). Enter the number of documents and average pages to be indexed, the minutes saved per question and a loaded hourly cost. Adjust the tokens per second per GPU to match a benchmark of your own model on your own hardware.
- Use pilot data for questions per user as soon as you have it
- Keep minutes saved conservative, 2 to 5 for most lookups
- For World, count spooled reports kept for reference, PDFs on the IFS and shared-drive documents you will index.
The formulas
Questions per day = users x daily active share x questions per user. Tokens per day = questions x tokens per question. Peak tokens per second = tokens per day x 0.2 / 3,600, assuming 20 percent of traffic in the busiest hour. GPUs = peak tokens per second / tokens per second per GPU, rounded up with a minimum of one. Index size = documents x pages x 1.2 chunks x 6 KB. Hours saved per month = questions per day x 22 x minutes saved / 60. Value = hours x loaded rate. Payback = 36 x monthly GPU cost / net monthly value.
Reading the result
A single GPU often covers a few hundred users because traffic is bursty and answers are short, so the GPU count is usually driven by availability and model size more than throughput. The sweep chart shows value rising linearly with users while GPU cost rises in steps, which is why value per GPU improves as you add users. If net value is negative, check whether minutes saved is realistic or whether the use cases are too narrow.
Common mistakes
People often assume every named user will ask questions daily; real adoption is lower. Others count the cheap tokens of a short question but forget the retrieved context that is sent with it. Do not forget implementation effort, staff time, licensing and storage, which this model excludes, and measure savings with a pilot rather than trusting a guess.
Frequently Asked Questions
Why only 20 percent of traffic in the busiest hour?
It is a common planning rule for office workloads, where use clusters in a few hours. If your usage is more concentrated, such as shift starts or month-end close, increase the factor by scaling questions per day or the tokens per second margin.
How do I get tokens per second per GPU?
Run your chosen model on your GPU under a serving stack such as vLLM with realistic concurrency, and record aggregate output plus input tokens per second. Published figures vary widely with model size, quantisation and batch size, so measure.
Does the model include licences and staff?
No. It covers GPU cost and time saved only. Add implementation, database licensing, storage, security review and support staff to get a full business case. Use the TCO and ROI calculators for a broader view.
What does a zero payback mean?
It means net monthly value is zero or negative with your inputs, so the hardware never pays back in this model. Raise realistic adoption or time saved, narrow the scope, or reconsider whether the use case justifies a dedicated GPU.
If you want these numbers validated against your JD Edwards World environment, Netray can run a short sizing review and a pilot on your own hardware.
Related Tools
JD Edwards World Private AI Layer Blueprint Generator
Fill in your JD Edwards World version, database, hosting and users to get a shareable architecture plan for a private, on-prem AI assistant.
On-Prem AIOn-Prem LLM Total Cost of Ownership Calculator
Model the full multi-year cost of running LLMs on your own hardware, including GPU capex, power, cooling, support contracts, and operations staffing.
On-Prem AIOn-Prem AI ROI Calculator
Turn hours saved per employee into annual net benefit, payback months, and 3-year ROI for an on-prem AI investment.
On-Prem AIGPU Sizing Calculator for LLM Inference
Work out how many GPUs you need to serve a given open-weight model to your user base, based on memory footprint and token throughput.
More Oracle tools
See all- Oracle EBS Discrete Job Statuses Reference
- Oracle EBS Inventory Transaction Types Reference
- Oracle EBS Item Attribute Template Worksheet
- Oracle EBS MRP Exception Messages Reference
- Oracle EBS BOM Interface Load Worksheet
- Oracle EBS Inventory Period Close Checklist
- Oracle EBS WIP Accounting Class Reference
- Oracle EBS Cycle Count Setup Worksheet
- Oracle EBS WIP Job Close Variance Worksheet
Keep exploring
Free tools
- JD Edwards EnterpriseOne AI Assistant Sizing and Value CalculatorEstimate peak load, GPUs, index size, hours saved and payback for an on-prem AI assistant on JD Edwards EnterpriseOne.
- JD Edwards World Private AI Layer Blueprint GeneratorFill in your JD Edwards World version, database, hosting and users to get a shareable architecture plan for a private, on-prem AI assistant.
- JD Edwards World to EnterpriseOne Data Conversion Mapping WorksheetEditable worksheet that tracks every World file you convert to EnterpriseOne: source, target, cleansing rule, record counts, owner and status.
ERP fixes and how-tos
- How to Add a Private AI Layer to JD Edwards World on IBM iAdd AI to JD Edwards World without moving data: DB2 for i access, journal-based replication, rebuilt row security, local GPUs and approved batch write-back.
- How to Add a Private AI Layer to JD Edwards EnterpriseOne On-PremAdd a private AI layer to JD Edwards EnterpriseOne: AIS data service, Orchestrator, Security Workbench mapping, a local model and human approval.
Runs with your ERP
- RF-SMART Manufacturing Data Collection for JD Edwards WorldShop floor barcode data collection for JD Edwards World with RF-SMART: what it reports, how it connects, setup steps, pitfalls and a private AI layer on top.
- Vertex Tax Connectors with JD Edwards EnterpriseOneHow Vertex calculates sales, use and VAT tax for JD Edwards EnterpriseOne and World, plus Oracle EBS and Cloud ERP: integration model, flows, setup, pitfalls.
- RF-SMART and JD Edwards EnterpriseOne: Barcode Scanning and Mobile WMSHow RF-SMART connects barcode scanning to JD Edwards EnterpriseOne and World: integration method, data flows, setup steps, pitfalls and where private AI helps.
AI on your ERP
- AI for JD Edwards World on IBM i, without a EnterpriseOne migrationAdd AI to JD Edwards World on IBM i without replatforming: read the physical files safely, ground an LLM on your data, and keep control on the box you already run.
- AI for JD Edwards Inventory Management and Shop Floor ManufacturingAI on JD Edwards EnterpriseOne inventory and manufacturing: item ledger, work orders, MRP messages and cost variances, answered in plain English on your own servers.
Integrations
- How to add AI agents to JD Edwards World on IBM iHow to add AI agents to JD Edwards World on IBM i: a read-first tool layer over DB2 for i, human approval before any write, and a fully on-prem model option.
- How to add an AI chatbot to JD Edwards WorldAdd an AI chatbot to JD Edwards World on IBM i: grounded in DB2 for i data, role-aware, web or Teams front end, and fully on-prem with open models.