Epicor Kinetic AI Assistant Sizing and Value Calculator
This calculator sizes a private AI assistant on Epicor Kinetic: how many GPUs peak load needs, how large the vector index gets, and what the time saved is worth against GPU cost. Every assumption is an input you can replace.
Your numbers
Users licensed to use the assistant.
Share of named users who ask at least one question on a given day.
Pilot logs give the real figure; 5 to 15 is common once habit forms.
Question, retrieved BAQ rows and document chunks, plus the answer. 3,000 to 6,000 is typical for grounded answers.
Travelers, drawings, inspection reports, certs and SOPs you want searchable.
Average across the document set.
Time a person would otherwise spend finding the answer across screens or asking a colleague.
Salary plus benefits and overhead for the people asking.
Hardware amortised over 36 months plus power, cooling, support and rack space.
Aggregate tokens per second under batching for your model and quantisation. Measure it; this is the most sensitive assumption.
Integration, document pipeline, security review and pilot.
Your results
Planning estimate only. Tokens per second, time saved per question and peak share vary widely; replace the defaults with measurements from your own pilot before committing to hardware.
Monthly value vs named users
Sweeps Named users from 20 to 1000, holding your other inputs fixed.
Epicor Kinetic sizing review
Optional: send your numbers and get an engineer's second opinion on GPU count, index size and the value assumptions.
Optional. The tool and every export work without this. No spam.
How to use it
Start with named users and the share who ask a question on a typical day. Set questions per active user from a pilot if you have one. Tokens per question include retrieved BAQ rows and document chunks, so grounded answers cost more than chat. Enter your measured tokens per second per GPU if you have it; otherwise keep the default and treat the GPU count as an estimate.
- Use a pilot log for questions per user
- Count retrieved context in the token figure
- Use amortised monthly GPU cost, not purchase price
- Run the sweep to see where a second GPU becomes necessary
The formulas
Questions per day = users x active share x questions per user. Peak-hour tokens per second = daily questions x 0.25 / 3600 x tokens per question. GPUs = peak tokens per second / throughput per GPU, rounded up. Index size = documents x pages x 2 chunks x 1024 dimensions x 4 bytes x 1.5 overhead. Hours saved = daily questions x minutes saved / 60 x 21 days. Payback = one-time cost / (monthly value minus GPU cost).
Reading the result
GPU count is driven by the busiest hour, not by headcount, so two sites with the same users can need different hardware. Monthly value is an upper bound until a pilot confirms the time saved. If value barely exceeds GPU cost, payback shows zero and the case rests on better decisions rather than time savings. Add a spare GPU if the assistant must stay up during a failure.
Common mistakes
The common errors are using the vendor's peak throughput figure instead of a measured one, forgetting retrieved context in the token count, and counting every named user as active. Also remember that Epicor's own BAQ dashboards may answer fixed questions at no extra cost; the assistant is worth the most on cross-module questions.
Frequently Asked Questions
Why does GPU count depend on peak and not users?
Because requests arrive unevenly. A GPU serves a limited number of tokens per second, so the busiest hour sets the requirement. Two hundred named users who ask a few questions each may need only one GPU.
What throughput per GPU should I enter?
Measure it with your model, quantisation and context length under batching. A 7B to 14B model on a 24 GB to 48 GB GPU often delivers roughly 1,000 to 2,500 aggregate tokens per second, but results vary widely, so the default is only a starting point.
Does the index size include the original files?
No. It estimates the vector index only. Original documents, extracted text and the SQL replica need separate storage, so plan additional capacity for them.
How reliable is the monthly value?
It is as reliable as your minutes-saved input. Pilot with a small group, log answers that saved real time, and replace the default before using the figure in a business case.
If you want these numbers validated against your Kinetic environment and a real pilot, Netray can run that with you. The calculator works without any contact.
Related Tools
Epicor Kinetic Private AI Layer Blueprint Generator
Generate a shareable private AI architecture plan for Epicor Kinetic on-premises, with components, security controls, rollout phases and open questions for IT.
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.
On-Prem AIRAG Infrastructure Sizing Calculator
Estimate vector storage, node RAM, generation GPUs, and monthly infrastructure cost for a retrieval-augmented generation deployment over your document corpus.
On-Prem AIPrivate AI Total Cost of Ownership Calculator
Model the full 3-year cost of an on-prem AI deployment, including amortized hardware, power, staff time, and support, against comparable API spend.
More Epicor tools
See all- Epicor Kinetic Job Status Reference
- Epicor BAQ Query Template Generator
- Epicor BPM Directive Design Template
- Epicor DMT Import Template Worksheet (Part and BOM)
- Epicor MRP Run Checklist
- Epicor Kinetic Upgrade Checklist
- Epicor REST API v2 URL Builder
- Epicor Security Group Design Worksheet
- Epicor Safety Stock and Reorder Point Calculator
Keep exploring
Free tools
- Epicor ERP 10 AI Assistant Sizing and Value CalculatorEstimate GPUs, index size, hours saved and payback for a private AI assistant on Epicor ERP 10 on-premises.
- Epicor 9 and Vantage AI Assistant Sizing and Value CalculatorEstimate GPUs, index size, hours saved and payback for a private AI assistant over a legacy Epicor 9 or Vantage system.
- Epicor Eclipse AI Assistant Sizing and Value CalculatorEstimate GPUs, index size, hours saved and payback for a private AI assistant over Epicor Eclipse extract data.
ERP fixes and how-tos
- How to Add AI to Epicor Kinetic On-Premises Without Moving Your DataReference architecture for a private AI assistant on Epicor Kinetic on-premises: BAQ and REST v2 access, SQL replica, local LLM, roles, audit and rollout.
- Epicor Kinetic Update Schedule: Release Cadence, Versions and Upgrade PlanningHow Epicor Kinetic releases are numbered and scheduled, how cloud and on-prem updates differ, and how to plan upgrades and regression testing.
- Convert Epicor Classic Dashboards to KineticHow to convert Epicor Classic dashboards to Kinetic during an upgrade: what carries over, what must be rebuilt, and how to verify each dashboard.
AI on your ERP
- Private AI for Epicor Kinetic Cloud, Outside the Multi-Tenant BoundaryRun a private LLM on Epicor Kinetic private cloud or Kinetic Cloud data via BAQs, REST v2 and Data Fabric, keeping sensitive manufacturing data off shared AI.
- Epicor Kinetic AI for Metal Fabrication: Jobs, Heat Numbers and Outside Processing in Plain EnglishPrivate AI on Epicor Kinetic for metal fabricators: ask about jobs, nests, heat numbers and outside processing in plain English, grounded in live data.
Integrations
- How to add an AI chatbot to Epicor KineticAdd an AI chatbot to Epicor Kinetic: an internal assistant for planners and buyers or a customer portal bot, grounded in BAQs and runnable fully on-prem.
- How to add AI agents to Epicor KineticHow to add AI agents to Epicor Kinetic: a tool layer over the REST v2 API and BAQs, MRP exception triage, PO expediting, and human approval before any write.
Software
- Epicor KineticEpicor Kinetic explained for manufacturers: modules, REST API, BAQs, deployment, strengths, limits and alternatives to compare before choosing or upgrading.
- Epicor CPQEpicor CPQ is a cloud configure-price-quote product with visual 3D configuration for manufacturers. Modules, ERP integrations and alternatives explained.