Epicor Prophet 21 AI Assistant Sizing and Value Calculator
This calculator sizes a private AI assistant on Prophet 21 for counter sales and purchasing. It estimates GPUs for the busiest hour, vector index size, hours saved and payback.
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, rows from the reporting copy and catalogue chunks, plus the answer. Catalogue snippets raise this.
Price sheets, supplier catalogues, spec sheets, contracts and order PDFs.
Average across the document set.
Counter lookups save minutes, not hours; use a smaller figure than manufacturing planning questions.
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.
GPUs needed vs tokens per question
Sweeps Prompt plus answer tokens per question from 1000 to 16000, holding your other inputs fixed.
Epicor Prophet 21 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
Enter named users and the share active daily; distribution counters ask more questions than planners, so use a higher questions-per-user figure from a pilot if you can. Tokens per question grow when catalogue chunks are retrieved. Use minutes saved per lookup that matches counter work, which is usually a few minutes.
- Counter users can ask 10 to 25 questions a day
- Short answers keep tokens low
- Treat branch opening hours as the peak
- Compare to P21 screens that already answer the question
The method
Daily questions = users x active share x questions each. Busiest hour carries 25 percent of the day. Tokens per second at peak = questions x 0.25 / 3600 x tokens per question. GPUs = that rate divided by throughput, rounded up. Index = documents x pages x 2 chunks x 1024 x 4 bytes x 1.5. Value = daily questions x minutes saved / 60 x 21 x hourly cost.
Reading the sweep
The line shows how GPU need rises with context length. Retrieval-heavy answers over catalogues use far more tokens than simple availability lookups, so keep the context tight. If the line crosses to a second GPU early, consider a smaller model or answer-length limits before buying hardware.
Common mistakes
Common errors include overestimating minutes saved per lookup, ignoring peak-hour concentration at branch open, and counting the value of questions the P21 screen already answers quickly. Use the assistant where it spans items, customers and vendors.
Frequently Asked Questions
Why are counter minutes saved so low?
Counter questions are quick lookups, so the saving per question is a few minutes at most. The value comes from volume. Use a conservative figure and let high question counts drive the total.
Does branch count change the result?
Not directly; users and question volume do. But branches that open at the same time create a sharper peak, so use the busiest hour from your own logs where you can.
Is the index size large for distributors?
It can be, because catalogues and spec sheets are page-heavy. The estimate covers vectors only. Plan separate storage for the files, the extracted text and the SQL reporting copy.
Can I use this for budget approval?
Yes as a first estimate, with a note that inputs are assumptions. Replace defaults with pilot measurements for throughput, question volume and minutes saved before presenting the final case.
If you want these numbers tested against your branch usage, Netray can help with a pilot. The calculator works without any contact.
Related Tools
Epicor Prophet 21 Private AI Layer Blueprint Generator
Generate a private AI architecture plan for Epicor Prophet 21 on-premises for counter sales, purchasing and branch operations.
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- Prophet 21 Inventory Replenishment Calculator
- Prophet 21 Pricing Library Design Worksheet
- Prophet 21 Upgrade Checklist
- Prophet 21 Data Cleanup Checklist
- Prophet 21 Special Order Request Form Template
- Prophet 21 Vendor Return Authorization Request Template
- P21 Dead Stock Hold vs Liquidate Calculator
- P21 Price Matrix Multiplier and Margin Calculator
- Prophet 21 Inventory by Location SQL Generator
Keep exploring
Free tools
- Epicor Prophet 21 Private AI Layer Blueprint GeneratorGenerate a private AI architecture plan for Epicor Prophet 21 on-premises for counter sales, purchasing and branch operations.
- Prophet 21 Data Cleanup ChecklistA checklist for cleaning item, customer, vendor, pricing and inventory data in Prophet 21 before an upgrade, migration or reporting project.
- Prophet 21 Upgrade ChecklistA phase-by-phase checklist for upgrading Prophet 21: scope, test copy, customizations, integrations, cutover and the first week after go-live.
ERP fixes and how-tos
- How to Add AI to Prophet 21 On-Premises Without Moving Your DataPrivate AI assistant for Epicor Prophet 21 on-prem: SQL Server views, P21 API options, local LLM, role and location filters, audit and rollout steps.
- Epicor Prophet 21 API Documentation: Which API to Use and Where to Find the DocsThe Prophet 21 API options explained: Data Service (OData), Middleware and SOAP style services, how authentication works, and how to choose.
- Epicor Eclipse or Prophet 21: how a distributor should make the decisionA blunt decision guide for CIOs on Epicor Eclipse versus Prophet 21: what to ask Epicor, which factors matter, and how to avoid a costly migration mistake.
Integrations
- How to add AI agents to Epicor Prophet 21How to add AI agents to Epicor Prophet 21: a tool layer over the P21 APIs and SQL Server views, distribution workflows, human approval and on-prem hosting.
- How to use ChatGPT with Epicor Prophet 21Using ChatGPT with Epicor Prophet 21: custom GPT actions, exports versus live access, enterprise data controls and when a private model fits better.