Business Central On-Prem AI Assistant Sizing and Value Calculator
This calculator estimates the hardware and value of a private AI assistant on Business Central on-premises. Enter users and question volume, and it returns GPUs, tokens, index size, hours saved and payback.
Your numbers
API results and retrieved passages add to the prompt.
Your results
Planning estimate. Measure throughput on your hardware, plan redundancy and validate time savings with a pilot.
Monthly net value vs questions per active user
Sweeps Questions per active user per day from 2 to 50, holding your other inputs fixed.
Get a sizing review for your Business Central estate
Optional: share your inputs and we will check GPU count and rollout assumptions.
Optional. The tool and every export work without this. No spam.
How to use it
Start with named users and the share who will use the assistant on a typical day. Questions per user depends on how often people look up orders, items and balances. Because API results are added to the prompt, tokens per question often run higher than for plain chat. Replace the default throughput with a measured value from your model and card.
- Use pilot data when you have it
- Raise tokens for document questions
- Compare one-GPU and two-GPU outcomes
- Keep the 22-day month in mind
The formulas
Questions per day equal active users times questions each. Peak tokens per second equal 20% of daily questions times tokens per question divided by 3600. GPUs equal that figure divided by throughput per GPU, rounded up. Index size equals pages times two chunks times 4096 bytes with 50% overhead. Net value equals hours saved times hourly cost minus GPU cost.
Reading the result
Look at the chart to see how value moves with usage: it rises with questions until a GPU step adds cost. If net value stays low, consider whether built-in reports and search cover the same questions. Payback shows how quickly the one-time build is recovered at the chosen inputs.
Frequently Asked Questions
Does API use change the sizing?
It affects tokens, because returned records are added to the prompt, and it adds load on the server instance. Keep result sets small and filtered.
Why does the value chart have steps?
GPU count is a whole number, so cost jumps when load crosses a capacity limit. The net value line shows those jumps as dips.
What default throughput is realistic?
It varies widely by model, quantisation and card. The default is a placeholder for planning; measure your own.
Is the index size the full storage need?
No. It covers vectors and metadata only. Keep the original documents and logs in your capacity plan too.
If you want these inputs tested against your Business Central environment, Netray can run a short sizing review with your IT team.
Related Tools
Business Central On-Prem Private AI Layer Blueprint Generator
Describe your Business Central on-prem setup and get an architecture plan for a private AI assistant built on API v2.0 and a local model.
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 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.
Microsoft DynamicsBusiness Central SaaS vs On-Premises TCO Calculator
Model subscription, licensing, infrastructure, admin time and upgrade effort for BC online versus on-premises over 1 to 10 years.
More On-Prem AI tools
See allKeep exploring
Free tools
- Business Central On-Prem Private AI Layer Blueprint GeneratorDescribe your Business Central on-prem setup and get an architecture plan for a private AI assistant built on API v2.0 and a local model.
- Dynamics NAV AI Assistant Sizing and Value CalculatorWork out the GPUs, index size and monthly value of a private AI assistant on NAV from your users and question volume.
- Dynamics GP AI Assistant Sizing and Value CalculatorSize a private AI assistant for Dynamics GP: GPUs, index and monthly value from users and questions per day.
ERP fixes and how-tos
- Adding a Private AI Layer to Business Central On-PremisesAdd AI to Business Central on-prem without cloud: API v2.0, custom API pages, SQL replica, retrieval, local LLM, BC permission sets, approved write-back.
- Business Central Manufacturing Setup: Items, BOMs, Routings and Production OrdersSet up Business Central manufacturing: Manufacturing Setup, work centers, production BOMs, routings, item settings, manufacturing policy and demo data.
- Business Central Item Templates and Customer TemplatesCreate and use item templates and customer templates in Business Central to default posting groups, costing method and dimensions on every new record.
AI on your ERP
- AI for Dynamics 365 Business Central in Discrete ManufacturingGrounded AI for Dynamics 365 Business Central discrete manufacturers: production orders, planning worksheets, routings and costing, on a private LLM.
- AI for Business Central manufacturing operations, beyond CopilotAI for Business Central manufacturing beyond Copilot: grounded answers on production orders, routings, and capacity via APIs v2.0, on-prem capable.
Integrations
- How to add an AI chatbot to Dynamics 365 Business CentralAdd an AI chatbot to Business Central: staff assistant, customer portal bot, grounding on ERP data, role-aware answers, and running it on-prem with open models.
- How to add WhatsApp to Microsoft Dynamics 365 Business CentralHow to connect WhatsApp to Dynamics 365 Business Central: API v2.0 or custom API pages, webhooks, template messages, and two-way replies that post back safely.
Software
- Microsoft Dynamics 365 Business CentralDynamics 365 Business Central explained for manufacturers: modules, APIs, AL extensions, deployment, strengths, limits and alternatives for small and mid-size firms.
- Microsoft Dynamics 365 Finance and Supply ChainDynamics 365 Finance and Supply Chain Management explained for manufacturers: modules, data entities, OData, deployment, strengths, limits and alternatives.