Deltek Costpoint AI Assistant Sizing and Value Calculator
Estimate GPUs, document index size and monthly value for a private AI assistant on Deltek Costpoint. Contract and policy documents often dominate index size, so the document inputs matter here. It uses plain formulas you can check and change.
Your numbers
Share of named users who ask the assistant something on a given day.
Includes retrieved context. Short SQL answers run lower; document questions run higher.
Time the user would otherwise spend finding the answer. Measure it in a pilot.
Amortised hardware plus power and hosting per GPU, or the monthly rate for private cloud GPUs.
Aggregate throughput with batching for your chosen model and quantization. Measure with vLLM on your hardware.
Your results
Planning model. Formulas: questions/day = users x active share x questions each; tokens/day = questions x tokens; GPUs = ceil(peak-hour tokens per second / tokens per second per GPU); value = questions/day x 22 working days x minutes saved / 60 x hourly cost. The 20% peak-hour share and 20 second request time are fixed assumptions. Validate throughput with your own model and prompts.
GPUs needed vs questions per active user
Sweeps Questions per active user per day from 2 to 60, holding your other inputs fixed.
Validate my sizing
Optional: have the numbers checked with a measured pilot on your hardware. The calculator works fully without it.
Optional. The tool and every export work without this. No spam.
How to use it
Enter the number of named Deltek Costpoint users and the share who use the assistant daily. Add questions per active user, average tokens per question, documents and pages for the index, minutes saved, loaded hourly cost and GPU monthly cost. The tokens per second per GPU input is the most important assumption, so replace the default with a number from a test on your hardware.
- Start with a pilot group size and read hours saved.
- Raise tokens per question if you use long documents.
- Use the chart to see how demand scales with users or usage.
The method behind it
Daily tokens are questions times tokens per question. Peak load assumes 20% of daily questions land in the busiest hour, converted to tokens per second and divided by per-GPU throughput. Concurrency uses the same arrival rate times a 20 second request time. Index size assumes about three chunks per page, each around 9 KB for text and vectors. Value is minutes saved converted to hours, times 22 working days and hourly cost.
How to read the result
Typical Costpoint questions cover project cost to date, funding remaining, labor by project and variance explanations, and many answers cite long contract or policy documents. If the GPU count is one, plan a second for resilience once the assistant is relied on. If payback days exceed 30, either the usage is low, the time saved is small, or the hardware is oversized for the load.
Common mistakes
Counting named users as active users, ignoring retrieved context in the token count, trusting vendor throughput numbers for a different model, and claiming time saved without a pilot measurement. Another is forgetting that model quality, not just speed, decides whether people keep using the tool. Treat value as a hypothesis until a pilot confirms it.
Frequently Asked Questions
Why is tokens per second per GPU an input?
It depends on the model, quantization, context length and batching. Public numbers rarely match your workload, so measure with vLLM on your hardware and enter the sustained figure.
Does the GPU estimate include redundancy?
No. It is the minimum for peak-hour load. For a production assistant, add at least one spare GPU or a failover plan.
How reliable is the value figure?
It is only as good as minutes saved per question. Measure that in a pilot by timing a sample of tasks with and without the assistant.
What does the index size include?
An estimate of text chunks and vectors for the documents you enter. It excludes the ERP database copy, which is sized separately by your DBA.
Want these numbers tested against your real Deltek Costpoint data and prompts? Netray can run a measured pilot on your own GPUs and report throughput and accuracy.
Related Tools
Deltek Costpoint Private AI Layer Blueprint Generator
Generate an architecture plan for a private AI assistant on on-prem Deltek Costpoint: SQL replica, web services and import interfaces, organization and project permissions, local GPU model and audit.
On-Prem AIOn-Prem GPU Sizing Calculator for ERP AI
Work out how much GPU memory and how many cards you need to serve an open-weight model to your ERP users on-prem.
On-Prem AIvLLM Throughput Estimator
Estimate aggregate tokens-per-second throughput for a vLLM deployment from model size, GPU class, and batch depth, accounting for continuous batching gains.
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.
More Other ERPs tools
See all- Infor VISUAL Work Order Status and Structure Reference
- Infor VISUAL Manufacturing Scheduling Checklist
- Infor XA (MAPICS) Period End Close Checklist
- Infor VISUAL Database Table Reference
- Infor XA (MAPICS) Application Module Reference
- IBM i Commands for Infor XA Administrators Reference
- Acumatica Generic Inquiry Design Template
- Acumatica Manufacturing Edition Setup Checklist
- Sage X3 Import Template Worksheet
Keep exploring
Free tools
- IFS Applications 10 AI Assistant Sizing and Value CalculatorEstimate GPUs, document index size and monthly value for a private AI assistant on IFS Applications 10. Maintenance and engineering documents often dominate index size.
- Deltek Costpoint Private AI Layer Blueprint GeneratorGenerate an architecture plan for a private AI assistant on on-prem Deltek Costpoint: SQL replica, web services and import interfaces, organization and project permissions, local GPU model and audit.
- SyteLine AI Assistant Sizing and Value CalculatorSize the GPUs and estimate the monthly value and payback of a private, on-prem AI assistant for SyteLine.
ERP fixes and how-tos
- Deltek Costpoint On-Prem AI Architecture for Government ContractorsPrivate AI architecture for on-prem Deltek Costpoint: SQL replica, web services and import interfaces, local GPU model, project permissions, audit and CUI.
- Deltek Costpoint Contract Management Module and Project Setup ChecklistA practical checklist for setting up a new contract and project in Deltek Costpoint: structure, funding, rates, billing, labor access and controls, in order.
- How to Process a Contract Modification in Deltek CostpointHow to record a contract modification in Deltek Costpoint: funding, value, ceiling and period of performance changes, with the sequence that protects billing.
AI on your ERP
- AI for Deltek Costpoint in government contract accountingAI on Deltek Costpoint for timesheets, indirect rates, and incurred cost, grounded on real data and deployed on-prem to keep DCAA-relevant data in house.
- AI for Deltek Costpoint Timekeeping and Labor: Timesheet Exceptions and Labor QuestionsPrivate AI on Deltek Costpoint timekeeping and labor: spot late, missing or unusual timesheet entries and answer labor questions without leaving your network.
Integrations
- How to add an AI chatbot to Deltek CostpointHow to add an AI chatbot to Deltek Costpoint: a grounded assistant for finance, contracts and program managers, running on-prem with open models when needed.
- How to use ChatGPT with Deltek CostpointHow to use ChatGPT with Deltek Costpoint: exports versus live access, custom GPT actions, enterprise data controls, and when a private model fits GovCon data better.
Software
- Deltek CostpointWhat Deltek Costpoint is, how its project accounting, manufacturing and indirect cost modules serve government contractors, and which ERP alternatives to compare.
- UnanetUnanet is project-based ERP for government contractors. See modules, integrations, strengths, limits, alternatives and where AI helps in contract accounting.