How to do AI in practice, part II – Quotation Workflow
And what might it actually look like? ERP receives a request for quotation. It contains data: material: 16MnCr5, requirement: CHD = 0.8 mm, customer, deadline, quantity. While ERP contains approved technological procedures, operations, work centers, furnace groups, approved recipes, control plans, cost rates, qualifications and equipment limitations, AI can suggest a better solution based on historical analysis
ERP sends a simple query to the AI layer via the API interface:
The AI layer queries the data warehouse.
“Find all batches of 16MnCr5 with CHD 0.75–0.85 mm in the last 12 months.”
The AI pulls out: boost/diffuse parameters, temperatures, pressures, gradients, fixtures, CHD results, hardness, deformations, complaints and evaluates which processes were the best, which had deviations, which had deformations, which had complaints and returns the result to the ERP system in the form of a simple answer:
ERP then does what it can, creates a bid product, assigns the bid production routing LPC_32_12_12 to the bid product, calculation and technological assumptions.
Is it still hard to imagine? AI has proposed the most suitable known process based on the available history. The proposal will then be forwarded to Contract Review, which can be partially or completely performed by AI again, and only at the end is the approval of the responsible person required. In the end, the result of AI‘s activities is the correct entry in ERP, a new offer, with the most advantageous production process, with ideal routing, optimal fixtures, price.
And here most companies from the tempering industry panic: Oh my god, someone has to program this! That’s IT! That’s ERP integration! That’s cloud!
This is only partially true. Middleware plays an important role here. This is software that acts as a bridge between applications, databases and operating systems. It plays an important role in cloud computing by helping to maintain simplified communication, data management and interoperability across environments, including on-premises servers, hybrid solutions and modern cloud platforms. Middleware can be implemented, for example, using the integration services of the Microsoft Azure platform, SAP BTP, other integration platforms or specialized industrial Middleware. So it is something that can be purchased.
The basis can be a standard software platform, but its deployment requires the configuration of connectors, data mapping. For non-standard ERP systems, historical databases or custom AI models, the development of specific integration functions may also be necessary.
The closest practical analogy is SCADA. SCADA is purchased as generic software, but must be configured for a specific furnace. The AI layer works in the same way.
=======================================================================================================
Abbreviations used:
AI: Artificial Intelligence
API: Application Programming Interface: definované rozhraní a soubor pravidel, podle kterých si dva systémy předávají data a příkazy. Webové API může být dostupné prostřednictvím jedné nebo více URL adres, označovaných jako endpoints.
JSON: JavaScript Object Notation: textový formát pro strukturovaný přenos dat. Vznikl v prostředí JavaScriptu, ale dnes je nezávislý na programovacím jazyce.
Middleware: integrační vrstva, která propojuje systémy, transformuje data, řídí komunikaci, zabezpečení a auditní záznamy.
AI model: matematický nebo statistický model, který provádí klasifikaci, predikci, detekci odchylek nebo doporučení.
OPC UA: Open Platform Communications nebo OPC Unified Architecture
AI vrstva: řešení sestavené ze standardních platforem, konektorů, pravidel a individuálně nakonfigurovaných nebo vyvinutých modelů.
Document AI: Technologie využívaná k extrakci využívá k extrakci informací z tištěných i digitálních dokumentů, jako jsou obrázky, texty, znaky
DMS: Document Management System
FQ: Request For Quotation
APQP: Advanced Product Quality Planning
PPAP: Production Part Approval Process
ERP: Enterprise Resource Planning
=======================================================================================================
Are you solving a similar problem? I will help you with the analysis…
40+ years of experience in the field
30+ years of experience… HT-PROGRES, Bodycote, Galvamet
cooperation… VŠB, Czechimplant, ECM Technologies, TAV Vacuum Furnaces, GHC Invest
12+ years of expert activity
Want to ask for a solution or want a non-binding consultation? Click on this link, I will usually respond within 24 hours. Contact email
========================================================================================================
Jiří Stanislav, Ing. CSc.
Consultant and forensic expert
========================================================================================================
31/7/2026
