What are the ProjectVIEW AI models? DANAOS ProjectVIEW AI combines domain-specific small language models (SLMs) with leading large language models (LLMs), and chooses the model per use case. SLMs handle pattern recognition and numerical analysis on project data. LLMs handle reasoning, language and multi-step planning. Both work on ERP context retrieved at the moment of the question, so no model needs to be retrained on your data. For construction and other project-based industries, this mix of SLM and LLM matches the work: precise numbers on one side, explanation and judgement on the other. What is the difference between an SLM and an LLM? A large language model is a general model trained on broad text. It is strong at understanding questions, writing, summarising and planning a sequence of steps. A small language model is a smaller model focused on a narrower domain or task. It is typically faster and cheaper to run, and it can be tuned to recognise patterns in specific kinds of data. Neither is better in general. The question is which one fits the task. Why combine domain-specific SLMs and LLMs in construction? Project data in construction, shipbuilding and other project-based industries is mostly structured and numerical: quantities, unit rates, commitments, certifications, retention, fuel use. It also comes with its own language: BoQ, WBS, Cost Codes, variations, claims. Numbers need consistent, repeatable analysis. That is SLM work. A director needs to know why a project is over budget, in plain words. That is LLM work. The ERP holds the facts. That is deterministic work. Deterministic ERP + probabilistic AI. ProjectVIEW ERP keeps the record exact. The models add detection, explanation and forecasts, and the user stays responsible for decisions. Which model type handles which task? The table shows how tasks typically split between model types. The actual model for each use case is selected per deployment. Task Model type ERP data used Flag a quotation above the budget rate SLM (anomaly detection) Quotations, budget rates, Cost Codes Probability of cost overrun, forecast cost at completion SLM (numerical analysis) Budget, committed cost, actual cost, progress Abnormal fuel use or idle time on machinery SLM (pattern recognition) Machinery, fuel and activity records “Why is Project Alpha over budget?” LLM (reasoning and language) Retrieved cost lines, variations, commitments Executive briefing across projects LLM (summarising) Project KPIs and exceptions Contract clause extraction LLM (language) Contract documents Agent cycle: detect, investigate, explain, recommend, request approval LLM for planning and explanation, SLM for detection The module’s data and approval workflow How do an SLM and an LLM work together on one question? Take a director’s question: “Why is Project Alpha over budget?” Retrieve. ProjectVIEW AI retrieves Project Alpha’s budget, committed cost, actual cost, progress and open variations, within the director’s permissions. Analyse. Numerical analysis identifies which WBS elements and Cost Codes drive the deviation and how far each one is off. Explain. An LLM turns the result into a short explanation in plain language, with the figures and the source lines. Recommend. Where relevant, it suggests what to review next: an unapproved variation, a supplier above budget rate, a delayed certification. The director gets an answer that can be checked line by line in ProjectVIEW cost control. The decision stays with the director. What does model-flexible mean? ProjectVIEW AI is model-flexible: the model is chosen per use case rather than fixed for the whole product. A numerical forecast and an executive summary do not need the same model. Being model-flexible also means the AI layer can adopt better models as they appear, without changing how your data is structured in ProjectVIEW ERP. The structure in the ERP is the stable part; the models around it can change. Client-specific SLMs are on the ProjectVIEW AI roadmap. Retrieval or retraining: how does the AI know your business? ProjectVIEW AI retrieves ERP context at inference time. When a user asks a question, the relevant records are retrieved from ProjectVIEW ERP and passed to the model with the question. The model does not need to be retrained on your data. Current answers. The model reads today’s commitments, not last quarter’s training snapshot. Permissions respected. Retrieval follows the user’s role, so the model only sees what the user may see. No data baked into a model. Your commercial data is not built into model weights. This is how ProjectVIEW AI learns your business: through your structured ERP data, not through guesswork. Read more in how ProjectVIEW AI works. Is our data used to train public models? No. Data is not sent to public consumer AI services, and ProjectVIEW AI runs in a private environment. On Microsoft Azure, prompts are not used for model training. See ProjectVIEW AI data security and governance and the background article on private enterprise AI for construction. Frequently asked questions Which LLM does ProjectVIEW AI use? ProjectVIEW AI is model-flexible. The model is chosen per use case, combining leading LLMs for reasoning and language with domain-specific SLMs for pattern recognition and numerical analysis. Do you train a model on our project data? No retraining is required. ProjectVIEW AI retrieves ERP context at inference time and passes it to the model with the user’s question. Why not use a general AI chatbot for cost control? A general chatbot does not have your BoQ, WBS, Cost Codes or commitments, and it is not built for consistent numerical analysis. ProjectVIEW AI works on your governed ERP data and uses SLMs where numbers matter. Will there be client-specific models? Client-specific SLMs are a stated roadmap direction. No date has been announced. Does ProjectVIEW AI work in mining, marine or manufacturing? The models work on ProjectVIEW ERP data structured by BoQ, WBS and Cost Codes, which is common to project-based industries. The same approach is designed for construction, shipbuilding and repair, marine and offshore, mining and quarrying, and project-based manufacturing. Want to see which model answers which question? Book a demo and see ProjectVIEW AI answer cost, procurement and contract questions on ProjectVIEW ERP data. Book a Demo