
Learn to use cloud in Excel for operations analytics with speed, structure, and judgment, modeling inventory, forecasting, and production to turn data into decisions and validate assumptions.
Discover how to use Claude AI in Excel with a disciplined, layered method—profile, model, plan, compare, and challenge—applied to inventory analytics, demand forecasting, and production planning.
Install the Claude add-in in Excel, connect your account, and explore the interface, including settings for instructions, session logging, model selection, and future skills.
Welcome to the Inventory Analytics section.
Inventory is one of those areas where small decisions can create big operational consequences. Too much inventory ties up cash and space. Too little inventory can create shortages, missed sales, and service problems. So the challenge is not only to calculate numbers, but to understand what those numbers mean for the business.
In this section, we will use Claude in Excel to work through inventory analysis in layers. We will first build a demand profile, then move into more quantitative models such as safety stock, reorder points, and replenishment logic. But we will not stop there. We will also translate the numbers into decisions, review exceptions, and question the assumptions behind the model.
That is the structure you will see throughout the course. We are not using AI just to create tables. We are using Claude to build an analytical workflow: understand the situation, model it clearly, and then move toward better operational decisions.
Learn to use Claude AI in Excel for Breitkart Market's inventory replenishment, translating demand profiles and lead time variability into data-driven reorder decisions.
Build the demand profile and ABC classification in Excel with Claude, creating a one row per product code table with metrics like annual demand, average weekly demand, variability, and ABC class.
Create a reusable Claude skill for inventory analytics in Excel, turning long prompts into modular instructions and enabling quick use via the Claude panel.
Learn how to turn inventory numbers into actionable business decisions by using Claude to interpret the model and generate an Inventory Decision Review with priority actions, risks, and management questions.
Welcome to the Demand Forecasting section. In the previous section, we worked with inventory analytics. But inventory decisions depend heavily on one question: what demand do we expect in the future? If the demand signal is weak, even a well-built inventory model can lead to poor decisions.
That is why we now move into demand forecasting. In this section, we will use Claude in Excel to understand demand patterns, build baseline forecasts, measure forecast error, and then translate those forecasts into operational planning signals.
The goal is not to create a forecast that looks sophisticated just for the sake of it. The goal is to build a forecasting workflow that is clear, auditable, and useful for operations. We want to understand seasonality, promotions, stockouts, supplier timing, and capacity pressure.
So, just as we did with inventory, we will move in layers: first understand the demand profile, then build the quantitative forecast, then translate the numbers into planning decisions, and finally challenge the assumptions and risks behind the plan.
Explore demand forecasting with Claude AI in Excel for Atlas, linking forecasts to purchasing and inventory planning. Assess promotions, stockouts, and calendar events to build a practical forecast for operations.
Create baseline forecasts in Excel using Claude, compare simple methods across the training and test periods, and measure forecast error by product to guide operational decisions.
Translate forecasts into purchasing timing and capacity planning to create a practical forecast operations plan that highlights capacity risks, including receiving capacity, supplier planning, and pre-demand actions.
Challenge forecast assumptions and review operational risks behind the plan using a forecast risk review to validate assumptions, stress test scenarios, and prepare management questions before final decisions.
Welcome to the final section of the course: Production Planning and Capacity Decisions with Claude AI in Excel. In the previous sections, we worked with inventory and demand forecasting. That sequence matters. Inventory decisions depend on demand. Forecasting helps us anticipate that demand. But at some point, operations also needs to answer a very practical question: can we actually produce what the plan requires, when the business needs it?
That is what we will explore in this section. We will use Claude in Excel to move from demand and capacity context into a production plan, then into quantitative scenarios, and finally into assumptions and risks.
And I want to emphasize something important. We are not using Claude only to fill tables in Excel. We are using it to build an analytical workflow. First, we understand the situation. Then we build a model. Then we translate the numbers into a plan. Then we compare alternatives. And finally, we challenge the assumptions behind the recommendation.
This is where the work becomes more managerial. We are not only calculating. We are preparing to explain a production decision, defend it, and identify what could go wrong before presenting it to an operations manager.
Create a baseline production plan in Excel using Clawd, producing a monthly production plan matrix across eight products and twelve months, plus an audit detail table, for 2027.
Compare the baseline plan, a demand matching plan, and a capacity smoothing plan in Excel using Claude. Assess cost, packaging utilization, production timing, and inventory traces to reveal trade-offs.
Explore how to challenge production plan assumptions and risks with Claude AI in Excel, building an assumptions and risks review, risk matrix, scenario recommendations, and management conversation prep.
Learn the Claude in Excel method for operations analytics: diagnose reality, build auditable models, translate calculations into plans, compare options, and challenge assumptions for reusable workflows.
Explore how cloud in excel enables operations analytics across inventory management, demand forecasting, and production planning, and develop reusable skills to interpret results and decide with business context.
This course uses artificial intelligence tools as part of the learning experience. The main workflow is built around Claude AI in Excel for operations analytics. AI-assisted tools may also be used to improve audio and video production quality. However, the course structure, teaching cases, exercises, analytical logic, examples, and instructional design were created by Carlos Martínez, Ph.D.
AI is already creating value in operations, supply chain, inventory management, forecasting, and planning. But in operations, speed alone is not enough. A spreadsheet can look clean, a forecast can look sophisticated, and a production plan can look professional while still hiding weak assumptions, supplier risks, capacity problems, or planning errors.
That is why this course is not about flashy prompts or isolated tricks. It is about using Claude AI in Excel for Operations Analytics with speed, but also with structure, rigor, and judgment.
In this course, you will learn how to use Claude in Excel to support practical operations workflows. We will work through realistic business cases that simulate real operational decisions, including inventory analytics, demand forecasting, production planning, capacity decisions, assumptions review, and risk analysis.
You will use Claude in Excel to build demand profiles, classify products, model safety stock and reorder points, create replenishment policies, build baseline forecasts, measure forecast error, translate forecasts into purchasing and capacity signals, create production plans, compare scenarios, and review operational risks before trusting the result.
Across the course, we follow a clear method: understand the situation, build a visible model, translate the analysis into a plan, compare alternatives, and challenge the assumptions before accepting the output. This method is important because Claude can generate polished Excel work very quickly, but polished does not always mean reliable.
The goal is not only to generate Excel files faster. The goal is to help you build auditable, explainable, and professionally defensible operations analytics workbooks. You will learn how to inspect the logic, improve the model, question assumptions, and move from data to better operational decisions.
You will also learn how to turn selected workflows into reusable Claude Skills. Near the end of the course, we package those skills into an operations analytics plugin, so you can see how AI-assisted workflows can become more structured, repeatable, and adaptable to your own work environment.
This course includes downloadable Excel files, prompts, PDFs, reference materials, assignments with suggested solutions, Claude Skills, access to the Q&A forum, and AI-powered roleplays where you practice defending recommendations, assumptions, and conclusions in realistic business conversations.
Those roleplays are important because operations analytics is not only technical. At some point, you need to explain the recommendation, defend the assumptions, respond to questions, and show that your analysis is not only polished, but also thoughtful, reviewed, and operationally sound.
This course is designed for professionals, analysts, managers, students, and Excel users who want to apply AI to real operations work without needing programming or advanced data science experience.
If you want to use Claude and Excel for inventory, forecasting, production planning, and operational decision support, this course will give you a practical method, realistic examples, reusable resources, and a structured way to work with AI more confidently.