https://ankurnapa.github.io/ Beer, Wine, Whiskey & AI explores where the drinks industry meets artificial intelligence — fermentation and distillation forecasting, production analytics, AI tasting notes, and the data science behind better beer, wine, whiskey, and mead. en-US Fri, 12 Jun 2026 12:41:31 -0700 Jekyll https://ankurnapa.github.io/2026/sankey-brewhouse-mass-energy-balance/ https://ankurnapa.github.io/2026/sankey-brewhouse-mass-energy-balance/ Fri, 12 Jun 2026 12:10:00 -0700 A brewery's biggest losses hide in plain sight across a dozen separate reports. A Sankey diagram puts the whole mass and energy balance in one picture — extract from grain to glass, water in to effluent out, energy in to heat lost — so the leaks become impossible to miss. brewing-sciencebrewing-data-vizdata-visualizationsustainabilityprocess-intelligence https://ankurnapa.github.io/2026/shelf-life-flavour-stability-trial-viz/ https://ankurnapa.github.io/2026/shelf-life-flavour-stability-trial-viz/ Fri, 12 Jun 2026 12:00:00 -0700 A beer's flavour stability is a story over time, not a single number — yet most breweries record it as a pass/fail. How to visualize forced-ageing and shelf-life trials as trajectories and small multiples, so staling becomes a path you can see, compare and predict. brewing-sciencebrewing-data-vizquality-controlflavour-stabilitydata-visualization https://ankurnapa.github.io/2026/spc-capability-cusum-ewma-brewing/ https://ankurnapa.github.io/2026/spc-capability-cusum-ewma-brewing/ Fri, 12 Jun 2026 11:50:00 -0700 The Shewhart control chart catches sudden spikes but is blind to slow drift — exactly how brewing quality usually fails. How process capability (Cp/Cpk), CUSUM and EWMA charts visualize the slow creep a basic control chart misses, in brewing terms. brewing-sciencebrewing-data-vizquality-controldata-visualizationprocess-intelligence https://ankurnapa.github.io/2026/true-to-target-batch-brand-profile-viz/ https://ankurnapa.github.io/2026/true-to-target-batch-brand-profile-viz/ Fri, 12 Jun 2026 11:40:00 -0700 True-to-target (TTT) tasting asks a different question than 'is it in spec' — does this batch still taste like the brand? How to visualize brand conformance with radar profiles, target bands and deviation tracking, so a panel's verdict becomes a picture the whole brewery reads. brewing-sciencebrewing-data-vizsensory-analysisquality-controldata-visualization https://ankurnapa.github.io/2026/brewing-viz-beyond-control-chart/ https://ankurnapa.github.io/2026/brewing-viz-beyond-control-chart/ Fri, 12 Jun 2026 11:30:00 -0700 Most brewery dashboards stop at the line chart and the control chart. This opens a series on the visualizations brewers rarely reach for — radar brand-profiles, CUSUM drift charts, shelf-life trajectories and Sankey balances — and how to match the chart to the brewing question. brewing-sciencebrewing-data-vizdata-visualizationquality-controlpower-bi https://ankurnapa.github.io/2026/vibe-coding-fermentation-dashboard-build-log/ https://ankurnapa.github.io/2026/vibe-coding-fermentation-dashboard-build-log/ Fri, 12 Jun 2026 11:20:00 -0700 A concrete, step-by-step build log of vibe-coding a small fermentation tracker with Claude Fable 5 — the actual prompts, the verify steps, the bug it introduced and how it got caught, so you can copy the loop for your own brewery tool. brewing-sciencevibe-coding-brewersvibe-codingclaudebuilding-with-ai https://ankurnapa.github.io/2026/claude-fable-5-for-brewers-who-build/ https://ankurnapa.github.io/2026/claude-fable-5-for-brewers-who-build/ Fri, 12 Jun 2026 11:10:00 -0700 Anthropic's latest model, Claude Fable 5, doesn't replace the brewer's judgement — it lowers the skill floor for building. What actually changes for a brewer making their own tools, what doesn't, and how to use it without fooling yourself. brewing-sciencevibe-coding-brewersclaudeai-toolsbuilding-with-ai https://ankurnapa.github.io/2026/vibe-coding-brewing-tool-claude-fable-5/ https://ankurnapa.github.io/2026/vibe-coding-brewing-tool-claude-fable-5/ Fri, 12 Jun 2026 11:00:00 -0700 Claude's latest model, Fable 5, makes it realistic for a brewer with no software background to build a small, genuinely useful brewery tool by describing what they want. Here's the honest loop, what Fable 5 changes, and where it still needs you. brewing-sciencevibe-coding-brewersvibe-codingclaudebuilding-with-ai https://ankurnapa.github.io/2026/brewer-generative-human-centered-ai-pair-guidebook/ https://ankurnapa.github.io/2026/brewer-generative-human-centered-ai-pair-guidebook/ Fri, 12 Jun 2026 10:30:00 -0700 The final stage of the brewer's AI roadmap — using generative AI well and building with it responsibly, grounded in Google's PAIR People + AI Guidebook and Microsoft Learn's responsible-AI resources, so what you make is something a brewer would actually trust. brewing-sciencebrewer-ai-roadmapgenerative-aiai-toolslearning https://ankurnapa.github.io/2026/brewer-first-machine-learning-model-free-courses/ https://ankurnapa.github.io/2026/brewer-first-machine-learning-model-free-courses/ Fri, 12 Jun 2026 10:20:00 -0700 Stage 3 of the brewer's AI roadmap — the machine-learning concepts that matter, then building a first real model on your own brewery data, using free resources: Google's Machine Learning Crash Course, Kaggle Learn, Elements of AI and scikit-learn. brewing-sciencebrewer-ai-roadmapmachine-learninglearningdata-science https://ankurnapa.github.io/2026/brewer-ai-foundations-data-python-free-resources/ https://ankurnapa.github.io/2026/brewer-ai-foundations-data-python-free-resources/ Fri, 12 Jun 2026 10:10:00 -0700 Stages 1 and 2 of the brewer's AI roadmap — data literacy with spreadsheets and Power BI, then Python — using only free, open resources: Microsoft Learn, Kaggle Learn and freeCodeCamp, with a real brewing project to learn against. brewing-sciencebrewer-ai-roadmaplearningpower-bidata-science https://ankurnapa.github.io/2026/brewer-ai-roadmap-step-by-step/ https://ankurnapa.github.io/2026/brewer-ai-roadmap-step-by-step/ Fri, 12 Jun 2026 10:00:00 -0700 A practical, five-stage learning path for a working brewer who wants to get into AI — data literacy, spreadsheets to Power BI, Python, machine learning and generative AI — built entirely on free, open resources like Microsoft Learn, Kaggle and Google's PAIR guidebook. brewing-sciencebrewer-ai-roadmaplearningai-toolsgenerative-ai https://ankurnapa.github.io/2026/winemaker-power-bi-fabric-developer/ https://ankurnapa.github.io/2026/winemaker-power-bi-fabric-developer/ Fri, 12 Jun 2026 09:20:00 -0700 What changes when one person has stood on the crush pad, run the ferments and pulled barrel samples — and also holds the Power BI and Microsoft Fabric certifications. Why the hybrid profile builds winery dashboards that survive a vintage, and the honest limits of being one. winemakingprocess-intelligencepower-bimicrosoft-fabriccareer https://ankurnapa.github.io/2026/brewer-distiller-power-bi-fabric-developer/ https://ankurnapa.github.io/2026/brewer-distiller-power-bi-fabric-developer/ Fri, 12 Jun 2026 09:20:00 -0700 What changes when one person has stood at the mash tun, the spirit safe and the crush pad — and also holds the Power BI and Microsoft Fabric certifications. Why the hybrid profile builds production dashboards that survive, and the honest limits of being one. distilling-maturationprocess-intelligencepower-bimicrosoft-fabriccareer https://ankurnapa.github.io/2026/why-power-bi-dashboards-fail-wineries/ https://ankurnapa.github.io/2026/why-power-bi-dashboards-fail-wineries/ Fri, 12 Jun 2026 09:10:00 -0700 A skilled Power BI developer walks into a winery and a vintage later the dashboards are abandoned. Not a tooling failure — a translation failure: units, lot genealogy, vintage time and KPIs that don't match how winemakers actually think. winemakingprocess-intelligencepower-bidata-strategywine https://ankurnapa.github.io/2026/why-power-bi-dashboards-fail-distilleries/ https://ankurnapa.github.io/2026/why-power-bi-dashboards-fail-distilleries/ Fri, 12 Jun 2026 09:10:00 -0700 A skilled Power BI developer walks into a distillery and eighteen months later the dashboards are abandoned. Not a tooling failure — a translation failure: units, batch genealogy, process time and KPIs that don't match how distillers and brewers actually think. distilling-maturationprocess-intelligencepower-bidata-strategywhiskey https://ankurnapa.github.io/2026/four-types-data-analytics-winery-fabric/ https://ankurnapa.github.io/2026/four-types-data-analytics-winery-fabric/ Fri, 12 Jun 2026 09:00:00 -0700 The four classic types of data analytics translated into winemaking language — yield per hectare, fermentation curves, wine faults, blend trials, barrel ageing — and where Microsoft Fabric's lakehouse, real-time intelligence and Direct Lake actually fit each one. winemakingprocess-intelligencedata-strategymicrosoft-fabricwine https://ankurnapa.github.io/2026/four-types-data-analytics-distillery-fabric/ https://ankurnapa.github.io/2026/four-types-data-analytics-distillery-fabric/ Fri, 12 Jun 2026 09:00:00 -0700 The four classic types of data analytics translated into distillery language — spirit yield, cut points, the angel's share, cask allocation — and where Microsoft Fabric's lakehouse, real-time intelligence and Direct Lake actually fit each one. distilling-maturationprocess-intelligencedata-strategymicrosoft-fabricwhiskey https://ankurnapa.github.io/2026/where-a-distillery-starts-with-ai/ https://ankurnapa.github.io/2026/where-a-distillery-starts-with-ai/ Thu, 11 Jun 2026 09:00:00 -0700 The capstone of the foundations series: not with a tool, but with one measured record. A distiller's order of operations — data, then dashboards, then machine learning, then generative AI — and the honest reason most AI projects fail before they begin. distilling-maturationdistilling-ai-foundationsai-adoptiondata-strategywhiskey https://ankurnapa.github.io/2026/heat-map-beer-use-cases/ https://ankurnapa.github.io/2026/heat-map-beer-use-cases/ Thu, 11 Jun 2026 08:00:00 -0700 When two categories meet — hour by day, style by month, account by SKU — a heat map shows intensity as colour, so patterns jump out of a grid. Three beer use cases and the colour-scale rules that keep it honest. brewing-sciencebeer-chart-guidedata-visualizationsales-intelligencecommercial-planning https://ankurnapa.github.io/2026/box-plot-beer-use-cases/ https://ankurnapa.github.io/2026/box-plot-beer-use-cases/ Thu, 11 Jun 2026 07:50:00 -0700 When you need to compare the spread and outliers of many groups at once, the box plot is unbeatable. Three beer use cases (consistency by brand, yield by shift, sensory spread by taster) and how to read the box. brewing-sciencebeer-chart-guidedata-visualizationquality-controlsensory-analysis https://ankurnapa.github.io/2026/histogram-beer-use-cases/ https://ankurnapa.github.io/2026/histogram-beer-use-cases/ Thu, 11 Jun 2026 07:40:00 -0700 Averages hide the story; a histogram shows the whole distribution — the spread, the shape, the second peak. Three beer use cases (fill-volume distribution, ABV consistency, sensory score spread) and the bin-width trap. brewing-sciencebeer-chart-guidedata-visualizationquality-controlfermentation https://ankurnapa.github.io/2026/bubble-chart-beer-use-cases/ https://ankurnapa.github.io/2026/bubble-chart-beer-use-cases/ Thu, 11 Jun 2026 07:30:00 -0700 A scatter plot with a third variable encoded as bubble size — show volume, value and growth together. Three beer use cases (portfolio maps, account prioritisation, market opportunity) and why size can mislead. brewing-sciencebeer-chart-guidedata-visualizationcommercial-planningsales-intelligence https://ankurnapa.github.io/2026/scatter-plot-beer-use-cases/ https://ankurnapa.github.io/2026/scatter-plot-beer-use-cases/ Thu, 11 Jun 2026 07:20:00 -0700 When the question is 'are these two things related,' the scatter plot is the answer — each point a batch, account or beer. Three beer use cases (process correlations, account value vs effort, recipe trade-offs) and the correlation-isn't-causation rule. brewing-sciencebeer-chart-guidedata-visualizationquality-controlsales-intelligence https://ankurnapa.github.io/2026/area-chart-beer-use-cases/ https://ankurnapa.github.io/2026/area-chart-beer-use-cases/ Thu, 11 Jun 2026 07:10:00 -0700 An area chart is a line chart with the space below filled — good for cumulative totals and, stacked, for how a composition shifts over time. Three beer use cases and when a line or stacked bar is the better call. brewing-sciencebeer-chart-guidedata-visualizationcommercial-planningsales-forecasting