[{"data":1,"prerenderedAt":301},["ShallowReactive",2],{"navigation":3,"page-\u002Fcreating-datasets":130,"\u002Fcreating-datasets-surround":295,"comments-\u002Fcreating-datasets":300},[4],{"title":5,"path":6,"stem":7,"children":8,"page":129},"En","\u002Fen","en",[9,53,87],{"title":10,"path":11,"stem":12,"children":13,"icon":52},"CRM Analytics Foundations","\u002Fen\u002Ffoundations","en\u002F1.foundations\u002F1.index",[14,16,20,24,28,32,36,40,44,48],{"title":15,"path":11,"stem":12},"Welcome & Dev Org",{"title":17,"path":18,"stem":19},"Graded Quiz","\u002Fen\u002Ffoundations\u002Fquiz","en\u002F1.foundations\u002F10.quiz",{"title":21,"path":22,"stem":23},"What Is CRM Analytics?","\u002Fen\u002Ffoundations\u002Fwhat-is-crm-analytics","en\u002F1.foundations\u002F2.what-is-crm-analytics",{"title":25,"path":26,"stem":27},"Architecture","\u002Fen\u002Ffoundations\u002Farchitecture-and-data-flow","en\u002F1.foundations\u002F3.architecture-and-data-flow",{"title":29,"path":30,"stem":31},"The Data Layer","\u002Fen\u002Ffoundations\u002Fthe-data-layer","en\u002F1.foundations\u002F4.the-data-layer",{"title":33,"path":34,"stem":35},"The Design Layer","\u002Fen\u002Ffoundations\u002Fthe-design-layer","en\u002F1.foundations\u002F5.the-design-layer",{"title":37,"path":38,"stem":39},"The Intelligence Layer","\u002Fen\u002Ffoundations\u002Fthe-intelligence-layer","en\u002F1.foundations\u002F6.the-intelligence-layer",{"title":41,"path":42,"stem":43},"Hands-On Tour","\u002Fen\u002Ffoundations\u002Fhands-on-tour","en\u002F1.foundations\u002F7.hands-on-tour",{"title":45,"path":46,"stem":47},"Six Adoption Steps","\u002Fen\u002Ffoundations\u002Fsix-steps-and-interview-prep","en\u002F1.foundations\u002F8.six-steps-and-interview-prep",{"title":49,"path":50,"stem":51},"Interview Questions","\u002Fen\u002Ffoundations\u002Finterview-questions","en\u002F1.foundations\u002F9.interview-questions","i-lucide-compass",{"title":54,"path":55,"stem":56,"children":57,"icon":86},"Setup & User Provisioning","\u002Fen\u002Fsetup","en\u002F2.setup\u002F1.index",[58,60,64,68,72,76,80,83],{"title":59,"path":55,"stem":56},"Provisioning Users",{"title":61,"path":62,"stem":63},"Licenses & Permissions","\u002Fen\u002Fsetup\u002Flicenses-and-permission-sets","en\u002F2.setup\u002F2.licenses-and-permission-sets",{"title":65,"path":66,"stem":67},"Integration User","\u002Fen\u002Fsetup\u002Fthe-integration-user","en\u002F2.setup\u002F3.the-integration-user",{"title":69,"path":70,"stem":71},"Security User","\u002Fen\u002Fsetup\u002Fthe-security-user","en\u002F2.setup\u002F4.the-security-user",{"title":73,"path":74,"stem":75},"Analytics Settings","\u002Fen\u002Fsetup\u002Fanalytics-settings","en\u002F2.setup\u002F5.analytics-settings",{"title":77,"path":78,"stem":79},"Hands-On Access","\u002Fen\u002Fsetup\u002Fhands-on-assigning-access","en\u002F2.setup\u002F6.hands-on-assigning-access",{"title":17,"path":81,"stem":82},"\u002Fen\u002Fsetup\u002Fquiz","en\u002F2.setup\u002F7.quiz",{"title":49,"path":84,"stem":85},"\u002Fen\u002Fsetup\u002Finterview-questions","en\u002F2.setup\u002F8.interview-questions","i-lucide-settings-2",{"title":88,"path":89,"stem":90,"children":91,"icon":128},"Creating Datasets","\u002Fen\u002Fcreating-datasets","en\u002F3.creating-datasets\u002F1.index",[92,94,97,101,105,109,113,117,121,125],{"title":93,"path":89,"stem":90},"What Is a Dataset?",{"title":17,"path":95,"stem":96},"\u002Fen\u002Fcreating-datasets\u002Fquiz","en\u002F3.creating-datasets\u002F10.quiz",{"title":98,"path":99,"stem":100},"The Data Landscape","\u002Fen\u002Fcreating-datasets\u002Fthe-data-landscape","en\u002F3.creating-datasets\u002F2.the-data-landscape",{"title":102,"path":103,"stem":104},"Upload a CSV","\u002Fen\u002Fcreating-datasets\u002Fload-data-from-csv","en\u002F3.creating-datasets\u002F3.load-data-from-csv",{"title":106,"path":107,"stem":108},"Grain, Lookups & Joins","\u002Fen\u002Fcreating-datasets\u002Fgrain-lookups-and-joins","en\u002F3.creating-datasets\u002F4.grain-lookups-and-joins",{"title":110,"path":111,"stem":112},"Dataset Builder","\u002Fen\u002Fcreating-datasets\u002Fbuild-with-dataset-builder","en\u002F3.creating-datasets\u002F5.build-with-dataset-builder",{"title":114,"path":115,"stem":116},"Run the Dataflow","\u002Fen\u002Fcreating-datasets\u002Frun-and-troubleshoot-the-dataflow","en\u002F3.creating-datasets\u002F6.run-and-troubleshoot-the-dataflow",{"title":118,"path":119,"stem":120},"Build with a Recipe","\u002Fen\u002Fcreating-datasets\u002Fbuild-the-same-dataset-with-a-recipe","en\u002F3.creating-datasets\u002F7.build-the-same-dataset-with-a-recipe",{"title":122,"path":123,"stem":124},"Combine Datasets","\u002Fen\u002Fcreating-datasets\u002Fcombine-datasets","en\u002F3.creating-datasets\u002F8.combine-datasets",{"title":49,"path":126,"stem":127},"\u002Fen\u002Fcreating-datasets\u002Finterview-questions","en\u002F3.creating-datasets\u002F9.interview-questions","i-lucide-database",false,{"id":131,"title":132,"access":133,"body":134,"description":285,"extension":286,"interview":133,"links":133,"meta":287,"navigation":288,"passScore":133,"path":89,"quiz":133,"seo":289,"stem":90,"video":290,"__hash__":294},"docs\u002Fen\u002F3.creating-datasets\u002F1.index.md","What Is a Dataset in CRM Analytics?",null,{"type":135,"value":136,"toc":275},"minimark",[137,141,159,162,167,174,185,190,194,201,212,223,231,234,250,257,261,264,268],[138,139,132],"h1",{"id":140},"what-is-a-dataset-in-crm-analytics",[142,143,144,145,149,150,154,155,158],"p",{},"Creating datasets is the ",[146,147,148],"strong",{},"first real step"," in any CRM Analytics (Tableau CRM) project. Before you can build a single dashboard, tell a story, or train an Einstein Discovery model, you have to get data ",[151,152,153],"em",{},"into"," the platform and shape it into something you can query. That \"something\" is a ",[146,156,157],{},"dataset",", and this whole section is about building them well.",[142,160,161],{},"After seven years of building on this platform, here is the honest version: nine times out of ten, your work starts by creating a dataset. There are exceptions — direct queries and live connections — but those solve narrow problems inside a specific dashboard. The bread and butter is the dataset.",[163,164,166],"h2",{"id":165},"so-what-actually-is-a-dataset","So what actually is a dataset?",[142,168,169,170,173],{},"A dataset is a ",[146,171,172],{},"storage format",". You take objects or tables that relate to each other, combine them, and store the result in a shape that is purpose-built for one analytics need.",[142,175,176,177,180,181,184],{},"Say you want to analyze opportunities. You would pull in the Opportunity object, but you'd also bring the ",[146,178,179],{},"Account"," each opportunity belongs to, the ",[146,182,183],{},"User"," who owns it, and maybe — down the road — related activities. All of that gets combined into one wide, self-contained dataset about opportunities. That is the exercise we'll do by hand later in this section.",[186,187],"lesson-cards",{":columns":188,":items":189},"3","[{\"title\":\"It's storage\",\"icon\":\"i-lucide-hard-drive\",\"description\":\"A dataset physically stores a snapshot of your data — it is not a live pointer back to Salesforce rows.\"},{\"title\":\"It's combined\",\"icon\":\"i-lucide-combine\",\"description\":\"Multiple related objects (Opportunity + Account + User) are joined into one dataset serving a single analytics purpose.\"},{\"title\":\"It's optimized\",\"icon\":\"i-lucide-gauge\",\"description\":\"Data is compressed and indexed so dashboards query huge volumes in milliseconds.\"}]",[163,191,193],{"id":192},"why-its-so-fast","Why it's so fast",[142,195,196,197,200],{},"You don't need this on a daily basis, but it helps to know what's under the hood. A dataset uses a ",[146,198,199],{},"flattened, inverted-index, key-value storage system"," — a fancy way of saying it's a columnar file store with a proprietary compression and indexing algorithm.",[142,202,203,204,207,208,211],{},"The payoff is the whole point: you can store ",[146,205,206],{},"large volumes"," of data in a dataset and still query it fast enough to power an interactive dashboard. That combination — big data ",[151,209,210],{},"and"," sub-second response — is why the platform bothers with a dedicated storage format instead of just querying Salesforce directly.",[213,214,216],"tip",{"icon":215},"i-lucide-lightbulb",[142,217,218,219,222],{},"Because a dataset is a ",[146,220,221],{},"stored snapshot",", its data is only as fresh as the last time you refreshed it. Keeping datasets current is a scheduling problem — one we'll come back to when we talk about sync, dataflows, and recipes.",[163,224,226,227,230],{"id":225},"when-not-to-build-a-dataset","When ",[151,228,229],{},"not"," to build a dataset",[142,232,233],{},"Datasets are the default, but they aren't the only option. CRM Analytics also supports:",[235,236,237,244],"ul",{},[238,239,240,243],"li",{},[146,241,242],{},"Direct queries"," — query a small set of Salesforce data on the fly, without materializing a dataset.",[238,245,246,249],{},[146,247,248],{},"Live connections"," — read directly from an external source (like Snowflake) at query time.",[142,251,252,253,256],{},"Both are real and useful, but they fit a ",[151,254,255],{},"specific"," dashboard component or requirement, not the general case. If you're just starting out, assume you're building a dataset and treat live\u002Fdirect as the exception you reach for deliberately.",[163,258,260],{"id":259},"whats-ahead-in-this-section","What's ahead in this section",[142,262,263],{},"We'll cover the three practical ways to create datasets, from simplest to most powerful:",[265,266],"lesson-steps",{":items":267},"[{\"title\":\"CSV upload\",\"description\":\"The quickest path — drop a spreadsheet straight into a dataset. Great for external or one-off data.\"},{\"title\":\"Dataset Builder\",\"description\":\"A guided tool that walks the Salesforce object relationships for you and builds a baseline dataset through a dataflow.\"},{\"title\":\"Recipes\",\"description\":\"The modern, flexible, drag-and-drop way to join objects, transform data, and output finished datasets.\"}]",[142,269,270,271,274],{},"By the end you'll have built the same opportunities dataset two different ways and then combined it with external CSV data — exactly the muscle memory you need on real projects. Next up: the ",[146,272,273],{},"data landscape"," that shows where datasets sit in the bigger picture.",{"title":276,"searchDepth":277,"depth":278,"links":279},"",1,2,[280,281,282,284],{"id":165,"depth":278,"text":166},{"id":192,"depth":278,"text":193},{"id":225,"depth":278,"text":283},"When not to build a dataset",{"id":259,"depth":278,"text":260},"A dataset is the compressed, query-optimized storage that every CRM Analytics dashboard, lens, and story reads from. Learn what a dataset really is, why you build one, and when a live connection is the better call.","md",{},{"title":93},{"title":132,"description":285},{"id":291,"start":292,"end":293},"-0mp2mUjyVI",4,114,"Ftq2O8sAQOv3Q0GsZzkmcvu2WEGVrYdf5Npb4gyb9_s",[296,298],{"title":49,"path":84,"stem":85,"description":297,"children":-1},"Rehearse common CRM Analytics admin interview questions — permission-set licenses, Manage Analytics, the Integration User, the Security User, and row-level security predicates.",{"title":17,"path":95,"stem":96,"description":299,"children":-1},"Take the graded CRM Analytics exam on creating datasets — datasets and grain, CSV uploads, Dataset Builder, dataflows, recipes, and combining datasets. Score 85% to pass; questions rotate.",[],1783475144142]