Blog · Topic
What AI can and cannot do with sales data, and why the language model should never do the arithmetic: our tools do it, and check it.
Use CRM and revenue exports to compare pipeline, ownership gaps and forecast changes. Build a weekly sales-operations review with spreadsheet formulas, a forecast bridge and clear exception handoffs.
Oct 24, 20265 min readAgentic analytics lets software coordinate an analysis. Set the scope, keep calculations in tools, and decide what a person must approve before acting.
Oct 17, 20264 min readA finance owner's guide to Snowflake semantic views: metric definitions, grain, relationships, answer checks, and when a file-first workflow fits.
Oct 17, 20265 min readCompare retailer advertising spend with attributed sales from campaign exports. Align attribution windows, account for matched refunds, and reconcile totals before interpreting performance differences.
Oct 15, 20265 min readSee revenue, margin and budget questions answered from a small business workbook. Each example identifies the required fields, works the figures and shows the checks and decisions they support.
Oct 14, 20266 min readThe four types of analytics answer different business questions. Compare a summary, a driver bridge, a forecast check and an action comparison using the same sales workbook, with explicit assumptions and reconciliations.
Oct 13, 20267 min readSet up a financial-statement analysis request using a ledger export, account mapping and budget. Rebuild a worked quarter comparison, reconcile the returned figures, and review the explanation before it enters a finance report.
Oct 9, 20266 min readCompare supplied financial scenarios with actual results using explicit assumptions and spreadsheet relationships. Reconcile revenue, costs and operating profit before asking AI to explain the differences.
Oct 1, 20265 min readCompare advertising and subscription revenue by account and offering from reconciled media revenue exports. Work through monthly movements, spreadsheet formulas and the checks that support an account review.
Sep 30, 20265 min readWrite agency analytics questions with a period, population and income basis. Ask for evidence and unknowns before explanations.
Sep 29, 20263 min readVerify scope, totals, evidence and uncertainty in AI-assisted agency reports. Review numbers and explanations separately.
Sep 29, 20263 min readDistinguish agency commercial reporting from insurer risk and pricing models. Match the question to the data and professional review required.
Sep 28, 20263 min readWhat text-to-SQL is, how accurate it is on the Spider and BIRD benchmarks, and a worked query on two tables, revenue by region for customers with more than 10 orders, with the check that proves it. Then the same question going wrong three ways, the alternative of mapping questions to tested calculations, and when text-to-SQL is the right tool.
Sep 26, 20266 min readWhere AI saves a small business time or money, as eight uses with what to measure for each. One is worked in full: which regular customers of a small wholesaler have gone quiet, with the check that proves the list. Then how to judge payback without a big project, and the risks to manage first.
Sep 17, 20266 min readWhere artificial intelligence actually earns its place in a company: 12 practical uses across finance, sales and operations, each with the measure that shows whether it paid back. Includes what the US Census Bureau and the Stanford AI Index report on adoption, a worked example of a question asked of a sales ledger, a payback template and the NIST AI Risk Management Framework as the risk checklist.
Sep 17, 20267 min readAn AI dashboard adds three things to ordinary charts: plain-language questions, flags on measures that moved beyond their normal range, and a written explanation. This page gives three examples, works through six measures with z-scores to show which ones are flagged and why, and covers what the AI model may write, what it must cite, and what to ask before you buy one.
Sep 16, 20265 min readWhat AI data analysis is, split into the part the AI model does well (reading the question, choosing the method, explaining the result) and the part it must leave to deterministic tools (the arithmetic). A worked gross-margin fall split into mix and rate shows the split in practice, with the checks that make an answer trustworthy and a five-question test for any tool.
Sep 16, 20266 min readWhat an AI data analyst tool actually does with a question, worked through on a CRM export to find which region's win rate fell most. It covers the checks that prove the answer, where such a tool has to stop, how it compares with a human analyst and a BI tool, what the BLS outlook says about analyst jobs, and five tests for choosing one.
Sep 16, 20266 min readWhich parts of financial analysis AI can be trusted with, which it cannot, and how to tell the difference. A budget variance question is worked through on six ledger accounts, with the checks that make the answer trustworthy, where AI helps most in FP&A, and the data and governance questions to settle first.
Sep 16, 20267 min readData-driven decision making starts with a question, comparable options and reconciled files. Follow a shipping-cost example from sales and cost exports through spreadsheet formulas, sensitivity checks and an accountable decision.
Sep 5, 20265 min readInteractive business analytics follows successive questions from a company total to the rows that explain it. This worked revenue example shows how to compare regions, customers and products while preserving a checked total.
Sep 5, 20265 min readA plain explanation of why large language models make arithmetic errors, for people deciding whether to trust AI with business figures. A language model predicts the next piece of text; it does not calculate. It reads numbers as fragments, not quantities, produces answers that look right, and is most likely to be wrong on long numbers, long columns and multi-step calculations, which is exactly what business data involves. This page explains the mechanism without jargon, shows the kinds of error to expect, and sets out the design rule that removes the problem: the model decides what to compute and explains the result, and code does every calculation.
Aug 28, 20265 min readUse AI for workforce analytics to explain department-level staffing, workload and labor-cost variances. Reconcile uploaded planning and actual files, separate hours and rate effects, and keep the analysis focused on aggregate resource planning.
Aug 22, 20266 min readThree software categories with overlapping names. Sales analytics measures what happened in your own sales data. Sales intelligence, as the market uses the term, mostly means third-party data about companies and contacts to prospect into. Revenue intelligence mostly means capturing and analyzing calls, emails and CRM activity to inspect deals and forecast. This page sets out what each actually does, the data each runs on, the question each answers, where coverage intelligence sits among them, and how to tell which one a problem needs.
Aug 20, 20264 min readA checklist for anyone about to put a customer ledger, a CRM export or a contract file into an AI analytics tool. It covers what is actually in a sales export that makes it sensitive, the nine questions to put to any vendor, covering model training, where data is processed, who at the vendor can see it, retention and deletion, tenancy, pseudonymization, access control, the model provider behind the tool, and what happens at exit, what a good answer sounds like for each, and how to reduce the risk yourself by removing what the analysis does not need.
Aug 15, 20265 min readA practical answer to whether a general-purpose AI chatbot can analyze a sales export. It can: given a clean file and a precise question, a chatbot with a code tool will compute correct totals, rankings and simple rates. It goes wrong in predictable places: silent assumptions about what columns mean, duplicated customers, joins across files, definitions that change between sessions, arithmetic done in prose rather than in code, and no check against the ledger. This page lists what works, the seven failure points, five checks anyone can run on an answer, and what a purpose-built tool does differently.
Aug 9, 20265 min readA plain argument for lists over dashboards as the output of sales analytics: what a dashboard asks the reader to do, what a list asks, why the dashboard's forty tiles produce no action and the list's ten rows produce ten, the four properties a list needs to be worked, ranked, valued, reasoned and owned, and how the dashboard survives as the place to check rather than the place to start.
Aug 8, 20263 min readThe one rule that makes AI analytics safe to put in front of a sales desk or a bank: the language model chooses the calculation and explains the result, and deterministic code computes every figure. Why the alternative fails, and what the rule changes in practice.
Aug 8, 20264 min readAn analytics assistant that reads computed tables and declines arithmetic will refuse some requests, and how it refuses decides whether the reader trusts it. This guide sets out the four requests a well-built assistant declines, add these up, average this, extrapolate that, estimate what is missing, what each refusal says, where it points instead, the tone that keeps the reader, and the refusals that are wrong because the table exists.
Aug 7, 20263 min readThe case for taking a scheduled file from the customer's systems rather than connecting to them: what a live connector costs in credentials, per-customer schema and outages, why every system already exports a file, the four ways a file arrives, and when a bespoke adapter is still right.
Aug 7, 20263 min readWhy self-service analytics fails without one governed definition of each metric, how to run a versioned registry where net revenue v4 supersedes v3 on a date, how scope is applied in the data layer rather than a prompt, and what an audit trail per answer has to record.
Aug 6, 20263 min readCoverage intelligence is the practice of measuring, from a company's own sales data, which customers it reaches, how much of each customer's spend it holds, and where the gaps are, with every figure reconciled to the ledger. This guide defines it, sets out its five measures, coverage, share of wallet, gap at norm, dormancy and concentration, shows how they roll up, and distinguishes it from BI, CRM reporting and sales analytics.
Aug 6, 20263 min readUse customer insights AI to explain verified changes in revenue, repeat buying and product breadth. Build the measures from your sales export, reconcile the customer bridge and separate observations from explanations that still need evidence.
Aug 1, 20265 min readA buyer's checklist for AI sales analytics: where each number comes from, whether the model computes or reads, how definitions are versioned, what the roll-up identity is and whether it is checked, how a wrong answer is caught, what data leaves your building, whether names are needed, what happens when the exports change, what the assistant refuses to do, and what you can take with you. Each with the answer that should worry you.
Aug 1, 20263 min readNatural language analytics turns a plain-English business question into a defined calculation. Follow a revenue comparison from source records to checked totals and a traceable explanation.
Jul 28, 20264 min readUse AI-assisted questions in Power BI with an independent check on the answer. Work from a sales export to signed revenue totals, reconcile the report and verify the explanation.
Jul 25, 20265 min readHow to decide what counts as a movement worth reporting for each measure in a weekly sales digest: thresholds from the measure's own week-to-week variability rather than a round number, the floor that stops small denominators generating alerts, the cap on items per digest, and the review that tightens or loosens each threshold from how many alerts were acted on.
Jul 25, 20262 min readA plain comparison for a commercial leader deciding what to buy: what self-service dashboards do, what an AI layer adds, the parts of the job that neither replaces, the two failure modes specific to AI analytics, generated numbers and unstated definitions, and the test that tells a trustworthy AI analytics tool from a fluent one.
Jul 24, 20263 min readAI customer segmentation starts with observable buying measures and approved rules. Use a sales export to assign customers to reproducible groups, reconcile their revenue and test how a threshold changes the result.
Jul 17, 20265 min readWhat an answer engine extracts from a page about a commercial measure: the one-paragraph direct answer, the formula in a form it can quote, the worked table, the definitions it can cite, and the questions it can answer verbatim. Why a page written for a person who has to compute the measure is also the page an assistant cites, the structure that serves both, and the four habits that make a page unquotable.
Jul 4, 20263 min readWhat separates a question an AI analytics assistant answers correctly from one it answers plausibly: naming the measure, the level, the period and the comparison, asking for the table before the sentence, and checking the citation. Six rewrites of common questions, and the four kinds of question an assistant should refuse.
Jul 4, 20263 min readHow an analytics product uses a language model without letting it touch a number: deterministic code computes every measure from stated definitions, a tool registry names each computation, the model plans which tools to call and reads their outputs, every output carries its citation, and the model's own text is labeled as a reading. The four boundaries that make this hold, what crosses each, and what never does.
Jun 29, 20263 min readCompare campaign spend, recorded conversions and customer revenue from your own exports. Follow a repeatable review with spreadsheet formulas, reconciliation checks and clear limits on attribution.
Jun 27, 20265 min readA number in a report or an assistant's answer is a claim until it carries a citation, and a citation has five parts: the table, the row, the period cut, the definition version, and the upload it was computed from. Why each part is there, what a reader does with it, the difference between a citation and a link, how a citation survives a re-upload, and the three shortcuts that turn a citation into decoration.
Jun 24, 20263 min readHow a team whose data lives in Excel or Google Sheets can ask plain-English questions of the workbook they already keep: reading the structure as it is, mapping columns once, validating the totals, and getting answers with the rows behind them, without pivot tables or a data warehouse.
Jun 21, 20263 min readWhy every effect measured from a company's own history, samples and prescriptions, onboarding milestones and renewals, first-touch latency and first-year revenue, delayed installs and non-renewal, is an association and not a cause, the selection that makes it so, the comparison group that removes most of the noise, the sentence that reports it honestly, associated with rather than caused, why it is still enough to direct effort, and the two claims that are never made from it.
Jun 21, 20263 min readAn annotated example of a weekly sales digest built from computed tables: the header that states the period and the checks, ten movements each with the measure, the level, the change, the threshold and the citation, the three lists that follow, untouched, slipped and dormant, the line that says what did not move, and the footer with the definition version. What each element is for, and the version of the same digest that nobody reads.
Jun 19, 20263 min readWhat is wrong with the red-amber-green account health field most CRMs carry, what a computed health score is made of, five inputs from the ledger and the CRM with stated weights, how the weights are set from the company's own churn history rather than opinion, why the score is shown with its inputs and never alone, the identity that every account has one score from the same rule, and how the score is validated against what happened.
Jun 19, 20263 min readEvaluate analytics deployment by locating original records, processing, saved results and access controls. Distinguish a hosted interface from hosted customer data.
Mar 17, 20193 min readEvaluate cloud dashboard collaboration with separate users, explicit role and data scopes, negative access tests and a record of failed or untested requirements.
Feb 10, 20163 min readEvaluate recovery of analytics inputs, configuration, definitions and approved outputs, with explicit recovery objectives, restore evidence and reconciliation checks.
Nov 2, 20073 min read