Floemdata
KNOWLEDGE BASE

Guides

Plain explanations of the systems and concepts behind the product.

A plus-shaped pixel pattern and its copy: in the copy one arm cell is missing and a stray amber cell sits in a corner
Featured
AI

AI-Written Report Summaries: Accuracy Risks

Letting a language model summarise a report saves time but risks invented commentary and wrong figures. Ways to limit the risk and Floemdata's stated principle.

2026-11-11 · 5 min read

Latest articles

One line enters a triangular prism and leaves as three diverging lines: one ends in a solid dot, two in hollow amber rings
Data & ETL

Join Fan-Out: Why Totals Inflate

A one-to-many join duplicates rows and inflates totals. How to spot the fan-out and prevent it, with an invoice and payments example and Floemdata's status.

2026-11-11 · 4 min read
A pipe carrying segments of different lengths through a round meter with a needle
AI

AI Usage Cost: What You Should Measure

What should you measure so the AI bill is no surprise? Tokens, caching, retries and cost per business outcome, as a measurement plan that invents no prices.

2026-11-09 · 5 min read
A line chart whose solid history line continues as a dashed forecast inside a widening uncertainty fan
AI

AI Financial Forecasting: Cash Flow

Why seasonality and payment behavior matter in cash flow forecasts. We cover starting simple, how to check a forecast against actuals, and its limits.

2026-11-02 · 3 min read
A chain of five nodes with a gap and a warning triangle where the third step breaks
AI

5 Common Failures with AI at Work

Five common mistakes in business use of AI tools, each with a fix: confidential data, unchecked output, leaving the math to the model, and more.

2026-11-01 · 3 min read
A speech bubble with text lines points to a three-bar chart, a question turning into an answer
AI

Natural-Language Data Queries with LLMs

Asking questions in plain language makes BI easier, but a model can invent numbers. We explain why turning the question into a validated report definition is safer.

2026-11-01 · 3 min read

How to detect anomalies in business data

Why hand-set thresholds go stale, why median and MAD beat mean and standard deviation, and why a rule should stay silent without enough history.

2026-10-01 · 6 min read
AI

Preparing ERP data for AI

Why letting a model query production directly is risky, and the pattern where AI fills in report definitions instead of writing SQL or doing arithmetic.

2026-09-22 · 7 min read