Skip to main content

Editorial Methodology

This page describes how RivoCalc's content is produced, reviewed, and corrected. We believe transparency about our process is the foundation of your trust in us.

Who we are

I'm Luís Amaral, a software engineer, and RivoCalc launched in May 2026.

The short version: I needed to figure out how much paint a wall would take, and went looking for a calculator that used real American units and made sense for a U.S. project. What I found was mostly generic, metric-first tools — cubic meters, foreign codes, examples with products that aren't sold here. Something obvious was missing: a calculator hub built specifically for the U.S. market — feet and inches, U.S. codes, the units and vocabulary people here actually use.

I decided to build it. Solo, with the help of AI where it scales, and with the same engineering rigor I'd apply to a commercial product: deterministic tests for every formula, multi-model content review, official sources cited on every page, zero sign-ups, and zero dark patterns.

RivoCalc is independent. No investors, no sponsors, no brand affiliations. We don't sell products. We don't collect personal data. There's no sign-up required to use a calculator.

How we create content

RivoCalc's content is produced with the help of artificial intelligence and reviewed by a multi-model system. This approach lets us cover a large number of calculations across multiple language markets at a consistent level of quality.

Production process

  1. Technical specification. We define the math formula, the input parameters, and usage examples. Formulas are based on official standards, technical manuals, or basic engineering calculations.
  2. AI-assisted generation. We use language models (the Claude family from Anthropic) to generate explanatory text, examples, and FAQs. The AI receives the technical specification along with explicit rules on vocabulary, units, and local context.
  3. Multi-perspective review. Generated content is evaluated from four independent angles:
    • Technical accuracy — checks whether the formula is applied correctly.
    • SEO optimization — checks meta tags, heading structure, schema.org markup.
    • Local fit — checks whether vocabulary, units, currency, and regulations match the target market.
    • Editorial consistency — checks whether the text follows the internal standards described on this page.
  4. Independent-model cross-check. After the four-perspective review, a different language model runs a cross-check and flags inconsistencies.
  5. Deterministic calculation validation. For every calculator, we run test cases with known values. If the calculator doesn't return the expected values, publication is blocked.
  6. Publication. Only after every gate above has passed does the calculator go live.

Why this approach?

We rely on AI for a practical reason: it lets us scale content production at a pace a solo team could never match otherwise. We recognize AI can get things wrong — it can invent regulations, mix up units, or produce incorrect calculations. That's exactly why the multi-model review system exists.

Official sources we consult

Every calculator explicitly cites the official sources behind its calculations. In Portugal, our primary sources are:

Sources for our other markets (Brazil, Angola, Spain, Mexico, the United States, the United Kingdom) are being validated. This page is updated as each market goes live.

Verification and corrections

Even with the multi-model process, errors can slip through. If you find a calculation error, off-target vocabulary, or an outdated regulation, tell us through the contact form.

The form only asks for your name and email — we don't create accounts, we don't send newsletters, and your email is used solely to reply about what you reported.

We commit to acknowledging receipt, investigating, and fixing calculation errors within 30 business days, and to updating values that depend on annually published tables (taxes, regulations) as soon as they're released.

AI transparency

RivoCalc uses generative AI as part of its production process. We believe this is compatible with useful, trustworthy content as long as the process stays transparent and the output gets verified.

  • Explanatory text, examples, and FAQs are generated with the help of AI.
  • Math formulas are defined by a human editor, not by the AI.
  • Final review runs through multiple models to catch errors a single model might miss.
  • Every calculator explicitly identifies the official sources it's based on.

We don't hide our use of AI. Misleading users about where the content comes from would go against everything this project stands for.

Editorial independence

RivoCalc has no sponsors, takes no money from brands, and doesn't promote products in exchange for payment. Any brand names that appear in worked examples are common names in the relevant market, not paid placements.

Future monetization will come exclusively from contextual advertising (display ads through an ad network such as Google AdSense or an equivalent platform), clearly labeled as advertising and kept separate from editorial content.

Last updated: May 23, 2026.