Intelligence

A projection is not a promise.

Visits, conversions and revenue are projected from observed trend and seasonality, and every projection is shown as a range rather than a single figure. The output describes what the current trend implies, nothing more. When the actual result leaves the range, the brief says so and the model is refitted.

Start free See how it works

In practice

Demo data

Are we going to reach the revenue number this month?

On the current trend, month-end revenue projects to roughly €96,000, in a range of €88,000 to €104,000, against a target of €100,000. The projection assumes the paid campaign ending on the 24th is not renewed.

How it helps

What Forecasts gives you

The range is the answer

Every projection carries an interval and the history it was fitted on. A month-end number quoted without its range is the part of forecasting that gets people into trouble.

Forecasts are scored afterwards

Past projections stay visible beside what actually happened, so you can see where the model runs hot or cold. A forecast nobody checks is just a number in a confident font.

Known events beat the curve

Business-defined events — a sale, a campaign end date, an invoicing cycle — are inputs rather than surprises. Where a period has no comparable history, the projection is labelled weak.

Evidence

Nothing here asks you to take its word for it.

Every explanation resolves to the metric, segment and period it used, alongside the alternatives it ruled out and the limits of what it can establish. The analytics engine computes the numbers; the AI explains what came back.

How evidence works

Demo data

Evidence

Mobile pricing conversion fell 27%.

Why Reveliqo says that

Traffic volume remained within its normal range. The decline is concentrated on iPhone Safari and begins 18 minutes after deployment #842.

Before deployment: 4.1%
After deployment: 3.0%
Visits analysed: 3,481
Difference: −26.8%

Metric: conversion_rate
Segment: device_class = mobile · browser_family = Safari · page = /pricing
Period: Yesterday 14:00 – today 09:00, compared with the preceding seven days

Strong correlation with deployment #842. Causation has not been proven — a controlled comparison would be needed for that.

Intelligence

The rest of the intelligence layer

Briefings

Scheduled daily, weekly, monthly, campaign and executive briefs built on the product's own metric definitions.

Anomaly detection

Watches people, revenue, performance, traffic quality and funnels against context-aware baselines.

Root cause

Decomposition that names the segment carrying the change, not just the headline.

Opportunities

Segments, pages and sources performing unusually well, and where more would plausibly pay.

Forecasts

Projections the metrics layer computes from observed trend, with the range, the assumptions and the limits stated in the explanation.

Explain this

Any figure, chart point, funnel step or segment can be opened and questioned.

Compare periods

Answers whether a change is real movement or a different mix of traffic.

Business questions

A library of the questions businesses actually ask, with the analysis behind each.

Connect a site today. Read tomorrow's brief instead of building it.

Connect a site and the first brief arrives with the day's changes already explained — traffic separated from bots, conversions attached to revenue, and the evidence behind every sentence one click away.

Start free See how it works

Real people separated from bots Every answer shows its evidence Reveliqo runs on Reveliqo