> ## Documentation Index
> Fetch the complete documentation index at: https://docs.attensira.com/llms.txt
> Use this file to discover all available pages before exploring further.

# What the agent notices on its own

> The hourly rules that watch your readings and file what changed — without a person and without a model asking a question.

## What a finding is

Every hour, a pass reads your workspace's recent readings and checks them against five fixed rules. There is no model in this pass and no prompt being asked — it is arithmetic over the same numbers your dashboard shows, which is what makes it fast, cheap, and consistent: the same window always produces the same findings.

## The five rules

<AccordionGroup>
  <Accordion title="A page of yours stopped being cited" icon="link-slash">
    A page on your domain was cited on at least three of the last seven days, and on none of the last three — with at least one successful read on each of those three days, so a run of scraper failures never looks like a loss.
  </Accordion>

  <Accordion title="A competitor was newly named" icon="user-plus">
    A rival is named on a prompt where it was not named before: named on at least two of the last three days, and never named across the seven days before that — counted only over days you actually read that prompt on that engine.
  </Accordion>

  <Accordion title="You dropped out of every answer on an engine" icon="triangle-exclamation">
    A page of yours was cited somewhere in the prior seven days, and in none of the last three, on one engine — with every one of those three days carrying a successful read. This is the whole site going quiet on an engine, not one page slipping.
  </Accordion>

  <Accordion title="A new domain entered an engine's top ten" icon="ranking-star">
    A domain that was not among an engine's top ten cited sources is now in it. This only fires once that engine has a full prior week to compare against — an engine you started sampling this week does not report its entire source list as new.
  </Accordion>

  <Accordion title="One of your pages changed" icon="pen">
    A page on your own domain changed since the last pass. Not a loss, and never filed as one — it is surfaced because it is usually the answer the other four rules are asking for.
  </Accordion>
</AccordionGroup>

## A day that could not be read never counts as a loss

This is the rule everything above is arranged around. Every finding that claims an absence — a citation stopped, a page dropped out — first checks that every day it is claiming silence from carried at least one successful read.

A day with three failed reads and a day with no reading at all look identical to this pass on purpose: both are silence, and silence is never evidence of you losing something.

## One row per deciding source, not per prompt

A source that decided seven prompts is one problem, not seven. Findings are grouped by the source that caused them before they reach your [Inbox](/agent/inbox), so the row reads **"affects 7 prompts"** and grows in place instead of filing seven near-identical rows.

The Inbox stays worth opening: **at most three open rows** from this pass at a time. A fourth finding bumps the closest existing row rather than raising a new one.

## What happens when a row is raised

A run may start under your workspace's [approval mode](/agent/approval) — the same setting that governs everything else the agent does on its own. What a finding is allowed to do next, from opening the row for you to reading further to proposing a fix, follows that setting exactly as a chat or automation would.

## This replaces the daily check-in

Every workspace started with a seeded **Daily check-in** automation whose job was to read the numbers each morning and say what had changed. Once these hourly rules are live for a project, that automation is paused — the two are never left to run together, because a customer should never see the same loss reported twice, phrased two different ways, from two different sources.

<Note>
  Findings are read-only in what they claim: a rule never invents a percentage from a single day, and a claim about a page always comes from a page the pass actually read.
</Note>