Watching for changes
A watch is only as good as its judgment about what counts as a change. A page that pings you every time its visitor counter ticks is worse than no watch at all. This is how an automation decides a change is worth telling you about — from character-exact for prices, to content-only for news, to meaning-only for prose that gets reworded but rarely says anything new.
The noise problem
Most of what changes on a page is not what you care about.
Open almost any web page twice and something will be different: a “last updated” timestamp, a view count, an ad, the order of a list, a rotating testimonial. A watch that fired on all of that would page you constantly and you would stop trusting it within a day. The whole craft of a good watch is telling the change you asked about apart from the churn around it.
How picky the watch is
One setting, three levels, chosen to match what you are watching.
You describe what you’re watching and the assistant picks the right level; you can always say “only tell me about real changes” to move it up. All three are deterministic — deciding whether something changed never itself costs a model call, so a watch stays free to run continuously.
| Level | Fires on | Ignores | Best for |
|---|---|---|---|
| Any change | Any difference at all, down to one character | Nothing | Prices, stock levels, anything where a digit is the point |
| Meaningful change | Real content changes | Counters, timestamps, re-ordering | News, blogs, docs, changelogs |
| Semantic change | A change in meaning | Pure rewording that says the same thing | Wordy prose that gets rephrased often |
Any change
Character-exact. The right default when every digit matters.
At this level the watch fires on the smallest possible difference. That is exactly what you want for a price, an inventory count, or a rate: if the number goes from 199 to 198 you want to know, and there is no such thing as an unimportant change. It is the most sensitive setting and the correct one whenever the thing you’re watching is a number.
Meaningful change
Content-aware. Blind to the churn that surrounds real edits.
This level compares the actual content of a page while deliberately ignoring the things that change on their own. It is “digit-blind” — a rotating view count or a ticking timestamp does not move it — and it is immune to items being re-ordered. A genuinely new sentence, a changed paragraph, an added section: those fire. A counter going up: silent.
Semantic change
Meaning-aware. Blind even to rewording that says the same thing.
The most forgiving level compares the meaning of the text rather than its wording. If a paragraph is rephrased but conveys the same thing, it stays quiet; if the substance actually shifts, it fires. This is the right choice for prose that gets frequently reworded — marketing copy, a frequently-edited description — where you only care when the message genuinely changes, not when someone swapped a few words.
Only new items
For feeds and lists, track what you have already seen and fire only on the genuinely new.
A page or feed of items — postings, articles, releases — is best watched by identity, not by difference. This mode remembers every item it has already shown you and fires only on entries it has never seen before. Re-ordering the list, re-publishing an old item, or bumping a timestamp does nothing. When it fires, your steps get the exact list of new items and a count of how many, so “email me the new postings” delivers each one once.
Watching a number move
Sometimes the alert you want is not any change, but a trend.
“Tell me when it changes” and “tell me when it drops below its weekly average” are different asks. For the second, the automation records the number to a named series on every check and compares the latest value against the history — the previous value, the seven-day average, the percentage change. That turns a watch into a trend alert: fire on a 10% drop, on a new low, on three rising checks in a row. The recorded history also draws a small line chart on the automation’s board. This builds on the record capability described in What an automation can do.
The silent first check
A watch never fires on its very first look.
The first time a watch runs, it has nothing to compare against — so it quietly records the current state as the baseline and delivers nothing. That’s deliberate: without it, every new watch would fire once on creation with a meaningless “this exists” alert. From the second check onward, it compares against what it saw and only speaks up on a real change.