Competitor Monitoring Prompts to Create a Weekly Digest

Every list of competitor monitoring prompts is slightly mis-titled, including this one. A model has no memory of what a competitor’s page said last month. It cannot notice a change. Noticing takes two looks separated by time, and a chat window holds one.

What a model does very well is the part that comes after. Take a pile of things that happened, work out which three matter, and write the short version. That is the job people find hardest. It means saying eleven of the fourteen items are not worth anybody’s attention, and almost nobody wants to be the person who cut something.

So the prompt starts where the collecting stops

Read the prompts below as the second half of a process. The first half is somebody, or something, watching the sources. If that first half is a person checking pages on a Friday, the digest will be as complete as their Friday was. The prompt cannot make up for a period nobody looked at, and it will not tell you the collection was partial.

The first writes the digest. The second is for readers who do not follow the category and need the consequence spelled out. The third points at your collection rather than at your readers. It is the one that finds the week you thought was quiet and was actually unchecked. Where a period genuinely carried one big thing, it belongs in an executive summary instead, on its own, rather than as item one of nine.

Two of these three are obvious. The middle one is why most digests slowly lose their readers.

Paste the raw items rather than your notes on them. A digest written from summaries is a summary of summaries. Every judgement you made while collecting has quietly become fact by the time it reaches a reader who cannot see the original.

Date order is the default because it takes no judgement, and it reliably puts the item that mattered underneath four that did not. The instruction to rank by what changes a decision is the most valuable line in the whole prompt. It is worth being specific about what it means.

An item changes a decision when somebody would do something differently having read it. A price move that changes what a rep should concede. A launch that makes a battlecard section wrong. A hiring pattern suggesting a competitor is entering a segment you were about to commit to. An item does not change a decision because it is recent, because it concerns your largest competitor, or because it took effort to find. The last one is the hardest to let go of.

Reporting a quiet period as a quiet period

The instinct in a week where nothing happened is to find something. Resist it for a practical reason rather than a principled one. A reader who learns that every edition contains three items, whatever the week, rightly concludes that the count is fixed and the ranking is for show. After that, the edition where something genuinely happened arrives looking exactly like the four before it.

That last sentence is what earns the edition. Absence is a signal too, and it is the one a summariser will never raise unless asked, because nothing in the collection stands for it. Ranking by decision also means the quiet categories drop out, and competitive signals are easiest to lose in exactly the weeks nothing loud happened.

Everything above assumes a collection exists. In practice that is the half that decays, and you cannot see it decaying from inside the digest. A period nobody checked produces a short, calm edition that reads exactly like a genuinely quiet week.

It happens the ordinary way. Somebody owns the Friday check, then a quarter-end lands, then they are on holiday, then the habit is gone and nobody announces it. Two months later the digest is still going out, still well written, and no longer connected to what the competitors are doing. The third prompt above exists because reading the digest will never tell you that.

Being late here rarely costs you one deal in a dramatic way. It costs you the thing the digest was for. The team stops treating it as where they find out, and starts finding out from a buyer instead. That is the same information arriving after the decision rather than before it.

One source repays a deeper pass than a digest gives it. A competitor’s release notes reward being read as a period rather than item by item, and analysing a whole changelog answers a question a week of collection never can: whether what they ship has changed.

The watching is what a platform does rather than what a prompt does. Flares tracks competitor pricing, product changes, launches and hiring continuously. The period arrives already collected, so the digest prompt works from a complete week rather than from whoever remembered to look.

Where nobody sits down at all, and the edition simply arrives on a Friday, a scheduled agent brief has to report what it read before it reports what it found. A quiet week and an input that stopped arriving produce the same edition, and only one of them is news.

The ranking still needs you. Which of this week’s changes deserves your team’s attention depends on which deals are open and what you are about to ship. No amount of collecting decides that. The prompts above are for that half, and they get better as the half beneath them gets more complete.