WF08 / Work / Keep watch

Track meaningful competitor changes with evidence

Keep a dated baseline and report what changed, where it changed, and why it might matter.

THE WAY THROUGH

From your material to a useful result.

01
Pick specific pages and facts: plan limits, releases, integrations, or positioning.
02
Capture the baseline, checked date, and exact relevant facts. Keep event dates separate from publication dates.
03
Compare the next successful observation; separate substantive changes from page rearrangements.
04
Explain possible implications as hypotheses, and include unchanged or unavailable sources in the check log.

A FICTIONAL TASK TO PRACTICE ON

Here’s the job.

Fictional baseline: Acme plan page September 1 lists 5 projects for $20/month. Current supplied snapshot September 9 lists 8 projects for $20/month. Release blog is inaccessible.

What a careful result should contain

Observed change: included projects increased from 5 to 8; price remains $20/month. Source: supplied plan snapshots, September 1 and 9.
Inference: this may affect comparisons based on project limits.
Unknown: release blog could not be checked. No claim about other product changes.

This is an authored reference, not a captured Grok Bot, Instinct, or other product run.

Download sample prompt Download reference

BEFORE YOU RELY ON IT

Give the result a proper check.

Every change has a before value, after value, and source.
A failed fetch is not evidence of a removed feature.
An inference about strategy is labelled as an inference.

Try to break it

A page fails to load twice. Pass: retain the last observed value with its old date. Fail: announce that the plan was removed.

TAKE IT FOR A SPIN

Bring your own details.

Describe your task and paste the source material you want to use. This page prepares a prompt; your chosen AI tool does the work.

Your material and constraints

These details stay in this page until you copy them. They are not saved or sent to a model here.

Read the full starting instructions

Compare the supplied or authorized primary sources against a dated baseline. Return meaningful before/after changes with URLs and observation dates, separate event dates, unchanged pages, and failed checks. Label business implications as hypotheses. Do not infer deletion from unavailable pages. Propose a monitoring schedule only if the tool supports persistence and scheduling.