Use when the user asks how operations is doing, hands over numbers for a read, or wants operational KPIs defined with formulas, targets, and owners.
The English summary is being prepared. Showing the original description.
Run score Not tested
See how to installReview the instructions the agent will receive before you install.
Use this when the user asks how operations is doing, hands over numbers for a read, or wants KPIs and targets defined.
The exports or connected numbers covering this period and the last, the metric definitions with targets, and the currency.
No metric definitions means you propose them from the columns you have and mark every target UNKNOWN. One source only means you build the scorecard for that one and name what is missing.
Say out loud the days you are scoring and the days you compare against. Never compare a partial period to a full one.
Name which sources you have and which days they cover. A source with no numbers gets named, never dropped quietly.
Name, formula, source column, target, owner, and type — INPUT (controllable, leading) or OUTPUT (lagging result). The owner watches their metrics and knows normal variance from exception.
Ops metrics that recur: error and rework rate, cycle time, forecast accuracy, utilization, SLA compliance, invoice accuracy, milestone attainment.
Money rounds to whole units, rates to one decimal.
Quarterly, audit every metric: the owner confirms the definition, source, and target still hold; dead metrics get retired; and the read notes who certifies the accuracy.
Score every metric against its target with red/yellow/green (R/Y/G), then rank the movers — biggest miss first, biggest gain next.
Decompose each move with the columns you have and tie it to something visible: a process that changed, a vendor that slipped, a hire that landed. When the numbers cannot explain the move, say so in one line and name the one thing you would need.
Fewer than about 30 observations in the period gets a line saying the move sits inside the noise. Monthly, roll the weeks into one read against plan.
No claim without a number behind it. No recommendation to spend or cut without the metric that justifies it — and even then, the plan proposes, the approver disposes. Label each line FACT, INFERENCE, or UNKNOWN.
Save the scorecard dated and write the period's figures to the metrics history.
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Use when a support account wobbles or a quarterly business review looms: read the health signals, run the success plan, and prep the review from evidence.
The English summary is being prepared. Showing the original description.
Reconcile accounts by comparing GL balances to subledgers, bank statements, or third-party data. Use when performing bank reconciliations, GL-to-subledger recs, intercompany reconciliations, or identifying and categorizing reconciling items.
The English summary is being prepared. Showing the original description.
Review open receivables and draft factual, staged payment follow-ups without inventing status or contacting a customer.
The English summary is being prepared. Showing the original description.
Write ad variants that each test one idea, within platform limits and supported claims.
The English summary is being prepared. Showing the original description.
Use on the first conversation with Alex, or whenever their memory has no product preferences yet: learn what the user is building and who for, where specs, roadmap and numbers live, who decides dates and scope, and get them to a first real product deliverable.
The English summary is being prepared. Showing the original description.
Use when a strategic alliance needs joint selling governance: operating model, joint targeting, steering prep, and milestone accountability.
The English summary is being prepared. Showing the original description.