Predict equipment failures from the logs you already keep
Turns service records and fault logs into trigger rules and inspection schedules that catch failures before they stop the job.
When to use it: When breakdowns keep surprising you and the service history sitting in a folder could have warned you.
You are a maintenance-planning analyst for an Australian small business that runs its own equipment. Build a practical early-warning plan from existing records — no sensors or software purchases assumed.
<context>
[EQUIPMENT_LIST] — each machine/vehicle, age, and how hard it works (hours/week, loads)
[RECORDS_KEPT] — what you actually log: service dates, fault notes, hours, fuel, repairs
[BREAKDOWN_HISTORY] — recent failures with dates and what it cost each time (repair + downtime)
[DOWNTIME_COST] — rough cost per day when a key machine is out
</context>
Before planning, triage the fleet using [BREAKDOWN_HISTORY] and [DOWNTIME_COST]: which assets are prediction-worthy (expensive failures with warning patterns), which are fine on a fixed service schedule, and which are cheap enough to run to failure. Show the reasoning per asset.
<task>
1. For each prediction-worthy asset, list the leading indicators findable in [RECORDS_KEPT] — e.g. shortening gaps between the same fault, rising fluid top-ups, recurring operator notes.
2. Write trigger rules in if-then form: 'same fault twice in 30 days → inspection before next job'.
3. Set an inspection cadence plus a 5-minute operator daily check per asset, tailored to its failure history.
4. Where records are too thin to support a trigger, provide a minimal log template: fields, who records, when — designed to take under 2 minutes per entry.
5. Define a monthly review loop: did any failure occur without a trigger firing? Adjust rules accordingly.
6. State the criteria for when paid condition-monitoring or CMMS software would earn its cost (frequency × downtime cost), without recommending brands.
</task>
<output_format>
Triage table; per-asset watch-plan (indicator, trigger, action); log template; review loop; upgrade criteria. Under 700 words.
</output_format>
Rules: use only supplied history — no invented failure rates or lifespans. Anything safety-critical (electrical, pressure vessels, lifting gear, brakes) must go to a licensed tradesperson on schedule regardless of triggers, and WHS duties apply — confirm specifics with your state SafeWork body. en-AU spelling.
Copy the block above straight into Claude — anything in [BRACKETS] is yours to fill in.
Want it tuned to your business? Bring it to the free weekly call and we'll adapt it live.
Join the free callMore data analysis prompts
Decide Which Customer Questions Your Data Can Actually Answer
Triage your customer-behaviour questions against the data you really hold, and get spreadsheet-level recipes for the answerable ones.
Match the Right Simple Analysis to Your Business Data
Pick analysis techniques that fit your question, data shape and sample size — with spreadsheet steps and misread warnings.
Use Sales and Feedback Data to Back Your Best Offerings
Combine sales, margin and feedback evidence into a keep/grow/fix/kill call on each product or service.