More in Large datasets & analysis.
Find why an electric bill nearly doubled from 12 years of meter readings with Gemini
WorkedEvidence: Screenshots or logsPosted Last checked
Gemini charted 750,000 of Peter Rukavina's meter readings and pinpointed September 2023, when a basement dehumidifier went in.
How to use this
- Tap Copy prompt.
- Open Gemini.
- Paste it into the message box.
- Send it, then read the answer before acting on it.
New to this? What's a prompt?
A prompt is the message you send to the AI tool. Copy the one on this page, put your own details where it asks, and read the answer before you act on it.
Prompt
Recreated prompt
The source didn't share its exact prompt, so we wrote one from what it describes. The result shown is the source's, not ours.
The person didn't share their exact words, so we wrote this from what they described. We haven't tested it, and they didn't use this exact version.
This is a CSV of my electric meter readings since 2014. The datestamp column has the date and time, and the reading column has the meter reading (divide by 100 to get kWh). Chart my daily usage over the years, show how usage changes by time of day, and tell me when and how my usage increased.
Try this in:
Sends the Recreated prompt shown above. ChatGPT and Grok open with it filled in, and ChatGPT may send it straight away. Gemini and Claude open empty, so we copy the prompt for you to paste. Every button also copies it.
Opens in a new tab. We don't see what you send.
These links are only a shortcut. We're not affiliated with OpenAI, Google, Anthropic or xAI, and your results may not match the source.
Optional stronger version
Our rewrite with extra checks. The poster didn't test it.
Before you start, ask me 1–3 short questions about the details below and wait for my answers. Once I've answered, confirm the plan in one line and run the whole task start to finish. Goal: Find when and why my household electricity use went up, using my own meter or utility data. Questions to ask me first: - What data do you have (meter readings, utility interval CSV), and what period does it cover? - What units are the readings in? - Did anything change at home (appliances, people, heating) that you know of? Inputs (fill in or confirm): - Data file: [CSV] - Column meanings and units: [COLUMNS / UNITS] - Electricity price: [PRICE PER KWH] - Known changes at home: [CHANGES] Rules: - Show daily usage over time and by hour of day as charts. - Find any lasting step change and give its start date. - List likely causes that fit the timing and pattern, labeled as guesses for me to check. - Estimate monthly cost of the extra usage at my price, showing the math. Checkpoint: Show me the first chart so I can confirm you read the units correctly. If you get stuck: If data is missing or the readings look wrong, say which dates. Verify before you finish: Recheck the step-change date and cost math. Output: Charts, the date of any step change, possible causes and a cost estimate. Done when: I know when usage rose and have likely causes to check.
AI tool
Outcome
Peter Rukavina's January electric bill had nearly doubled, from $95.78 in January 2021 to $180.95 in January 2026. For 12 years Rukavina had archived home electricity readings, over 750,000 of them, and exported a CSV of the meter readings to Gemini with a request for charts of usage over time. Gemini charted the data and found a dramatic and permanent step up in daily usage beginning the first week of September 2023. Rukavina checked and found that a dehumidifier had been installed in the basement that same week. A follow-up with Gemini suggested that running it 24/7 could use as much as 11 kWh per day, which Rukavina works out to about $60 a month at 17.3 cents/kWh.
Evidence: Screenshots or logsThe source shows screenshots, a transcript or the AI's output.
Source
- Posted
- by Peter Rukavina (ruk.ca)
- Last checked
- Method:
- How we verify
https://ruk.ca/content/im-electricity-private-detective
Context: Rukavina found the dehumidifier receipt; Gemini only spotted the date of the change. The dehumidifier explains a significant chunk of the increase, not all of it.
More in Large datasets & analysis
Turn X bookmarks and likes into a searchable knowledge base
The poster scraped all their X bookmarks and likes with Claude in Chrome and other tools and built a searchable RAG chatbot.
WorkedClaude in Chrome +1Evidence: Described by posterView CaseAnalyze every entry of a huge JSONL file with Claude Code subagents
Claude Code defined a schema and ran hundreds of subagents over about 45 minutes so every entry in a huge JSONL file was analyzed.
WorkedClaude CodeEvidence: Described by posterView CaseCompare Claude Code, Codex and Gemini CLI on a 97k-message chat dataset
The poster gave the same 97k-message chat dataset to Claude Code, Codex and Gemini CLI and published an evaluation table.
WorkedClaude Code +2Evidence: Described by posterView CaseReproduce an economics paper's findings from replication data with Claude
From only the paper and its replication archive, Claude converted STATA code to Python and reproduced an economics paper's findings.
WorkedClaude (Sonnet 4.5)Evidence: Article or interviewView Case
Similar cases
Check an electric bill against other rate plans with ChatGPT
ChatGPT read Craig A. Linton's Con Edison usage data and suggested a rate plan switch Linton says saves about $1,100 a year.
WorkedChatGPTEvidence: Described by posterBeginner-friendlyView CaseLower an electricity bill with ChatGPT's energy-saving tips
Tom's Guide's Elton Jones told ChatGPT they paid a $230+ monthly energy bill and asked for tips to lower it.
WorkedChatGPTEvidence: Article or interviewBeginner-friendlyView Case