Ad results and the next test questions
Ad dashboard has twelve metrics. The owner asks one question: what did we get?
Tested Claude Opus 5.5, medium effort · 15 Nov 2026 · on the practice files
Export ad results
Use ad code, spend, clicks, leads and same date range. Keep missing metrics blank.
Privacy Remove personal names, phone numbers, email IDs, photos and customer identifiers. Use approved business facts, anonymous codes or aggregate data.
Whenever I send the next brief, use this format. Period: [Period] Review rule: [Review rule] I'm attaching ad-results.xlsx. A. Calculate CPC and CPL if denominator positive; sum spend and known leads. B. List above-threshold, zero-lead and missing rows; compare complete-row CPL only. C. Three suggested tests, not automatic stop/scale decisions. Use only supplied facts. No invented statistics, awards, testimonials, customer names, No. 1, guaranteed, health, finance or legal claims. Do not copy competitor copy or use real people's names or photos. Write regional-language versions only if I request them in a box. A person checks before publishing or deciding.
Set it up once. Save the approved brand facts, tone and format, not customer details. Pick your tool at the top to see how.
What is that?
A Project is a folder in ChatGPT that keeps your instructions and files for every chat inside it. It's on the free plan too. Checked 14 Nov 2026.
What is that?
A Project in Claude is a workspace with its own instructions and files that every chat inside it uses. Checked 14 Nov 2026.
What is that?
A Gem is a custom Gemini that loads your instructions before every chat. Free on every plan; you create it on a computer. Checked 14 Nov 2026.
What is that?
Signed in with a work account, Microsoft's Copilot Chat applies enterprise data protection: your prompts aren't used to train its models. Checked 14 Nov 2026.
After that, each time: send the new brief and current approved facts; check the result.
First time? Try it in a normal chat: paste and send.
Which model? Use your tool's strongest model with thinking turned on.
In your AI tool: attach the files with the + button, paste, send.
Keep actual company records in your own workbook; ask AI for the local method using headings and rules only.
Excel A:D ad code, spend, clicks, leads. Rule [Review rule]. Give formulas for CPC and CPL only with positive denominators, zero/missing flags and above-threshold CPL, sum known spend and leads. Keep suggestions separate from data; no automatic ad spend change. Tell me exactly where to paste formulas or set up the local steps. Use fictional examples only; do not ask for actual company records.
Run locally, verify the figures and flags against your source records and ask the responsible person to approve before acting.
- A2₹600 CPL. ₹6,000 / 10.
- A3Zero leads. No CPL; review.
- A4Leads missing. Hold CPL.
Then send this: Recalculate rates and total; check zero/missing denominators.
Divides by zero
Reply: "Not applicable."
Stops ad automatically
Reply: "Suggested tests only."
Invents cause
Reply: "Ask what changed."
Sir ne bola urgent. Ab bolo: ho gaya.
Did it work?
If your whole team does this, we'll set it up for all of them in one session.