Today's AI Tip
← All posts

AI wrote "Not specified," then filled the field anyway.

· View on Instagram · View on Facebook

AI wrote "Not specified," then filled the field anyway.
Fictional call notes in, eight CRM fields out: Contact name, Job title, Company size, Budget, Decision maker, Competitors considered, Target go-live date and Next step.

Fictional call notes in, eight CRM fields out: Contact name, Job title, Company size, Budget, Decision maker, Competitors considered, Target go-live date and Next step.

Most of us would write this. I ran it on fictional notes. With real ones, remove names, account numbers and personal details first, and check the tool's data policy or your employer's approved tools.
Fill in these 8 CRM fields from my sales call notes: Contact name, Job title, Company size, Budget, Decision maker, Competitors considered, Target go-live date, Next step.

Tested in GPT-5.5 (OpenAI API), Oct 2026

Most of us would write this. I ran it on fictional notes. With real ones, remove names, account numbers and personal details first, and check the tool's data policy or your employer's approved tools.

It wrote "Not specified" in two fields, then filled them anyway. Dana also got a made-up job title, "Wholesale lead."

Real output · GPT-5.5 (OpenAI API) · Oct 2026

… - **Job title:** Runs wholesale side / Wholesale lead - **Company size:** Not specified; at least 2 delivery vans - **Budget:** Not specified; requested pricing for 2 vans …

It wrote "Not specified" in two fields, then filled them anyway. Dana also got a made-up job title, "Wholesale lead."

Each field was filled anyway. The notes only say Dana "runs the wholesale side," so "Wholesale lead" is made up. Vans aren't a company size, and a pricing request isn't a budget. A filter for empty Budget would miss it.

Each field was filled anyway

The notes only say Dana "runs the wholesale side," so "Wholesale lead" is made up. Vans aren't a company size, and a pricing request isn't a budget. A filter for empty Budget would miss it.

A field asks to be filled, so the model tends to reach for the closest fact. Anthropic's docs suggest telling it to use only your information and letting it say it doesn't know.
Fill in these 8 CRM fields from my sales call notes: Contact name, Job title, Company size, Budget, Decision maker, Competitors considered, Target go-live date, Next step. Use only what the notes say. If the notes don’t state a field, write “Not mentioned”. Don’t guess or infer.

Tested in GPT-5.5 (OpenAI API), Oct 2026

A field asks to be filled, so the model tends to reach for the closest fact. Anthropic's docs suggest telling it to use only your information and letting it say it doesn't know.

Source: Anthropic, Claude Docs: Reduce hallucinations

With the added line, Company size and Budget now say "Not mentioned," and Job title quotes the notes instead of inventing a title. Both runs did this.

Real output · GPT-5.5 (OpenAI API) · Oct 2026

… | Job title | Runs the wholesale side | | Company size | Not mentioned | | Budget | Not mentioned | …

With the added line, Company size and Budget now say "Not mentioned," and Job title quotes the notes instead of inventing a title. Both runs did this.

Still check every field. It still isn't clean CRM data: Job title is a description, Decision maker names no person, and the go-live date is "Before the Valentine's rush." Anthropic says these steps reduce made-up answers, not eliminate them.

Still check every field

It still isn't clean CRM data: Job title is a description, Decision maker names no person, and the go-live date is "Before the Valentine's rush." Anthropic says these steps reduce made-up answers, not eliminate them.

Try it: Add the line to your next call-notes prompt, then count the Not mentioned fields.

Source: Anthropic, Claude Docs: Reduce hallucinations

Sources and assumptions

Assumptions:

The short version

Follow @todaysaitipSave this post on Instagram

More posts