Prompt Engineering

Missing Data in AI Extraction — Null, Unknown, or Skip

The most consequential setting in any extraction prompt: what the model does when the field isn't in the text. Four behaviors, and when each is right.

Overview

Every extraction eventually meets a text that doesn't contain the field — and what happens next is the difference between a reliable pipeline and silent garbage. Four contracts exist: Leave Empty (visible gap, human-friendly), Return Null (stable keys, pipeline-friendly), Return Unknown (loud gap a reviewer can't miss), and Skip Field (lean output, consumers must check key existence). This resource loads a sparse-by-nature lead-form extraction set to Return Unknown with strict ambiguity — the configuration where missing data is most visible — so you can see the contract language and swap behaviors to compare.

Workflow

Match the behavior to the consumer
Code parsing the output wants Return Null; a human scanning a sheet wants Leave Empty or Return Unknown; Skip Field needs existence-checking consumers.
Swap behaviors and diff the prompt
Load this setup, change Missing Data, and watch the MISSING DATA block rewrite itself — the contract is two lines, and they do all the work.
Keep the never-invent rule
Whatever behavior you choose, the constant is "never invent or guess a value for a missing field" — the line every behavior shares.

Why This Works

Naming the behavior in the prompt removes the model's single biggest improvisation point
"Unknown" exploits human attention: a literal string in a data column gets investigated
The never-invent rule survives every behavior choice — absence stays absence

Best for

Sparse sources — forms, short messages, partial documents
Teams debugging "where did this value come from?" incidents
Pipelines whose consumers disagree about null vs missing keys

Not for

Ambiguity handling — that's the neighboring policy; missing means absent, ambiguous means unclear
Format-level null semantics (JSON null vs empty XML element) — the engine adapts those automatically

Use cases

Choosing the right missing-data behavior before a pipeline ships
Making data gaps visible to human reviewers with "unknown"
Stopping models from inventing values for absent fields

Customize This Resource

Opens this setup in Extraction Prompt Generator. Generate to get the full extraction prompt — then adjust the fields, missing-data behavior, and ambiguity policy.

Open in Extraction Prompt Generator

Prompt Template

TASK
Extract lead details from the submitted form text in the input for our CRM.

SOURCE
The input is unstructured free text.
Reading guidance: Read the entire text before extracting — relevant values may appear anywhere, in any order.

FIELDS TO EXTRACT
- lead_name (required): Lead's full name
- email (required): Lead's email address
- company (optional): Lead's company
- team_size (optional): Number of people on their team
- use_case (required): What they want to use the product for
- timeline (optional): When they plan to start

EXTRACTION RULES
- lead_name: The person's full name as written — do not expand initials or invent missing parts.
- email: A valid email address only — not the surrounding text.
- company: The organization's name as written, without surrounding commentary.
- team_size: Extract as a digit, not words.
- Extract values from the source text only — do not use outside knowledge to fill fields.
- Do not summarize or interpret the document — return only the fields listed above.

MISSING DATA
- If a field is not found in the source, return the literal string "unknown".
- Use "unknown" only for genuinely absent information — never as a shortcut for skimming the text.
- Never invent or guess a value for a missing field.

AMBIGUITY POLICY
- Extract only information explicitly stated in the source text — do not infer values.
- If a value is implied but not stated, treat the field as missing.

OUTPUT FORMAT
Return the extracted data as a single valid JSON object using the field names below.

EXAMPLE OF A VALID EXTRACTION
{
  "lead_name": "Jane Smith",
  "email": "user@example.com",
  "company": "Acme Corp",
  "team_size": 3,
  "use_case": "Automate weekly reporting",
  "timeline": "Q3 2026"
}

OUTPUT RULES
- Return only the JSON object — no text before or after it.
- Do not wrap the output in markdown code fences.
- Use the field names exactly as defined — no renaming, no extra fields.

Related Resources

Explore more resources that work well with this one.