AI Prompts for Supply-Chain Sustainability Analysis

Short answer: Use this workflow to organize supplier evidence, boundaries, activity data, factors, reporting periods, and open questions into a calculation-ready analysis plan. It must not produce an unsupported Scope 3 value or assurance claim.

This page is a practical prompt workflow. Treat every bracketed field as required input; do not ask an AI system to invent facts, citations, customer results, credentials, compliance conclusions, or financial outcomes.

When not to use this workflow

  • The organizational or operational boundary is unclear.
  • Supplier evidence, activity data, factors, or units are missing and the gap would change the result.
  • The output will be used as an assured disclosure or procurement decision without qualified review.

Variables to provide

Variables to provide
Variable What to provide Quality check
[Boundary and period] Entities, categories, suppliers, sites, exclusions, and reporting dates Boundary choices are documented.
[Activity data] Quantity, unit, source, supplier, and collection method Data provenance and completeness are recorded.
[Emission or impact factors] Factor name, version, geography, unit, and applicability Factors are selected by a qualified reviewer.
[Supplier evidence] Questionnaires, invoices, certificates, transport records, and uncertainty Evidence is matched to the correct supplier and period.
[Review questions] Known gaps, sensitivity checks, owner, and approval path The analysis produces questions instead of filling gaps with guesses.

Copy-ready prompt

You are an evidence-mapping assistant for supply-chain sustainability analysis. Boundary: [BOUNDARY]. Period: [PERIOD]. Activity data: [DATA WITH UNITS AND SOURCES]. Factors: [FACTORS WITH VERSION AND GEOGRAPHY]. Supplier evidence: [EVIDENCE]. Known gaps: [GAPS]. Qualified reviewer: [REVIEWER].

Return: (1) a calculation-ready input table, (2) factor and unit checks, (3) missing supplier evidence, (4) formulas to be independently reproduced, (5) sensitivity questions, and (6) a reviewer checklist. Do not invent activity data or factors, calculate an unsupported Scope 3 figure, or state compliance/assurance. Label estimates [ESTIMATE] and missing inputs [SOURCE NEEDED].

Example prompt failure

Illustrative example only — not a customer run and not evidence.

Calculate our supply-chain emissions and show that our Scope 3 program is compliant.

The illustrative prompt asks for a calculation and compliance conclusion without a boundary, units, factors, supplier evidence, or review method.

Why the controlled version is safer

The controlled version separates inputs, factors, formulas, gaps, and review decisions. It produces a reproducible plan rather than a fabricated number.

  1. Confirm the source set, version, audience, and owner.
  2. Run the prompt with the required fields; leave unknowns labelled rather than filling them.
  3. Compare each factual sentence with its source and record any judgement call.
  4. Obtain the named reviewer approval before publication or external use.

Proof-of-execution record

Empty proof template — no execution claim. Complete this section only after a real, permissioned run. Redact confidential customer, employee, supplier, personal, and commercially sensitive data.

Model family and version
[Record the actual model and version]
Run date
[YYYY-MM-DD]
Input excerpt
[Paste a short approved excerpt]
Observed output
[Paste a short approved excerpt or write “not recorded”]
Human reviewer
[Name or role]
Changes made
[Record edits and why]
Limitations
[Record failure cases, missing evidence, and unresolved questions]

Limitations and reviewer responsibility

This is not an emissions inventory, assurance statement, certification, or compliance opinion. Qualified sustainability and accounting reviewers must validate the method and source data.

Related workflow pages

Scroll to Top