LOMexcelLOMexcel
Back to The Shift Change
Template · Prompt Engineering

Claude Opus 4.7 Prompt Template.

A fill-in-the-brackets template used by mining engineers, economists, and analysts to get consistent, audit-ready answers from frontier models. Lifted from the Claude Opus 4.7 Playbook.

The template

You are a [senior process engineer / project economist / mining analyst / due diligence reviewer] with deep experience in [commodity / jurisdiction / project stage].

Context:
[Paste the relevant report sections, data tables, prior memos, or source material here.]

Task:
[Verb-led, scope-specified ask. e.g. "Benchmark the capital intensity of Project X against the 5 peer projects listed below..."]

Examples of the output shape:
<example>
[A prior deliverable that matches the format and depth you want]
</example>

Before finishing, audit your answer against the requirements above. Revise if anything falls short.

If anything in this brief is unclear, ask me before starting. Do not assume.

Operating rules for this task:
1. Do not invent facts. If something is not in the context provided, treat it as unknown.
2. Never fabricate numerical values. If a value is missing, return "not provided in source" and continue.
3. For every value cited, state the source: either the document and section, or the assumption.
4. Distinguish between values quoted directly from source documents and values derived through calculation. For derived values, show the inputs.
5. Declare every unit, currency, and basis conversion explicitly, including the conversion factor used.
6. Time-stamp every reference where time matters (commodity prices, regulatory citations, peer project disclosures, tax rates).
7. State a confidence level for any interpretive answer: High (source-backed), Medium (interpolated from analogous data), Low (generalized industry estimate).
8. Where the data provided is insufficient to support a conclusion, say so explicitly. Do not manufacture a conclusion to be helpful.
9. If any part of this brief is unclear before you start, ask. Do not assume.
10. Ask clarifying questions if required.

How to use it

  1. Replace every bracketed placeholder with your specific role, context, task, and an example of the output shape you want.
  2. Lead the task line with one of the 12 verbs below — the model responds to verbs more than adjectives.
  3. Read the prompt out loud. If a graduate engineer with no context couldn't deliver exactly what you want from it, name the missing piece and add it.

The 12 verbs that make the model sing

Start the Task line with one of these. Pair it with a clearly scoped object.

Draft
Review
Compare
Rank
Extract
Summarize
Reconcile
Benchmark
Validate
Forecast
Quantify
Synthesize

The 10 operating rules

These are the anti-hallucination rules baked into the prompt above. Lifted from The Hallucination Control Playbook. Keep them in every brief — they are what makes the output survive technical review.

  1. Do not invent facts. If something is not in the context provided, treat it as unknown.
  2. Never fabricate numerical values. If a value is missing, return "not provided in source" and continue.
  3. For every value cited, state the source: either the document and section, or the assumption.
  4. Distinguish between values quoted directly from source documents and values derived through calculation. For derived values, show the inputs.
  5. Declare every unit, currency, and basis conversion explicitly, including the conversion factor used.
  6. Time-stamp every reference where time matters (commodity prices, regulatory citations, peer project disclosures, tax rates).
  7. State a confidence level for any interpretive answer: High (source-backed), Medium (interpolated from analogous data), Low (generalized industry estimate).
  8. Where the data provided is insufficient to support a conclusion, say so explicitly. Do not manufacture a conclusion to be helpful.
  9. If any part of this brief is unclear before you start, ask. Do not assume.
  10. Ask clarifying questions if required.

The 5-second audit

Read your prompt out loud. Would a graduate engineer with no context know exactly what to deliver from this brief? If yes, send it. If no, name the missing piece.

Want the full context?

Read the Claude Opus 4.7 Playbook for Mining Professionals

The full article unpacks the shifts in how the latest models think, the moves that fix stale prompts, and worked examples from real mining workflows.

Open the full playbook
Strategic Engagement

Want a topic covered next?

Tell us what would actually help your team — we build The Shift Change around questions practitioners are really asking.

Book a ServiceExplore Services