Stage 4 — Technical Specification

Why this stage matters more than the analysis itself

Two ideas stack here:

1. Spec-driven design. The ability to specify analytical work precisely is more valuable than the ability to execute it. Execution scales through teams, tools, and AI. Specification requires domain expertise that can't be delegated. This stage asks you to define the work, then judge the output.
2. You draft first, the LLM reviews, then you iterate together. You write the spec's first draft from the project materials and your workbook; then you condition an LLM on the same materials to review it, and the two of you revise until it's a document you'd sign.

The spec's anatomy

Part A — Model specification items 1–7

Enough detail to reconstruct your template and populated model from the document alone:

1. Scope & objective: company, fiscal period, reporting standard, currency, audience
2. Model architecture: tabs, color coding, input/calc/output separation
3. Data inputs: every data point with its numeric value from your Stage 3 workbook
4. Named range conventions: the full map of BAL_*, INC_*, CASH_*, RATIO_* to values
5. Derived inputs: averages, start-of-year figures, after-tax operating income, with explicit formulas
6. Ratio definitions: all 25+ ratios across the six categories, each with formula in named-range notation, expected unit, and a one-line interpretation guide
7. Validation rules: internal consistency checks (balance sheet balances, Du Pont ROE = direct ROE, etc.)

Part B — Analysis specification items 8–11

8. Analysis requirements: per category (what to interpret, against what benchmarks, which cross-category connections to examine)
9. Du Pont decomposition: specific ROE-breakdown instructions
10. Strategic recommendations: how many (3–5), what evidence standard, how actionable
11. Output format: exact section order, length targets, tone, audience

Cite numerically. "Total assets" is not a spec. BAL_assets_total_2025 = 394,328 (VND billions) is.

The human-in-the-loop (HIL) requirement

A single-shot LLM dump is below standard. You must show at least one documented iteration: you found a gap in the draft, understood why your prompt or spec caused it, and fixed it. Pick one form of evidence:

Specificity is the standard. "I asked it to expand the section" earns nothing. "Part A.4 listed BAL_assets_total without a year suffix, so the Stage 5 LLM wouldn't know which year to pull. I added the year-suffix convention and re-ran" earns full credit.

How to run the draft, the review, and the iteration

1. Draft first, yourself: fill every section of the spec template, keep the YAML frontmatter, use named-range notation throughout, and pull real numbers from your workbook into the Data Inputs table.
2. Then give the LLM: the Stage 4 brief (raw GitHub URL), the spec template (raw URL), your Stage 1 template (.xlsx upload), your Stage 3 populated workbook (.xlsx upload), and your draft. Ask it to review the draft for gaps before changing anything.
3. Good opening move: have it list the 3–4 assumptions it would need that your draft doesn't state (standard, fiscal year, audience).
4. Iterate together: expand sparse sections, tighten verbose ones, verify formulas tie to your template.
5. If a section keeps coming out weak, fix the prompt, not the output. Hand-editing hides the problem; re-prompting fixes the system that produces the document.

Submission checklist

• Spec at capabilities/performance-ratios/spec.md (a spec already committed under the older docs/specs/ still counts), YAML frontmatter intact
• Part A items 1–7 complete: every input value present numerically
• All 25+ ratios specified in named-range notation with units and interpretation guides
• Part B items 8–11 complete: benchmarks, Du Pont instructions, recommendation criteria, output format
• Validation rules included (balance check, Du Pont vs direct ROE)
• Prompt log updated with the review and iteration sessions
• HIL evidence committed: before/after note, round-2 prompt, or annotated diff
• Self-test passed: a fresh LLM given only the spec produces something substantially correct

Rubric

The headings below are what the work is read for. Weights and due dates are in your course schedule.

Check yourself