Kumu / Corporate Finance / Stage 5

Stage 5 — Analysis, Evaluation & Repo Polish

Weight: 25% Deliverable: the polished repo URL itself

The capstone. Feed your spec — and nothing else — to an LLM. Verify its numbers by hand. Correct, annotate, and finish with the executive judgment only a human can supply. The future of finance work isn't "do the analysis" or "let AI do it" — it's specify, evaluate, and take responsibility.

The three moves

  1. Execute. Paste your Stage 4 spec into a fresh LLM session with zero extra context — no "please also consider…". Save the complete raw output. This is your spec's exam.
  2. Verify & evaluate. Recompute ≥5 ratios by hand from your Stage 3 financials, compare to the LLM's values, and flag every discrepancy with a cause. Then edit the analysis: correct errors, annotate weak reasoning, add your voice.
  3. Polish. Make the repo a portfolio artifact — READMEs everywhere, clean history, license, description. Budget 2–3 hours; don't leave it for the night before.

The verification table — your defense against confident nonsense

Three sources of ratio values exist by now: the template's auto-computed values, the LLM's stated values, and your manual recomputation. The graded table compares manual vs LLM. Pick ratios across categories, and deliberately choose the ones an LLM is most likely to fumble: anything involving averages, start-of-year values, or unit conversions.

RatioFormula (named ranges)Manual (show arithmetic)LLMMatch?Note
ROAINC_net_income / avg(BAL_assets_total)12,500 / ((100,000+96,000)/2) = 12.76%12.76%Correct averaging
DSO(BAL_receivables / INC_revenue) × 365(8,000/80,000) × 365 = 36.5 d36.0 dLLM used a 360-day year without disclosing
Inventory turnoverINC_cogs / avg(BAL_inventory)60,000 / ((15,000+13,000)/2) = 4.29×4.62×LLM used end-of-year inventory, not the average

Discrepancies are the good rows

A mismatch with a one-line causal note earns full credit — it proves you caught the machine. An unflagged discrepancy is the failure mode. (And every mismatch is retrospective gold: did your spec state the day-count convention? The averaging rule?)

The six deliverables

#FileWhere
1Raw LLM output (unedited)deliverables/…-llm-raw.md
2Manual verification table (≥5 ratios)analysis/validation/…-stage5-verification.md
3Evaluated final analysisdeliverables/…-final-analysis.md
4Spec retrospective (template-based)deliverables/…-spec-retrospective.md
5Updated prompt logdeliverables/prompt-log.md
6(Optional) Stage 2 feedback responsedocs/decisions/…-stage2-feedback-response.md

Produce them in order 1 → 2 → 3 → 4 → 5: raw output first, verification second — so you confront discrepancies before writing the final analysis, not after.

The final analysis must contain

  1. Company & data summary — verified context, assumptions, accounting-standard notes
  2. Ratio results & interpretation — all six categories, with your corrections to the LLM
  3. Du Pont analysis — is the LLM's decomposition story sound?
  4. Strategic recommendations — 3–5, each citing specific ratio values; note what nuance the LLM missed
  5. LLM evaluation — what it executed correctly; where it deviated, hallucinated, or oversimplified; spec-gap errors vs model-limitation errors
  6. Executive justification — the investment/strategic thesis in your voice. The "so what?" no machine supplies.

The spec retrospective — honest beats flattering

Using the course template: a section-by-section verdict (Clear / Vague / Missing) tied to symptoms in the output, your top three gaps with evidence, three revisions you'd make, an effectiveness rating, and one process suggestion. "My spec was perfect" scores worse than "Part B.9 said 'recommend strategic actions' without an evidence standard, so the LLM produced generic advice — I'd require each recommendation to cite two ratio values."

Feedback incorporation & repo polish

Submission checklist

Rubric

Criterion%Strong work looks like
Analytical correctness25%Numbers tie to source; interpretations defensible; LLM errors caught and fixed
Manual verification artifact10%≥5 hand-recomputed ratios; discrepancies flagged and explained
LLM evaluation + spec retrospective25%Specific, evidence-tied critique of the AI and of your own spec
Strategic recommendations + executive voice20%Each rec backed by ratio evidence; the voice is yours
Stage 2 feedback incorporation5%Visible response to PR comments
Repo polish15%A professional artifact you'd link on LinkedIn

Check yourself