FORGECOURSE ForgeMind AI · Hands-On Portfolio
HO4 · Sample 02 · Interview scorecard

The One-Shot Rebuild

Arjun's hiring panel scores candidates in their heads, and the bar moves with the mood of the room. He asks Claude for a scorecard. It takes 13 turns — because the rules that make a scorecard fair (weights, must-have gates, a threshold that a high score cannot override) all live in his head. Then he writes them down, folds them into one prompt, and rebuilds it in a fresh chat in one message.

THE TOOL The scorecard he was trying to get — score a candidate and watch the gate fire

This is what she ended up with. Every rule below it — the slabs, the cap, the order of operations — had to be dragged out of her head one turn at a time. Change the inputs and watch them fire.

Interview scorecard working
BUILD 1 The messy way — 13 turns

Click through it. Notice what each turn actually is: not Claude failing, but a rule arriving late. Every correction is a piece of context that was missing from turn 1.

STEP 2 The corrections log

At the end of the messy chat she asked Claude one question: “list every correction I gave you in this chat.” Claude has the whole conversation in front of it, so the log costs almost nothing to produce — and this log is the context she was carrying in her head all along.

ScaleEvery criterion is scored 1–5. Never out of 10.

WeightsCoding 40% · System design 25% · Communication 20% · Culture 15%.

GateCoding is a must-have. Under 3 on coding = NO HIRE, whatever the weighted total says. The gate beats the arithmetic.

Gate displayWhen a gate fails, say NO HIRE loudly and name the gate that failed. The score stops being the headline.

ThresholdWeighted score is out of 5. 3.5 or above is a hire — inclusive.

Tie-breakOn a tie, the higher coding score wins.

BlanksA blank is not a zero. Any unscored criterion = incomplete card, and no verdict at all.

JustificationA score of 1 or 2 requires a written note. Nobody kills a candidate without a reason.

TransparencyShow each criterion's contribution (score × weight), not just the total.

BehaviourRecalculate live, and never wipe the notes when a score changes.

OutputOne screen, no login, prints cleanly for the panel file.

STEP 3 The one-shot prompt

The log, folded into a single message: role, spec, the rules, the order they fire in, the edge cases, the output format. This file is the real deliverable of HO4 — not the tool. The tool is just the proof that the context is complete.

Build a single-file HTML interview scorecard for hiring engineers. No login, no backend,
one screen, prints cleanly.

CRITERIA — each scored 1 to 5 (never out of 10), each with a weight:
  Coding          40%
  System design   25%
  Communication   20%
  Culture         15%

SCORING RULES — follow these exactly
1. The weighted score is out of 5. Show each criterion's CONTRIBUTION (score x weight),
   not just the final number.
2. HIRE at 3.5 or above. The threshold is INCLUSIVE — 3.5 exactly is a hire.
3. CODING IS A MUST-HAVE GATE. If coding scores under 3, the verdict is NO HIRE no matter
   what the weighted total says. The gate BEATS the arithmetic — do not show a healthy total
   as the headline and bury the gate. Say NO HIRE loudly and name the gate that failed.
4. A blank is NOT a zero. If any criterion is unscored, the card is INCOMPLETE: give no
   verdict at all, and say what is missing.
5. Any score of 1 or 2 requires a written justification note. No note, no verdict.
6. On a tie, the higher CODING score wins. Say so.

BEHAVIOUR
- Recalculate live as scores change, and never wipe the notes when a score changes.
- Show the verdict as one unmissable line: HIRE / NO HIRE / INCOMPLETE.
BUILD 2 Fresh chat. One message.

She opened a new chat, pasted that one prompt, and got the same tool — working, first try. Same features, none of the archaeology.

Build 1 — the messy way
13
turns, each one prising a rule out of her head
Build 2 — one-shot
1
one message, in a fresh chat with no history
Feature parity
11/11
every rule survived the rebuild — because every rule was written down
Criteria scored 1–5
Weights: 40/25/20/15
Per-criterion contribution shown
Hire threshold 3.5, inclusive
Coding must-have gate at 3
Gate overrides the total
Gate named when it fails
Blank ≠ zero — card incomplete
Notes required for a 1 or 2
Coding breaks a tie
Live recalculation

This is the whole lesson. Claude was never the bottleneck. The context was — it just arrived one turn at a time instead of all at once. Say it up front and the fourteen turns collapse into one.

Make it your own
Pick a tool with real rules — caps, tiers, gates, rounding, cut-offs. A page with no rules produces no corrections, and the corrections log is the exercise.
Do not tidy up as you go. Build it messily on purpose, and let it be wrong. The wrongness is the data.
When it finally works, ask Claude to list every correction you gave it. That is your log, free.
Rebuild in a genuinely fresh chat. Re-using the old one proves nothing — the context is already in there.
If the rebuild misses a rule, you left it out of the log. Add it and go again. That gap is the most useful thing you will learn all week.