moki
Hybrid engine · LLM proposes, you review, math decides

A hard gate for soft ideas.

Most idea scorecards average six numbers and call it judgment. MakeOrKillIt runs a knockout gate first, scores in ranges instead of false precision, and argues against your idea before it lets it pass.

No sign-up to run your first idea. Watch it reach a verdict live.

6
Weighted scoring dimensions
5
Must-meet knockout criteria
3
Verdicts: make · hold · kill
2
Thresholds, not one fragile line
The problem

Averaging is how good ideas die politely.

Score everything, take the mean, ship the top quartile — and a single fatal flaw hides behind five healthy numbers. The fix isn't a better average. It's separating what's fatal from what's merely weak.

Naïve scorecard

One number per dimension, averaged into a single verdict. A 9 on market quietly cancels a 1 on legality. False precision, real blind spots.

MakeOrKillIt

A binary knockout gate catches the fatal flaw first. Survivors are scored in confidence-weighted ranges, then aggregated by a deterministic rule.

The method

Six phases from raw text to a defensible call.

The LLM does the reading and proposing. You correct what it got wrong. The band math and aggregation are deterministic — same input, same review, same verdict.

Phase 0

Extraction

An LLM pulls structured attributes from your free text — problem, market, model — and never invents numbers. Thin evidence lowers confidence, not honesty.

Phase 1

Knockout gate

Five must-meet criteria run as a binary gate. Any clear failure kills the idea before scoring — a fatal flaw can't be averaged away.

Phase 2

Hybrid scoring

Each dimension gets a point, a confidence, and a rationale. Low-confidence scores fall to you for review. You override; the math stays deterministic.

Phase 3

Band aggregation

Weighted low and high bounds combine conservatively into a 0–100 range. Correlated uncertainty widens the band — cautious by default.

Phase 4

Decision

Two thresholds plus band width map to make / hold / kill. Where the band sits — and how wide it is — is the verdict.

Phase 5

Explanation

You get the binding constraints dragging the score down, the cheapest experiments to shrink the band, and what would flip the verdict.

Banded scoring

Never a single number.

Every dimension is a range whose width is set by confidence. Guess a market size instead of reading it, and confidence drops — so the band widens and the verdict leans toward hold. Uncertainty is priced in, not hidden.

  • Wide band High uncertainty → gather cheap evidence before you commit.
  • Narrow & low Confidently mediocre → reshape the idea or drop it.
  • Band, not point The range itself is the argument for the call.
High confidence[62, 71]
Medium confidence[48, 74]
Low confidence[31, 79]
Six dimensions

What gets weighed — and how much.

Weights sum to one and are the starting point, not the last word: the calibration loop retunes them as real outcomes come in.

Market attractiveness0.22
Differentiation0.20
Financial reward0.18
Strategic leverage0.15
Risk (inverse)0.13
Team & resource fit0.12
The knockout gate

Five ways an idea dies before it's scored.

Any clear failure is an instant kill. When the evidence is genuinely unclear, the gate doesn't guess — it asks you.

Legal & ethical

Can it be done lawfully and ethically at all?

Minimum market

Is there a meaningful floor of users to serve?

Technical feasibility

Is the core build reasonably possible?

Strategic alignment

Does it fit the stated mission and strategy?

Resource access

Can you reach the minimum resources required?

Adversarial by design

For every idea, it writes the strongest case for killing it.

The scoring model runs skeptical. For each dimension it names the single strongest piece of disconfirming evidence, then builds a whole-idea kill case — the most convincing version it can, whether it believes it or not. It's the best defense against talking yourself into your own idea.

The verdict

Two thresholds and a band width.

The decision comes from where the aggregate band sits relative to the make line (65) and the kill line (40) — and, for everything in between, how wide the band is.

Make

Even the floor clears the bar.

low ≥ 65 — the worst realistic case is still good enough. Build it.

Hold

The band straddles the line.

Wide band → reduce uncertainty with cheap evidence. Narrow but middling → reshape or walk.

Kill

Even the ceiling is too weak.

high ≤ 40— the best realistic case still isn't worth it. Move on.

The calibration loop

An opinion that checks itself against reality.

Every verdict is stored as a prediction. When the real outcome is known, it's recorded and paired back. Once enough outcomes accumulate, weights and thresholds are re-fit against what actually happened — proposed for human approval, versioned so you can roll back. Without this loop it's just an opinion generator; with it, it earns its verdicts.

Put your idea through the gate.

Paste the problem, the user, and how it makes money. Watch the knockout gate, the bands, and the verdict resolve live.