Examples
9
Curated public plain examples.
At a glance
Average rubric
23.7/25
Deterministic output-quality checks.
Controls
None
Example studies are absolute, not contrastive.
Metric and rubric definitions
Source words
Words in the local study source for a variant; this is the local authoring burden.
Variable words
Words in a variant's explicit input payload, when a template or refinement uses one.
Output words
Words in the saved compiled final artifact.
Leverage
Output words divided by local source words; larger means more final artifact per local word, not quality by itself.
Fact units
Novelty-weighted semantic fact units extracted from the output by deterministic rules.
Density
Discounted fact units per 1,000 output words; higher means a more information-dense output.
Yield
Discounted fact units per 1,000 local source words; higher means more semantic material per local authoring word.
Rubric
Five 1-5 checks: intention fit, completeness, writing/structure, no leakage/pathologies, and direct usefulness.
No leakage/pathologies
Scans for unresolved directives, placeholders, local paths, WeaveMark internals, TODOs, nulls, and brittle assistant meta-language.
Example metrics
| Example | Source | Vars | Output | Leverage | Facts | Density | Yield | Rubric |
|---|---|---|---|---|---|---|---|---|
| Program Review Checklist | 506 | 22 | 788 | 1.56x | 43.75 | 55.5 | 86.5 | 24/25 |
| Program Debugging Assistant | 319 | 172 | 948 | 2.97x | 67.75 | 71.5 | 212.4 | 24/25 |
| Learning Tutor | 234 | 90 | 942 | 4.03x | 57.75 | 61.3 | 246.8 | 22/25 |
| Research Brief | 281 | 103 | 1,370 | 4.88x | 99 | 72.3 | 352.3 | 25/25 |
| Decision Advisor | 274 | 157 | 803 | 2.93x | 48.25 | 60.1 | 176.1 | 23/25 |
| Investment Brief | 191 | 42 | 731 | 3.83x | 52.5 | 71.8 | 274.9 | 24/25 |
| Deep Summary | 205 | 179 | 1,005 | 4.9x | 57.5 | 57.2 | 280.5 | 24/25 |
| Messy Notes Action Plan | 258 | 211 | 1,058 | 4.1x | 67 | 63.3 | 259.7 | 25/25 |
| Prompt Refiner | 205 | 98 | 635 | 3.1x | 45.5 | 71.7 | 222 | 22/25 |
Rubric detail
Program Review Checklist
Produce a practical review checklist tailored to a programming project.
24/25 total rubric score.
Open outputProgram Debugging Assistant
Produce a debugging assistant prompt that diagnoses behavior from evidence.
24/25 total rubric score.
Open outputLearning Tutor
Produce an adaptive tutor prompt grounded in learner context and practice.
22/25 total rubric score.
Open outputResearch Brief
Produce a research brief prompt with source expectations and caveats.
25/25 total rubric score.
Open outputDecision Advisor
Produce a decision-advice prompt with options, tradeoffs, and uncertainty.
23/25 total rubric score.
Open outputInvestment Brief
Produce an educational investment brief with evidence, risks, alternatives, and decision triggers.
24/25 total rubric score.
Open outputDeep Summary
Produce a deep-summary prompt that preserves structure and audience needs.
24/25 total rubric score.
Open outputMessy Notes Action Plan
Turn messy notes into an organized action plan.
25/25 total rubric score.
Open outputPrompt Refiner
Produce a prompt-improvement prompt that preserves intent and improves clarity.
22/25 total rubric score.
Open output