spp
  • Home
  • Why spp
  • Methodology
  • Installation
  • Usage
  • Phases
  • Examples
  • Scope
  • Changelog
  • Benchmark

On this page

  • Worked runs
  • Per-mode skeletons
  • See the methodology measured

Examples

Worked runs and skeletons, from a real public-data run to per-mode templates.

The spp repository ships a set of examples under examples/. Two are full worked runs; the rest are per-mode skeletons that show the expected artifact shape for each task type spp supports.

Worked runs

  • public-benchmark — the first example backed by a real, fully reproducible run on public data. A TREC (6-class question-type) run on gpt-5-nano, with every iteration’s prompt / eval / discrepancy / auditor trio, the frozen prompt, the single sacred-test read, and a three-way comparison against EvoPrompt and DSPy. Every row, prediction, and prompt is genuine and unredacted. This is the same run documented in the benchmark site’s TREC loop log.
  • hair-loss-relevance — the canonical worked example shipped with spp’s first release. Demonstrates the end-to-end binary-relevance workflow and the failure-cluster taxonomy that motivated the methodology.

Per-mode skeletons

These show the artifact layout and plan.md shape for each task type, so you can see what spp produces before running it on your own data.

Example Task mode
multi-field-extraction multi-field structured output (K>1)
nested-schema hierarchical labels via JSON schema
feature-group-split feature-group prompt splitting
entity-extraction structured extraction (variable-cardinality, span-grounded)
decomposition-pipeline prompt decomposition (managed linear pipeline)

See the methodology measured

For the full evidence that the methodology works — accuracy, cost, token breakdowns, the fairness ledger, and per-task loop logs documenting every iteration and the human-in-the-loop gate exchange — see the dedicated benchmark site:

→ The spp benchmark

spp — Supervised Prompt Producer · MIT

 

Built with Quarto