Prompt Optimizer 1.2.0

Prompt Optimizer 1.2.0

This release is about knowing whether the prompts we generate are actually
any good — and about the prompts themselves getting measurably better.

Added — conformance checking

Every generated variant now carries a badge showing which of its format's own
rules it satisfies, with the evidence for each violation.

The rules are not generic advice: they are the ones each format declares in the
app's own system prompts. A Claude Code prompt is checked for backticked paths,
a plan-and-stop section, a separate git branch; a GEMINI.md for Markdown-only
structure and concrete, runnable commands; a System+User pair for a non-empty
User field.

Only rules a parser can decide are checked. Anything needing judgement is left
unchecked rather than guessed — an approximate check produces false positives,
which is exactly what made the previous linter untrustworthy.

This replaces a linter that applied 3 generic rules to all five formats while
the formats declare around forty, and that contradicted them in two places.

Added — a regression harness for the prompts

npm run eval runs a fixed corpus of 66 cases through the real system
prompts and reports a per-rule conformance rate. Pinned model, three repetitions
per case, evidence for every failure. It is a development tool: it never runs in
the shipped app and never spends the end user's quota.

Until now the prompts were the one part of the project we changed without any
regression test — we edited them, they read better, we shipped them.

Changed — the system prompts, rewritten and measured

Not by taste: by measurement, before and after.

Rule	Before	After
Chat: XML tags properly closed	76%	100%
Claude Code: reads CLAUDE.md	93%	100%
Gemini: Markdown structure kept	92%	100%

Two of those failures existed because the prompt had never actually said what
it wanted — "close the tags" and "no XML tags" were both left implicit, and
emphatic capitals had been quietly compensating for the omission.

Changed — model selection

The default is now the current Flash-Lite alias: cheapest and fastest tier,
and a moving alias, so the app follows Google's current model without an update.
Sampling parameters are left at the model default, as Google recommends for the
Gemini 3.x family.

Fixed

• Few-shot examples are sent once instead of being repeated for every
  selected format — up to five copies of the same text in a single request.
• Two teaching cards in the app were out of date. One of them recommended
  prefilling, a technique Anthropic has since removed: following it today
  returns a 400 error, on the very models this app uses.
• Scaffold generation no longer bakes Windows line endings into its output.

Full details in the CHANGELOG.
The measurements behind every claim above are in
docs/eval-baseline.md,
including the experiments that failed.

Download

• Installer (recommended): Prompt.optimizer_1.2.0_x64-setup.exe — installs
  into your user profile, no admin rights required.
• Portable: pop_app.exe — a single executable (requires WebView2,
  usually already present on Windows 10/11).

⚠️ The app is unsigned: on first launch Windows SmartScreen may warn you →
"More info" → "Run anyway".

Prompt Optimizer 1.1.1

Prompt Optimizer 1.1.1

A maintenance release on top of 1.1.0 — same features, one build-correctness fix.

Fixed

• Scaffold line endings are now normalized to LF. The scaffold constants
  generator reads the template .md files from the working tree, which on Windows
  (core.autocrlf=true) holds CRLF. Those \r\n were baked inside the generated
  string literals as content — where git cannot normalize them — which made the
  build output platform-dependent, dirtied the repository on every build, and
  shipped CRLF line endings inside the scaffolds generated for users. Output is now
  deterministic and idempotent across Windows and Linux/CI.

No changes to app behaviour, prompts, or the optimization formats.

Full details in the CHANGELOG.

Download

• Installer (recommended): Prompt.optimizer_1.1.1_x64-setup.exe — installs
  into your user profile, no admin rights required.
• Portable: pop_app.exe — a single executable (requires WebView2,
  usually already present on Windows 10/11).

⚠️ The app is unsigned: on first launch Windows SmartScreen may warn you →
"More info" → "Run anyway".

Prompt Optimizer 1.1.0

Prompt Optimizer 1.1.0

What's new

• Self-improvement loop (lessons.md) in the outputs meant for iterative
  software development: the Claude Code and Gemini optimization formats,
  and the Structured scaffold mode, now instruct the agent to keep a
  lessons.md — record a rule after each correction, re-read it at session
  start, promote stable lessons into the main instruction file. Intentionally
  left out of the one-shot formats (Chat, System+User, Cowork), where it isn't
  needed.
• New docs — prompt optimization strategies
  (EN · IT),
  linked from the README: what each format's strategy is and why, based on the
  program's real system prompts.
• Dev tooling: npm run sync:standards to align the method files across forks.

Changed

• Development methodology bumped to v0.5 (self-improvement loop + a balanced
  "demand elegance" checkpoint).

Full details in the CHANGELOG.

Download

• Installer (recommended): Prompt.optimizer_1.1.0_x64-setup.exe — installs
  into your user profile, no admin rights required.
• Portable: pop_app.exe — a single executable (requires WebView2,
  usually already present on Windows 10/11).

⚠️ The app is unsigned: on first launch Windows SmartScreen may warn you →
"More info" → "Run anyway".

Prompt Optimizer v1.0.0

Release 1.0.0 - prima versione definitiva dell'edizione pubblica solo-API di Prompt Optimizer.

Contenuto:

• pop_app.exe - eseguibile standalone portable (richiede WebView2, di norma gia presente su Windows 10/11)
• Prompt_optimizer_1.0.0_x64-setup.exe - installer NSIS per-utente (nessun diritto admin)
• manuale-utente.pdf - manuale utente (IT)
• user-manual.pdf - user manual (EN)

Ottimizzazione prompt con anonimizzazione PII, generatore di scaffold istruzioni agenti, e rifinitura via API (Claude API / OpenAI API). Nessuna dipendenza da CLI locali.

Nota: app non firmata -> Windows SmartScreen puo avvisare ("Ulteriori informazioni" -> "Esegui comunque").