
2 · configure
3 · deploy
NewAvailable product — files, demo URL and secure download get mapped in EDF 0.3.
Prompt workbench: version, compare and test prompts
A local-first workspace for prompts. Write them with {{variables}}, keep every version with a diff, run them on Claude, OpenAI, Gemini or a local Ollama model with streaming and live metrics, compare models or versions side by side, and run test sets with checks (contains, JSON, regex, length, LLM judge) to see whether your last edit helped. React 19 + TypeScript with an optional zero-dependency Node proxy that keeps API keys on the server.
Origin: EWDS Store (epicwebdesignstudio.com) · Roadmap window: EDF 0.2


Placed in the private vault layout (deploy/vault/products). Downloads stay disabled until checkout is connected.
Derived by the mapping engine (family · layer · tags · dependency rules). Stored in the catalog as compatibility, dependencies, relations[].
| VERSION | STATE | NOTES |
|---|---|---|
| v1.0.0 2026-10-02 | AVAILABLE | Initial release. This package contains: Prompt library with folders, tags, stars and search; system + user prompts with {{variables}}; Immutable versions with notes, line and word diff against any version or your draft, restore, and a production marker; every run points to the exact version it used; Run with streaming and Stop: time to first token, total time, tokens, tokens per second, cost (from prices you enter), 👍/👎 rating, exact-message preview; Compare 2–4 models or 2–4 versions on the same inputs, side by side; Test sets: cases per variable, checks (contains, not contains, equals, regex, valid JSON + keys, min/max length, LLM judge), parallel runs, pass rate by version and model, CSV import/export; Providers: Anthropic Claude, OpenAI, Google Gemini, Ollama and any OpenAI-compatible API, plus an offline Mock model; fetch model lists from the API. |
| → EDF 0.2 | Roadmap | Target window for the next stage. |
I verified streaming, compare, test sets and model listing against a real local Ollama model, and the OpenAI and Anthropic stream formats against a fake upstream server in the tests. The Anthropic, OpenAI and Gemini calls follow their public API formats but were not exercised with real keys here, so try your own key first. The app ships no price list (enter your own prices to see cost). Direct browser mode keeps your key in the browser: use the Node proxy for shared or deployed setups. Single user, no accounts or sync; data lives in one browser profile (use the JSON backup). The demo on this site runs the offline Mock model. Requires Node 20.19+ for the tooling.
Standard (personal or commercial use in one end project or your own business) · Extended ×3 (SaaS, unlimited client projects, finished products only). Agency licence comes later.
Personal: use for yourself on your own devices and servers. Commercial: use for one client or company. Extended: unlimited clients and deployments, including your whole team. No resale, redistribution or hosting as a service for third parties.
Activated by 1.0 (download) and 2.0 (one-click deploy). Download will be a 10-minute signed URL from the R2 vault — never a public /files/product.zip.



