Skip to content
TFD-42 edited this page Aug 10, 2026 · 2 revisions

Frequently Asked Questions

Quick answers about Wild_Root_Prompt — what it is, what it costs, whether your data leaves your machine, what hardware it needs, and how it compares to writing prompts by hand.


What is Wild_Root_Prompt, in one sentence?

A local prompt engineering tool that rewrites a rough idea into an expert-level prompt or a full 12-section instruction manifest, by applying 173 prompt engineering techniques before your model ever sees the input.

Does it send my data anywhere?

No. Generation runs against a local backend over the loopback interface. The only outbound traffic is the optional web enrichment — a search on your task text — and --offline disables even that. There is no telemetry, no account, and no API key in the codebase.

Do I need an OpenAI or Anthropic API key?

No. It runs on Ollama or any OpenAI-compatible local server. There is nothing to pay for and nothing to sign up for.

Is it free?

Yes — MIT licensed, for personal and commercial use.

What hardware do I need?

A 3B model needs roughly 4 GB of RAM and works fine, especially in Quick mode. 7–8B models want ~8 GB and are the sweet spot for Full manifests. It runs on Android via Termux too. See Installation.

Do I need to know the command line?

No. Double-click the launcher and use the Web UI in your browser. The CLI is there for people who want technique bundles, scripting, and parallel dual-model runs.

What's the difference between Quick and Full mode?

Quick returns one enhanced prompt to paste into any LLM. Full returns a 12-section instruction manifest meant to be executed by an agent. Iterate in Quick, deliver in Full. --draft gives you sections 1–2 of a Full manifest as a cheap direction check.

What are the 173 techniques?

Prompt engineering methods — Chain-of-Thought, Tree-of-Thought, ReAct, MECE, Constitutional AI, red teaming, and 160-plus more — across 15 categories, stored as editable JSON. The complete catalogue is at Prompt Engineering Techniques.

Which techniques should I pick?

Start with the defaults (15, balanced). For a specific job use a bundle: --techniques "bundle:Audit / securite". If you're unsure, --recommend-techniques picks based on your task's own wording.

Is more techniques always better?

No. Past roughly 30 active techniques, small models start producing a mushy compromise between competing instructions. A coherent bundle of 10–20 beats a 100-technique pile.

What are slash metacommands?

Inline modifiers typed in your task text — /expert /tableau /sources — that control persona, format, depth, reasoning style and epistemic standards. There are 60. See Slash Metacommands.

Why run two models in parallel?

Because their disagreements are informative. Pair a systematic model with a creative one and the synthesis pass has genuinely different material to merge, rather than two paraphrases of the same answer.

Can I use LM Studio / GPT4All / text-generation-webui instead of Ollama?

Yes — --backend openai_compatible with the server's URL. The backend must run on the same machine (loopback only, by design). See Configuration.

Does it work offline?

Completely, with --offline. That skips web enrichment and connectivity checks entirely. Everything else — pre-processing, technique injection, generation, synthesis — is local anyway.

Can I add my own techniques or templates?

Yes. Both are plain JSON in the repo root: prompt_expert_methodology.json and prompt_templates.json. Edit them and the changes apply on the next run — no code change, no rebuild. Contributing if you want to share them.

What is the 12-section manifest for?

Handing a complete, unambiguous brief to an LLM agent — including ambiguity zones, error handling, control loops and a reproducibility checklist. It's written to be executed, not just read. Structure: Architecture.

Can I use the output with a hosted model?

Yes. The manifests are model-agnostic — that's the point. Generate locally, execute anywhere.

Does it remember previous sessions?

Yes, in memory/, injected as context so a sequence of related tasks stays coherent. Disable per-run with --no-memory, per-prompt with /neuf, or wipe it with memory clear. It can be encrypted at rest.

Can I drive it from my own program?

Yes — a small REST API with SSE streaming, or the CLI with --quiet --output. See REST API.

Is it safe to expose the Web UI on my network?

No. It binds to loopback and has no authentication because it has no remote attack surface by design. If you need remote access, tunnel over SSH rather than exposing the port.

Why does macOS say the app can't be verified?

It isn't notarized — that requires a paid Apple developer account. The source is public and you can build it yourself. Workaround in Troubleshooting.

Why do some technique and bundle names appear in French?

The methodology file was authored bilingually and the identifiers were kept stable rather than renamed, since they're referenced by ID and by name in saved configurations. Bundle names are matched case-insensitively, and the numeric form (bundle:6) works everywhere the name does.

How do I report a bug or request a feature?

The issue tracker. Include the command you ran and the full error.


Next: Examples — real before/after runs · Comparison — versus other approaches · Glossary — every term defined · Use Cases · Quick Start.

Clone this wiki locally