# Manage your prompt library

> How to add, generate, star, and archive the evaluation prompts every benchmark runs — and why a stable library keeps your score comparable over time.

- Section: Guides
- Updated: 2026-07-11
- Canonical: https://knitknot.ai/docs/manage-your-prompt-library/
- Publisher: KnitKnot, the AI Presence Management platform (https://knitknot.ai)

---

Your prompt library is the set of buyer-style questions every benchmark runs through ChatGPT, Claude, Perplexity, and Gemini. It's the measuring stick — so the most important thing about it is that it stays stable. Prompts persist across runs; each benchmark measures the same questions, which is what makes your score trend meaningful instead of noise.

You manage it from the **Prompts** page in the [console](https://app.knitknot.ai).

## What's in the library already

Most workspaces arrive with a library already built — evaluation prompts grounded in real Google search queries with monthly volume data, not synthetic templates. They're weighted toward the head-to-head and landscape questions buyers actually ask, and layered across features and buyer personas.

Each prompt is scoped to a [subject](/docs/subjects/) — your brand, or one of its products — so per-product libraries stay separate. When you filter the Prompts page to a product, you're editing that product's questions only.

## Add a prompt

Use **Create prompt** to add a question by hand. Write it the way a real buyer would ask an AI — "what's the best tool for X," "compare us vs a competitor," "does product Y support Z." Manual prompts join the same library and are measured identically to generated ones.

## Generate prompts

The **Generate** action rebuilds a batch of prompts from your keyword corpus — real search seeds with volume data behind them. Generation runs live LLM calls and can fetch fresh keyword data, so it's a manual button rather than something that fires automatically. Run it when you've added a product, entered a new market, or want to widen coverage of a topic — not on every visit.

## Star, activate, and archive

Two independent controls shape what a benchmark actually runs:

- **Status** — a prompt is either **active** or **archived**. Only active prompts are included when a benchmark runs. Archive a prompt to retire it without losing its history; archived prompts keep the sentiment and results they earned.
- **Star** — a flag you layer on top of any active prompt to mark it as a priority. Starring doesn't change whether a prompt runs; it surfaces the questions you care most about.

Archiving is almost always the right move over deleting. Deleting is permanent and drops the prompt's history; archiving keeps the record and lets you reactivate later.

## Keep the library stable

Every prompt you add, archive, or regenerate changes what future runs measure. That's fine — just do it deliberately. If you want a clean before-and-after on a specific fix, avoid reshuffling the library between those two runs so the only thing that changed is your content, not the questions.

Next: [manage the competitors](/docs/manage-competitors/) your prompts benchmark you against, or [run a benchmark](/docs/run-and-schedule-benchmarks/) once the library looks right.