> ## Documentation Index
> Fetch the complete documentation index at: https://docs.zued.ai/llms.txt
> Use this file to discover all available pages before exploring further.
# Recommendations
> After every audit run, zued generates specific, ranked recommendations for every URL in your project.
After each audit — initial or weekly snapshot — zued generates recommendations automatically. They are specific to each URL, chunk, and prompt: not generic advice, but concrete changes tied to the exact analysis that produced them.
## Four types of output
Per prompt and per content chunk: what AI engines say versus what your page actually contains. Includes missing topics, format mismatches, and accuracy issues.
Per URL: bot blocking, JavaScript rendering failures, Core Web Vitals problems, missing structured data.
For prompts spanning multiple pages: how your URLs work as an ensemble, internal linking gaps, and unified recommendations. See [Cross-URL Analysis](/recommendations/cross-url-analysis).
A ranked list of the highest-impact, lowest-effort changes across your entire project — sorted by priority score.
## Priority score
Every recommendation has a priority score from 0 to 100. The score is calculated from impact, effort, and how many AI engines are affected. See [Prioritization](/recommendations/prioritization) for the full formula.
Recommendations are grouped into four categories:
| Category | Score | When to act |
| ------------------------ | :----: | ---------------- |
| **Quick Win** | 80–100 | This week |
| **Strategic Investment** | 50–79 | Next sprint |
| **Medium Priority** | 30–49 | After quick wins |
| **Low Priority** | 0–29 | Deprioritize |
Technical issues that block AI crawlers are always scored at Priority 100 — fix these before any content changes.
## How recommendations are grounded
Every page's recommendations are built on top of a set of observations about that page — what concepts it already covers, how consistently it names its primary entity, which explanatory questions it answers, and which AI engines mention topics it does not. Recommendations are required to cite these observations as evidence, which keeps them specific to the page and hard to confuse with generic advice.
Content gaps are prioritized by the strength of the signal behind them. Topics that many AI engines discuss receive the highest priority. Topics another page of your site already covers are surfaced as linking or consolidation opportunities, not as rewrites. Topics a single engine mentions are flagged but ranked lower.
Recommendations also favor how the engines actually behaved on your page over general expectations about how a given engine tends to behave. When what we observed an engine doing on your page disagrees with its usual style, and we saw that behavior consistently across more than one response, the recommendation follows what we observed on your page. A signal seen in only a single response is treated as weak and does not override the general guidance.
Each new-section recommendation also includes example phrasing grounded in your own entity list, so you have concrete starting sentences rather than an abstract topic brief.
## Tracking progress
When you implement a recommendation and the next snapshot runs, zued compares the new scores against the previous snapshot. Resolved quick wins are tracked automatically — you can see which changes produced measurable improvements.