> ## Documentation Index
> Fetch the complete documentation index at: https://agents.concierca.ch/llms.txt
> Use this file to discover all available pages before exploring further.
# START HERE — What can you ask?
> The intent library: every kind of question the Vertical answers, grouped by goal — plus the mandatory first-use bootstrap.
This is the map of what the Vertical can answer. You do not need to know signal names — pick the **question** you have, and the AI routes it to the right tool and signals.
## Mandatory first-use bootstrap
**On the first use of a Vertical in a session, bootstrap before any advisory task.**
1. Call `vertical_legend` — the live capability manifest (channels, benchmarks, lookups, the signal catalog, and the bootstrap article ids).
2. Load the editorial method it points to: call `vertical_knowhow(article_id)` for the **getting\_started** and **agent\_rules** articles referenced in the legend.
Only then answer advisory questions. The legend tells you what exists *right now*; the know-how articles tell you how to reason over it. Skipping this step is the most common cause of ungrounded answers.
## The intent library
### A. Understand one entity
* Give me an **overview** of Brand A.
* Is Brand A **growing**?
* What **changed** recently for Brand A?
* What is Brand A's **current strategy**?
* Where is Brand A **vulnerable**?
* What should Brand A **do next**?
### B. Compare entities
* How does Brand A **compare to** Brand B (and Brand C)?
* Who is **stronger on** growth / paid media / engagement / launches?
* Line up Brand A, Brand B, and Brand C side by side.
### C. Discover across the market
* Which brands are **accelerating**?
* Which brands are **showing warning signs**?
* Which brands **recently changed direction**?
* Which brands **use a particular launch style**?
### D. Analyze channels
* How is Brand A doing on **Instagram**?
* What is Brand A doing in **Stories**?
* Analyze Brand A's **Meta Ads**.
* How is Brand A's **YouTube** presence?
* Give me a **cross-channel** read on Brand A.
* Put Brand A's channel activity in **brand context**.
### E. Analyze markets
* How **dense** is the market in Country X?
* Who is **expanding** into Country X?
* What is the **industry pulse** right now?
* What **trend clusters** are forming?
### F. Get recommendations
* What does the **evidence** say, what's the **coverage**, what's the **playbook**, and what do you **recommend**?
## Routing table — intent → primary tool
| Your intent | Primary tool | Then |
| ---------------------------------- | ------------------------------------ | ------------------------------------ |
| "I'm not sure what exists" | `vertical_legend` | — |
| Turn a name into an entity | `vertical_resolve` | `vertical_card` / `vertical_compare` |
| Understand one entity | `vertical_card` | `vertical_knowhow` for framing |
| Compare 2–6 entities | `vertical_compare` | — |
| Discover across the market | `vertical_search` (by `signal_type`) | categorize by class/band |
| Market / benchmark question | `vertical_benchmark` | — |
| Playbook / method / interpretation | `vertical_knowhow` | — |
| Controlled vocabulary values | `vertical_lookups` | — |
## Decision tree
```text theme={null}
Do you know what data exists?
No → vertical_legend (and, first use, load getting_started + agent_rules via vertical_knowhow)
Yes ↓
Is the question about a NAMED entity?
Yes → vertical_resolve → one entity? → vertical_card
→ 2–6 entities? → vertical_compare
No ↓
Is it "which entities across the market …"?
Yes → vertical_search (filter by signal_type; categorize by class/band)
No ↓
Is it "what is normal / how dense / industry pulse"?
Yes → vertical_benchmark
No → vertical_knowhow (method / playbook) or vertical_lookups (vocabulary)
```
## Next
Ground every answer: the ten rules.
Each intent above, expanded into a tool-and-signal flow.
What each tool does and when to call it.
The concept behind this section.
See also the full [Vertical tool list](/for-agents/vertical) and the wider [Operating Contract](/for-agents/ai/operating-contract).