> ## 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.

# Vertical Playbook

> How an AI uses the market-intelligence layer: start with the legend, route by question, ground every answer.

The Vertical layer is Concierca's market- and competitive-intelligence surface. This playbook is how an AI client uses it well: learn the data model first, route by the shape of the question, and ground every recommendation in retrieved signals. The full tool reference is in [Vertical](/for-agents/vertical).

## Start here: learn the model

If you don't already know the vertical's data model, **do not call brand tools blind.** Learn it first:

<Steps>
  <Step title="vertical__vertical_legend">
    Returns the live data model — channels, the signal catalog and what each signal **means**, example questions, benchmarks, lookups, and live coverage / counts. This is your map.
  </Step>

  <Step title="vertical__vertical_knowhow">
    Returns the getting-started guidance and agent rules — the playbook and method for reasoning over this vertical.
  </Step>
</Steps>

## Route by question

| The question is about…        | Use                                                         |
| ----------------------------- | ----------------------------------------------------------- |
| One brand                     | `vertical__vertical_resolve` → `vertical__vertical_card`    |
| Multiple brands               | `vertical__vertical_compare` (don't loop single cards)      |
| A cross-brand market question | `vertical__vertical_search` with the relevant `signal_type` |
| A country / market benchmark  | `vertical__vertical_benchmark`                              |
| A playbook or method          | `vertical__vertical_knowhow`                                |
| "I'm not sure what exists"    | `vertical__vertical_legend`                                 |

<Note>
  For any brand, **resolve first**. `vertical__vertical_resolve` turns a brand name into the canonical entity the other tools expect — never hand-type a brand id into a card or compare call.
</Note>

## Grounding rules

These are what separate a grounded market answer from a plausible-sounding guess. Promote them in every response:

* **Check `data_coverage` before advising on a brand** — thin coverage means a weaker claim.
* **Don't invent missing statistics.** If a number isn't in the data, say so.
* **Brand-specific numbers beat generic best practice** — a retrieved figure outranks a rule of thumb.
* **Ground recommendations in retrieved signals**, not prior assumptions.
* **Distinguish facts from estimates** explicitly.
* **Don't fabricate exact rankings** from quartile or band signals — a band is a band, not a rank.
* **If the dataset lacks a requested fact, say so** rather than filling the gap.

### Answer shape

Frame market answers as a chain the user can audit:

> **Your data shows X → the playbook says Y → therefore Z.**

That keeps the retrieved evidence, the method, and the recommendation visible and separable.

## Naming & counts

<Warning>
  Prefer the canonical `vertical_*` tools. The `feed_*` names (`feed_card`, `feed_search`, `feed_compare`, `feed_brand_resolve`, …) are **deprecated aliases** — use the `vertical_*` equivalents.
</Warning>

Never hard-code dataset counts or coverage numbers. `vertical__vertical_legend` reports them **live** and is the authoritative source — read them at the time you answer, don't carry a remembered figure.

See [Vertical](/for-agents/vertical) for the complete tool list and parameters, and [Routing](/for-agents/ai/routing) for how market intelligence fits the wider tool map.