> For the complete documentation index, see [llms.txt](https://docs.tryflox.xyz/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.tryflox.xyz/using-flox/reading-a-verdict.md).

# Reading a verdict

A worked example, from live mainnet data.

```
USDE   SIZE_HALF   size x0.50   SAR 0.183
pressure $2,971,745   depth@2% $16,236,005   net issuance $2,911,861
events 3649   concentration 98%   stale 4s
  - SAR 0.183 = pressure $2,971,745 / depth@2% $16,236,005
  - 98% of pressure from one address — SIZE_FULL downgraded to SIZE_HALF
```

## Line by line

**`SIZE_HALF size x0.50`** — the verdict and the position multiplier. If you were planning to take a position, take half of it.

**`SAR 0.183`** — supply pressure was small relative to depth. On the ratio alone this would be a full-size position.

**`concentration 98%`** — but 98% of that supply pressure came from a single address. The concentration override dropped the verdict one band, from `SIZE_FULL` to `SIZE_HALF`. This is the agent doing something the ratio alone cannot.

**The reasons** are the actual strings the engine emitted, in order. They are the real explanation — the narrative from the analyst layer restates them, but these are authoritative.

## Contrast: a refusal

```
PENGU   REFUSE   size x0.00   SAR 2.654
pressure $103   depth@2% $39   net issuance $-1,270
  - depth $39 below floor $50,000 — refuse regardless of ratio
```

Here supply is actually contracting (negative net issuance), but the pool is so thin — $39 of absorbable depth — that the floor override refuses regardless. A market you can't trade into isn't made safe by favorable supply.

## The point

Same engine, same moment, different answers driven entirely by what the books can absorb. A deep book gets sized; a thin one gets refused. That discrimination is the product.


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://docs.tryflox.xyz/using-flox/reading-a-verdict.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.
