> For the complete documentation index, see [llms.txt](https://nytshift.gitbook.io/nytshift-docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://nytshift.gitbook.io/nytshift-docs/agentops/paper-and-evidence.md).

# PAPER and evidence

[← Qualification loop](/nytshift-docs/agentops/qualification-loop.md) · [Documentation home](/nytshift-docs/start-here/readme.md) · Next: [Venues, accounts and authority →](/nytshift-docs/agentops/venues-and-authority.md)

PAPER is the first controlled environment in the AgentOps model. It lets a human or issued agent test behaviour against fresh normalized books while keeping venue-order capability at `none`.

## Current PAPER surfaces

### Human PAPER

* **Owner:** person using the customer workspace
* **Store:** browser-local versioned ledger
* **Authority:** simulation only

### Agent PAPER

* **Owner:** one platform-operator-issued MCP connection
* **Store:** private server ledger under immutable policy
* **Authority:** simulation only

These stores remain separate today. A human terminal run is not automatically an agent run, and neither surface currently creates a shared strategy record.

Read the [Paper trading guide](/nytshift-docs/engineering-guide/05-paper-trading.md) for order, risk, marking and protection semantics.

## What PAPER proves

PAPER can provide run evidence that declared behaviour stayed inside the simulator's market, loss, drawdown, spread, slippage and notional rules for a specific observation window. It can also expose rejected entries, incomplete marking and stale evidence. The current ledgers do not store a strategy ID or version; that attribution is **NEXT**.

It does not prove live profitability, execution quality or venue readiness.

## What PAPER models and withholds

The current human PAPER surface models venue-rule leverage profiles, cross or isolated margin, initial and maintenance margin, estimated liquidation and a live-rate funding projection. Those values remain simulator evidence, not venue account state.

It explicitly excludes or limits venue fees and rebates, funding accrual or settlement, venue-exact bankruptcy and liquidator fees, auto-deleveraging, queue priority, hidden liquidity, venue latency and background execution while a browser is closed. Those omissions remain part of the evidence rather than being hidden behind a return figure.

Agent PAPER is narrower. It retains immediate fresh-book executions, positions and risk-lock state, explicitly labels fees, funding and liquidation as not modeled, and has no GTC, protection, leverage or margin model.

## From activity to Flight Recorder

Current product activity provides bounded evidence for implemented surfaces. The planned Flight Recorder will unify the lineage of:

1. agent and strategy version;
2. source-labelled market and account inputs;
3. tool calls and typed intents;
4. proposal and AEGIS results;
5. PAPER requests, fills, positions and policy violations;
6. degraded, stale, partial or unknown states;
7. revocation and later version changes.

That unified recorder is **NEXT**. Until it exists, the documentation and interface must not imply that all human, agent, strategy and venue activity already shares one complete audit trail.

## Evidence before marketplace claims

A future strategy network could support private sharing, cloning and eventually licensing. NYTSHIFT will not reduce a strategy to a return screenshot. Any public comparison would need standardized windows, explicit costs and limitations, version lineage, drawdown and mandate-discipline evidence. Public rankings and paid strategy sales remain **VISION**.


---

# 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://nytshift.gitbook.io/nytshift-docs/agentops/paper-and-evidence.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.