> 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/qualification-loop.md).

# The qualification loop

[← Current capabilities](/nytshift-docs/agentops/current-capabilities.md) · [Documentation home](/nytshift-docs/start-here/readme.md) · Next: [PAPER and evidence →](/nytshift-docs/agentops/paper-and-evidence.md)

NYTSHIFT organizes the product around one idea: a specific strategy version should accumulate evidence before a human account owner considers any wider authority boundary.

The diagram below is the **target product sequence**, not a shipped end-to-end workflow. Current and next stages are separated in the table that follows.

```mermaid
flowchart LR
    O[Observe] --> S[Simulate]
    S --> R[Record]
    R --> C[Challenge]
    C --> Q[Qualify]
    Q --> B[Bound]
    B --> M[Monitor]
    M --> V[Revoke]
    V --> O
```

## What each stage means

### Observe · CURRENT

Read source-labelled market and consented account context inside exact scopes. Agent access requires an entitled, issued scope.

### Simulate · CURRENT

Run deterministic PAPER without venue-order capability. Human and agent stores are separate; agent PAPER is gated by entitlement and issuance.

### Record · CURRENT

Keep attributable context, intent, policy and outcome evidence. Activity is a partial foundation. Unified lineage is **NEXT**.

### Challenge · CURRENT

Test stale data, slippage, loss, drawdown, scope and other declared boundaries. These checks exist inside implemented PAPER and policy contracts. A broader harness is **NEXT**.

### Qualify · NEXT

Compare an exact strategy version against named evidence gates. No current qualification-to-promotion workflow exists.

### Bound · CURRENT

Issue a narrowly scoped, expiring mode after a separate human decision. Research, proposal and PAPER scopes are issued independently of qualification. Linking them to qualification is **NEXT**.

### Monitor · CURRENT

Observe activity, drift, degraded evidence and unknown outcomes. Activity is a partial foundation.

### Revoke · CURRENT

Stop or expire issued access without relying on the model. This applies to platform-operator-issued connections.

There is no automatic graduation. Qualification does not equal authorization, and authorization for one mode does not imply authorization for another.

## Strategy versions are the unit of proof

A result belongs to the exact strategy, mandate, data window, policy and simulator assumptions that produced it. Changing material behaviour creates a new version and returns it to the loop.

The **NEXT** Strategy Passport is planned to make that relationship portable by binding:

* strategy and version identity;
* human or agent creator attribution;
* allowed venues, symbols and accounts;
* mandate and risk-policy identity;
* model, prompt and tool configuration hashes where appropriate;
* PAPER sessions and evidence windows;
* cost and simulator limitations;
* violations, drawdown and unresolved inputs;
* lineage from prior or cloned versions.

The Strategy Passport is **NEXT**. It is not a current certification, performance guarantee or license to trade.

## Promotion is narrower than access

The long-term promotion model may distinguish research, PAPER, validated PAPER, shadow observation, testnet policy and bounded-capital modes. Each would require its own evidence and explicit human-owned gate. NYTSHIFT does not currently offer automatic shadow-live or mainnet-agent promotion.


---

# 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/qualification-loop.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.