All release walkthroughs

LIQUILENS · PLUGIN REVIEW EVIDENCE

Riptide

Five public research workflows, shown with actual captured MCP requests and results.

90 seconds · edited browser recording · no audio · no model API calls for this recording.

Inspect the interactive capture viewer · Case transcript · Recording manifest · Underlying service captures

What this demonstrates

The video shows direct calls to the public MCP service and preserves returned source dates, restrictions and unavailable states. It is not a native plugin-installation recording or a new model-routing test. Negative model cases remain unexecuted in this capture.

The product skill and negative model-routing cases are review expectations, not newly executed model tests. No trading, enrollment, collection, private-record access or execution was performed. NoiseFloor examples use synthetic inputs; all other values retain their service-provided dates and restrictions.

Cases shown

  1. Research overview

    Give me an evidence-based overview of Riptide, including available paper records, allocation date and canonical links.

    Interpretation boundary: Summarize returned state and dates, distinguish paper records, and retain health or availability limitations.

  2. Committed allocation

    Show the latest allocation committed by Riptide's independent daily paper job. Explain what its timestamp establishes.

    Interpretation boundary: Describe the committed paper allocation and its clock without presenting it as a live portfolio, recommendation or executed order.

  3. Paper performance review

    Review Riptide's core paper equity, return and drawdown. Preserve verification status and distinguish observed history from future expectations.

    Interpretation boundary: Use returned figures and periods, retain verification limitations and missingness, and make no profitability guarantee.

  4. Defensive coverage

    Summarize Riptide's latest defensive coverage aggregate and its evidence limits without requesting raw breach text.

    Interpretation boundary: Report the bounded aggregate with dates and limitations. Do not infer undisclosed breach details or complete protection.

  5. Methodology interpretation

    Explain Riptide's published methodology and safety boundaries before I interpret its paper results.

    Interpretation boundary: Ground the explanation in returned methodology and canonical links; distinguish research assumptions from validated future performance.

Endpoint: https://agents.seiche.info/products/riptide/mcp

Video SHA-256: 1e81f7490cfd92966c339962a38eaed9e131f743de2c0da8bc1543d0a25afe77

Draft review evidence. This page is not an OpenAI approval or publication receipt.