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.
What this demonstratesThe 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.
- Synthetic A/B comparison
Use NoiseFloor to compare synthetic A/B results: group A has 40 successes out of 100, group B has 55 out of 100. Explain uncertainty.
Interpretation boundary: Use the declared synthetic counts with the advertised schema and explain effect, uncertainty and test assumptions; do not claim causality from this example.
- Synthetic change check
Use NoiseFloor to check whether this synthetic chronological series changed: [10,11,9,10,12,10,9,11,20].
Interpretation boundary: Use the supplied values without adding observations. Report change evidence and sample limitations without declaring a structural change certain.
- Synthetic forecast interval
Use NoiseFloor to forecast the next value of this synthetic series with nominal coverage 0.8: [10,11,10,12,11,13,12,13,14,13,15].
Interpretation boundary: Use the supplied values and nominal 0.8. Explain the returned interval, assumptions and any insufficiency rather than promising realized coverage.
- Sampling-size sensitivity
Use NoiseFloor to inspect whether this synthetic series could reflect sampling variation. Values: [10,11,10,12,11,13,12,13,14,20]; sample sizes: [100,110,100,120,110,130,120,130,140,200].
Interpretation boundary: Use both aligned arrays as supplied, retain warnings and distinguish sampling evidence from a causal explanation.
- Chronological forecast scoring
Use NoiseFloor to score forecasts on this synthetic chronological series: [10,11,10,12,11,13,12,13,14,13,15,14,16,15,17,16,18,17,19,18,20].
Interpretation boundary: Use the 21 supplied observations with chronological evaluation, explain baselines and sample limitations, and do not claim future investment performance.
Draft review evidence. This page is not an OpenAI approval or publication receipt.