Energy datasets you can ask questions about.

Gridleaf dataset: ERCOT 4CP Monitor Tool: gridkit_ercot_4cp_monitor Sources: ERCOT load forecast, ERCOT storage/WSL, Gridleaf 4CP model Source readiness: Market-day monitoring / Operations screening Query contract: - Title: 4CP curtailment query contract - Primary entity: ERCOT load zone or facility - Time grain: 15-minute intervals - Visualization mode: Risk gauge + interval bars - Inputs: operating_date (date, required) e.g. today; site_or_zone (string, required) e.g. Houston data center; interval_load_mw (number, optional) e.g. 18 MW; curtailment_mw (number, optional) e.g. 4 MW - Example queries: Monitor 4CP risk for a Houston data center today with 18 MW load.; Which ERCOT intervals should I curtail if I can shed 4 MW? Analysis plan contract: - Version: gridleaf-analysis-plan.v2 - Dataset: ERCOT 4CP Monitor (ercot-4cp) - Tool: gridkit_ercot_4cp_monitor - Workflow: ERCOT 4CP Monitor baseline analysis - Output: Risk gauge + interval bars - Result preview: 4CP risk window result (4CP risk score) - Query contract: 4CP curtailment query contract (15-minute intervals) - Metrics: 4CP risk score, Estimated CP load, Headroom MW, Curtailment value - Sources: ERCOT load forecast, ERCOT storage/WSL, Gridleaf 4CP model - Source readiness: Market-day monitoring (Operations screening) - Source caveats: ERCOT settlement and WSL inputs can revise after the operating day.; Account exposure remains model-assisted until interval load and tariff data are attached. - Source next actions: Refresh source status before issuing a curtailment instruction.; Confirm facility interval load before treating modeled value as billing-grade. - Steps: Route the natural-language question to the right Gridleaf dataset. -> Run or prepare the matching Gridleaf portal tool with source-status caveats. -> Return a decision-ready answer and the next Claude or ChatGPT prompt. Result preview contract: - Title: 4CP risk window result - Chart: Interval risk - Primary metric: 4CP risk score - Fields: interval, risk_score, headroom_mw, curtailment_value_usd_per_mw - Example rows: 15:00 CT: 81 risk ($5.2k/MW); 16:00 CT: 94 risk ($7.8k/MW); 17:00 CT: 73 risk ($4.1k/MW) Dataset insight packet: - Version: gridleaf-dataset-insight.v1 - Contract key: dataset_insight - Dataset: ERCOT 4CP Monitor (ercot-4cp) - Tool: gridkit_ercot_4cp_monitor - Workflow: ERCOT 4CP Monitor baseline analysis - Visualization: Risk gauge + interval bars - Fields: interval, risk_score, headroom_mw, curtailment_value_usd_per_mw - Rows: 15:00 CT: 81 risk ($5.2k/MW); 16:00 CT: 94 risk ($7.8k/MW); 17:00 CT: 73 risk ($4.1k/MW) - Source readiness: Market-day monitoring (Operations screening) - Next queries: Monitor 4CP risk for a Houston data center today with 18 MW load.; Which ERCOT intervals should I curtail if I can shed 4 MW?; Should I curtail a Texas facility this afternoon?; Which intervals are most likely to become a 4CP event? Monitor ERCOT 4CP risk for a Houston data center today. Show peak-risk windows, WSL adjustment, curtailment value, and what I should ask Claude to analyze next. Return a concise analytical memo, call out source freshness and caveats, and suggest the next Gridleaf portal query. User question: Monitor 4CP risk for a Houston data center today with 18 MW load. query_contract: 4CP curtailment query contract Primary entity: ERCOT load zone or facility Time grain: 15-minute intervals Query inputs: - operating_date: today (required) - site_or_zone: Houston data center (required) - interval_load_mw: 18 MW (optional) - curtailment_mw: 4 MW (optional) Required inputs covered by provided values or contract examples. Return Risk gauge + interval bars with source_status_policy caveats, result_preview fields, and the next Gridleaf portal or Claude follow-up.