Illustrate prescriptive sensitivity and conflict analysis in templates

v1/README.md

@@ -11,15 +11,15 @@ This directory contains the templates for v1. Each template folder includes its
 | [book_slate_recommendation](./book_slate_recommendation/) | Recommend K books per reader and order them by slot, under diversity, freshness, and explainability constraints. |
 | [campaign_roi](./campaign_roi/) | Reallocate marketing campaign budgets across regions to maximize conversions, with per-campaign floor and cap constraints and a regional cap on a paused region. |
 | [cell_tower_coverage](./cell_tower_coverage/) | Select candidate cell tower sites and assign demand zones to maximize covered population under budget, tower-count, and capacity limits. |
-| [cicd_runner_allocation](./cicd_runner_allocation/) | Assign CI/CD workflow jobs to the cheapest compatible runner type, subject to concurrency limits, with scenario analysis across capacity levels. |
+| [cicd_runner_allocation](./cicd_runner_allocation/) | Assign CI/CD workflow jobs to the cheapest compatible runner type, subject to concurrency limits, with scenario analysis across capacity levels and conflict analysis to diagnose an infeasible outage. |
 | [commercial_underwriting](./commercial_underwriting/) | Run rules-based eligibility checks and risk-tier classification across a four-level commercial property/casualty hierarchy (insured entity, policy, location, coverage). |
 | [datacenter_compute_allocation](./datacenter_compute_allocation/) | Multi-reasoner template (chain follow-up to energy_grid_planning): heterogeneous-graph GNN classification of per-workload utilization probability, hardware-compatibility rules, dependency PageRank, and 24-cell scenario MIP for inside-the-fence GPU allocation across hyperscaler campuses. |
 | [demand_forecasting](./demand_forecasting/) | Forecast next-period unit sales per (store, item, day) with a regression GNN over a heterogeneous retail knowledge graph: sales transactions linked to stores, items, and item families so the GNN propagates signal through the store and product hierarchies. |
 | [demand_planning_temporal](./demand_planning_temporal/) | Plan weekly production and inventory across sites over a date-filtered planning horizon to minimize total cost while meeting demand. |
 | [diet](./diet/) | Select foods to satisfy nutritional requirements at minimum cost. |
 | [disease-outbreak-prevention](./disease-outbreak-prevention/) | Use weighted degree centrality to identify the highest-risk healthcare facilities in a public health network, considering both connection volume and intensity, to prioritize resource deployment during disease outbreaks. |
 | [energy_grid_planning](./energy_grid_planning/) | Multi-reasoner template: demand forecasting, grid vulnerability analysis, compliance rules, and multi-objective optimization for AI data center interconnection planning on the ERCOT (Texas) grid. |
-| [factory_production](./factory_production/) | Maximize profit from production with limited resource availability per factory. |
+| [factory_production](./factory_production/) | Maximize production profit under per-factory resource limits, then read the sensitivity marginals (capacity shadow prices and product reduced costs) from one solve. |
 | [financial_index_replication](./financial_index_replication/) | Prescriptive optimization template for selecting a sparse 20-stock replication basket and weights that track an S&P 500-like benchmark. |
 | [fraud-detection](./fraud-detection/) | Multi-reasoner transaction-fraud pipeline: account PageRank (Graph) + high-volume account flags (Rules) feed a GNN binary classifier (Predictive) whose per-transaction scores drive a knapsack investigator-budget MILP (Prescriptive). |
 | [hospital_staffing](./hospital_staffing/) | Explore the tradeoff between overtime cost and patient service level using bi-objective optimization with epsilon constraint. |
@@ -42,7 +42,7 @@ This directory contains the templates for v1. Each template folder includes its
 | [smoker_status_prediction](./smoker_status_prediction/) | Predict whether a person is a smoker from demographic and medical attributes plus a network of social connections, using a Graph Neural Network. |
 | [sprint_scheduling](./sprint_scheduling/) | Assign backlog issues to developers across sprints, minimizing weighted completion time while respecting capacity and skill constraints. |
 | [subscriber_retention](./subscriber_retention/) | Telco churn-risk scoring: PageRank over a Subscriber→Subscriber call graph (Graph) plus aggregate-derived call-volume features feed a regression GNN (Predictive) that scores per-subscriber churn risk, then surfaces the highest-risk subscribers per segment for retention campaigns. |
-| [supplier_reliability](./supplier_reliability/) | Select suppliers to meet product demand while balancing cost and reliability. |
+| [supplier_reliability](./supplier_reliability/) | Select suppliers to meet product demand at minimum cost, with sensitivity marginals and supplier-disruption scenario analysis. |
 | [supply_chain_resilience](./supply_chain_resilience/) | A multi-reasoner template that chains blast-radius reachability, graph analysis, rules-based classification, and prescriptive optimization to build a risk-adjusted minimum-cost network flow for supply chain routing. |
 | [supply_chain_transport](./supply_chain_transport/) | Minimize inventory holding and transport costs with TL/LTL mode selection. |
 | [synthetic_eligibility_records](./synthetic_eligibility_records/) | Generate K distinct, internally consistent member eligibility records per solve using a CSP solver in multi-solution mode: each record satisfies CMS Medicare-eligibility, age-by-plan-type CFDs, and PCP-network attribution. |