‹ Workflows
Demand prediction
● Active v23Owner: Maria Chen · Supply Chain VP · Created 2025-09-14 · 30-day rolling window · open agent UI →
Forecast accuracy · last 30 days
91.2%
↑ 5.4 pts vs baseline
Forecast accuracy
Baseline (no changes)
Approved improvement
Agent anatomy
View skill registry →
Skills active
9 versions
Tools available
7 tools
query_sap_sales(sku, region, years)
fetch_noaa_weather(region, weeks_ahead)
get_inventory_status(sku, store)
read_skill(skill_id)
run_pipeline(version_id, fold)
analyze_failures(run_id, k)
fire_markdown_alert(sku, severity)
Topology
Single-agent loop · proposer + gate · improvement loop wraps the agent
Multi-agent topology graph view shipping in Phase 2 (post-Demo-Day) — composing this workflow with the labour-management agent.
Entry point prompt
You are a demand-forecasting agent. Forecast weekly demand at SKU-store level. Flag SKUs likely to need markdown within 4 weeks. Read skills lazily via
read_skill. Cite sources for every forecast. view full →Active failure clusters · 3
View all →
Seasonal anomaly missed in winter footwear demand
forecast_demand(sku=BOOT-W42, region=PNW, week=2026-W45) → 312 units
actual: 1,847 units · markdown_alert fired W49 (4 weeks late)
actual: 1,847 units · markdown_alert fired W49 (4 weeks late)
Review proposal →
Gate: 12 / 12 passing
Promotional uplift underweighted on bundled SKUs
forecast for 4-pack bundle ignored 30% promo lift on parent SKU
3 SKU bundles affected · revenue exposure $128k
3 SKU bundles affected · revenue exposure $128k
Supplier delay impact missed for 12-week lead-time SKUs
Recent improvements · 30 days
Audit trail →
Seasonal anomaly fix
+1.1 pts
Supplier price bake-in
+1.4 pts
Regional variance fix
+1.2 pts
Promotional uplift handler
+1.7 pts
Trace volume · 7d
2,841
Avg 406 / day · 0 dropped
Eval coverage
128 cases
38 cluster-derived · 90 hand-picked
Gate pass rate · 30d
100%
12 approvals · 0 rolled back
Skill versions
23
9 active skills · last update 2h