The grid runs on rules. Its AI agents should know them.
The Operational Context Graph for energy and utilities — generation, transmission, distribution, ISO/RTO ops, retail. Agents that cite the standard. Healthcare ships today. Energy ships Q4 2026. The design-partner cohort is open — shaping the ontology before GA.
Every Amandil OCG carries the same dimensions — public-data spine, reference standards, regulatory frameworks, canonical operational example. The substance is per-vertical. Healthcare is live today; energy ships Q4 2026.
The same two sides as the live healthcare graph — the knowledge an agent reasons from, and the guardrails that govern what it does — instantiated for generation, transmission, distribution, ISO/RTO ops, and retail. Final scope shaped with the design-partner cohort.
L1 domains across power, gas, renewables, and retail. Reference processes with owners, metrics, and dependencies. Anchored to NERC CIP, IEEE 1547, NEMA, IEC 61850. Stitched to FERC eLibrary, NERC standards, EIA datasets, ISO/RTO settlement data.
FERC, NERC, NEPA, PHMSA, OSHA. Tariff filings, audit checkpoints, escalation paths. Reliability standards and operating procedures. Trace coverage on every agent action.
Three example archetypes shown on the healthcare page — Reconstructor, Pattern Analyzer, Submission Compiler — illustrate shapes the substrate produces. Each will be tuned to the energy substrate with the cohort.
Rebuilds an incident package from ISO/RTO event data, asset history, severity classification, and the NERC EOP reporting requirement that applies.
Classifies curtailment events against tariff schedules, prior-restoration patterns, peer responses, and the policy clauses each event type maps to.
Assembles a regulator-ready FERC Form 1 (or equivalent state filing) from the utility's operational data, cited against every line item's source instruction.
The same three customer segments that anchor every Amandil vertical. Operators run the grid. Advisors compress discovery into branded analysis. Build partners embed the graph into their products.
"Where should we invest in AI?" You run the grid — generation, transmission, distribution, ISO/RTO ops, retail. Most teams pick what to automate based on a vendor pitch or what feels problematic to an executive. You need a benchmark-anchored answer — and agents that cite NERC, name the operating procedure, and return the audit trail.
You get: diagnose against the energy benchmark library → prioritize by automation score reweighted by your gaps → simulate the top candidates → ship agents grounded in the graph via MCP.
"How do we scale our energy AI engagements?" Every project opens with a discovery phase. Weeks rebuilding the same outage workflow, the same NERC submission, the same ISO interconnection study. The sameness goes unclaimed — and the artifact ages on contact with reality.
You get: the discovery phase compressed to a 30-minute branded analysis. White-label per client. Branded blueprints, business cases, diagnostics. Multi-client workspaces with scoped grants.
"What grounds our energy AI features?" You're shipping AI inside your product. Every LLM-integrated feature hits the same wall — the model has no grounded knowledge of how a utility, generator, or grid operator runs. Building the graph yourself is a multi-year, multi-million-dollar undertaking.
You get: a native MCP server. OAuth 2.0 plus headless bearer tokens, instantly revocable. Grant-scoped per partner. Versioned, validated graph surface. Multi-year build, solved on day one.
Generation, utility, or ISO operators preferred. Design partners shape the ontology, get the substrate at cost during the cohort window, and lock pricing for two years post-GA. We don't take partners we can't deeply serve.
Tell us where you sit — where the AI-vs-ops gap is sharpest, what regulation pins your team down, and what you'd want the first agent to do. We'll come back with a roadmap shaped to that.