Kortex
snapshot · 2026-07-18
Kortex · applications · what customers operate

One graph. Six workflows.

Applications are what customers buy and operate; the insight pages are published research proving the same graph discovers non-obvious relationships. Kortex leads with one application, large-load siting, and every additional workflow below runs on the identical substrate: the same identities, topology, market series and evidence discipline. A relationship validated for one application strengthens all of them. The substrate underneath is the full estate; 541 governed datasets from 152 registered sources, refreshed continuously, every one licence-tracked and retrievable (coverage register).

★ Primary application

Large-load siting

Eliminate weak data-centre and large-load candidates before commissioning utility, engineering and property studies. Bring a shortlist; Kortex re-ranks it against installed dispatchable low-carbon capacity, EHV topology, wholesale price, water stress, queue evidence (where it exists, zones without it say so) and counterparty ownership, every score traceable, every rejection reasoned, the whole answer receipted.

Additional applications
same graph, same evidence discipline; different standing question

Infrastructure due diligence

"Before we buy this plant, portfolio or utility; what would we wish we had known?"

Fleet composition on the canonical operational universe, revenue-mix exposure, cooling-water dependencies (validated US subset), queue history where the assets sit, and the ownership chain to the ultimate parent; as one screen instead of five datasets.

infrastructure funds · lenders · project finance · strategic buyers

Ownership intelligence

"Who ultimately owns this infrastructure; and what else depends on the same counterparty?"

GLEIF-anchored entity resolution with blind-validated precision (96.7% family / 73.3% exact-entity on the manual tier, published), parent chains checked against issuers' own Exhibit 21 filings, abstention by default on weak stitches; a confident false identity is worse than none.

diligence teams · risk · compliance · counterparty exposure

Portfolio risk

"Our assets are diversified on the map. Are they diversified in physics?"

Common-mode exposure a map hides: cooling-water systems that fail in the same drought, weather positions that co-move, capture-rate erosion as penetration rises. Weather concentration is research-preview until measured correlations land; and is labelled so.

renewable funds · IPPs · insurers

Grid intelligence

"What does this grid actually pay, hour by hour; and what gets built in it?"

The market-timing suite as one product: a grid's day (capture prices per fuel), hourly clean-supply structure, a decade of capture-rate decline, and queue-cohort reality; observed series, deterministically joined, receipted.

utilities · consultants · traders · developers

Infrastructure groundingEARLY

"Give our agents ground truth about the physical world; with receipts."

The same graph as an agent surface: MCP server, deterministic answers, per-metric evidence classes, frozen retrievable receipts and fail-closed rights modes. Built for autonomous workflows that must cite what they claim. Early; the contract is real, the tooling around it is still growing.

agent builders · AI platforms · research tools

Questions the applications are built to answer

Worked results below were verified against the linked endpoints as of the 2026-07-18 snapshot. The graph refreshes continuously, so figures drift between snapshots; the endpoints always return current values with source provenance.

Which utilities pair the lowest interconnection-queue completion with the largest fossil-generation base in the same grid zones?
Traverses: LBNL queue completion data × generator revenue × corporate ownership × grid topology.
Result: a ranked exposure list; the utilities combining bottom-decile queue clearance (e.g. ~1.5% of projects built since 2015) with the most fossil generation concentrated in their own zones, i.e. the cohort most exposed to FERC Order 2023 queue reform. Ranking is the product; the revenue attached to each row is a modelled screening estimate for comparison, not audited financials (see methodology).
Where should a hyperscaler site a data centre for the cheapest clean power?
Traverses: wholesale prices × generation fuel mix × queue pipeline × grid capacity × climate risk.
Result: Norway NO4 at ~$12/MWh wholesale, 1% dirty share, 8.5 GW installed dispatchable low-carbon capacity in zone; screening evidence for a connection study, not confirmed headroom.
Which operators claim clean energy but earn over 90% revenue from fossil?
Traverses: generator fuel type × 3-layer revenue model × GLEIF corporate hierarchy × entity resolution.
Result: a ranked operator list with the fossil/clean revenue split per operator; every row traceable to its source data and testable against public filings.
The hierarchy is deliberate: applications are workflows customers operate; insights are published research demonstrating the graph generalises; evidence proves both can be trusted; coverage, validation (misses included), sources, licensing and receipts. The graph is the platform underneath; it is never the product. Start a pilot.