Calibrated grid intelligence

Calibrated grid intelligence for energy capital.

Loom Light builds the probabilistic engine for pricing renewable assets in a grid-constrained world. Used by insurers, infrastructure investors, lenders, and developers to forecast and stress-test the parts of a project's economics that the grid increasingly determines.

Get in touch See how it works

Approach

The price of energy is becoming the price of the grid.

For most of the last century, the dominant variables in energy project economics were fuel costs and wholesale prices. Marginal costs are now collapsing. The variables that increasingly determine project value sit on the grid side: where the network binds, how curtailment evolves, what connection risk looks like, what locational and ancillary services pay.

Pricing this layer with the rigour that financial decisions require needs network models calibrated against measurement, with uncertainty quantified at every step. That is the infrastructure Loom Light is building.

Product

What we do.

Loom Light is a forecasting and scenario platform for grid-side risk on renewable assets. Three product modules sit on a shared calibrated engine. Curtailment is available today. Connection risk and harmonics are in development.

Curtailment forecasting

Available

Per-asset and per-portfolio curtailment forecasts, conditional on scenarios the user controls: connection date, dispatch strategy, reserve held back, neighbouring connections, future build-out. Outputs include central forecasts, sensitivity to each scenario lever, and confidence bounds calibrated against measured network behaviour. Designed for use in underwriting, investment committee papers, and refinancing reviews.

Loom Light curtailment forecasting product, showing a BESS site forward curtailment forecast with scenario controls (ancillary energy reserve, hybrid dispatch, attrition, period, confidence) and a year-by-year distribution chart with P5–P95, P25–P75, and P50 bands.

Curtailment forecasting for a 99.8 MW BESS at a constrained GSP. Scenario controls on the top; year-by-year forecast with confidence bands on the right.

Connection risk forecasting

Coming soon

Forecasts of connection timing and as-built export capacity, accounting for queue position, network reinforcement plans, and the realistic variance around DNO and TSO programmes. Replaces the binary "queued versus not queued" view with a quantified timing forecast that infrastructure capital can model into IRR and debt covenants.

Harmonics risk forecasting

Coming soon

Forward-looking forecasts of harmonic distortion and compliance risk for BESS and inverter-based assets, accounting for the local network and the evolving generation mix in the vicinity. Designed to support retrofit budgeting, connection compliance, and pre-FID risk allocation between developer and equity.

More modules are on the roadmap. If your team is grappling with a grid-side risk question we have not yet listed, we want to hear from you.

Tell us about your problem →

For insurers and ILS funds

Underwrite the grid side of an energy project.

Parametric and structured products on renewable assets — curtailment cover, revenue floors, connection-delay triggers — require probabilistic inputs that conventional planning models do not provide.

Loom Light supplies calibrated forecasts and stress-tested scenarios that can be attached to trigger design, attachment points, and capital reserve calculations.

Trigger and attachment design

Quantify the underlying loss distribution that triggers, attachments and limits are written against, with explicit uncertainty bounds on each parameter.

Capital reserve evidence

Reproducible, auditable forecasts of grid-driven loss that can be referenced in capital adequacy and reserve calculations.

Portfolio aggregation

Aggregate calibrated forecasts across a book of renewable risks, exposing correlation and concentration that single-asset modelling hides.

For infrastructure investors and lenders

An independent, auditable view of grid-side risk.

Investment committees and credit teams need forward-looking, scenario-tested views of curtailment, connection timing and ancillary exposure that survive technical due diligence.

Loom Light provides these as an interrogable platform: every forecast is reproducible, every assumption visible, every sensitivity quantifiable on demand.

Investment committee evidence

Forward-looking forecasts that can be modelled into IRR, downside scenarios and base case sensitivities, with assumptions visible end-to-end.

Debt covenant structuring

Quantified grid-side risk views that support cover-ratio definitions, reserve account sizing, and trigger events tied to operational reality.

Portfolio screening

Run consistent calibrated forecasts across a pipeline of assets to identify which sites carry grid risk that has not yet been priced into the deal.

For developers and IPPs

Forecast the grid-side economics of your pipeline.

Screen sites against calibrated network models. Stress-test curtailment under realistic forward scenarios. Quantify the connection-timing risk that equity and debt counterparties will model against.

Useful at site selection, FID, PPA negotiation and refinancing — wherever a grid-side number needs to survive scrutiny.

Site selection

Compare prospective sites on a like-for-like calibrated basis, before committing capex or paying for site-specific consultancy work.

FID and financing

Forecasts and sensitivities your counterparties can interrogate, supporting financing conversations and trigger negotiation rather than disputing them.

Operational planning

Translate forward curtailment expectations into dispatch and reserve strategy, and into a quantified case for hybridisation or co-location.

For network operators

Where your models diverge from reality.

Loom Light's engine produces a probabilistic audit of where a CIM model is well-identified by available measurements and where it is not.

This supports monitoring strategy, flexibility market design, and hosting capacity decisions where overly conservative defaults are leaving capacity on the table.

Model quality diagnostics

A probabilistic map of which parameters of your network model are well-identified by measurement and which are not.

Hosting capacity with uncertainty

Hosting capacity figures with calibrated uncertainty bounds, not just worst-case numbers, so headroom can be released defensibly.

Monitoring strategy

Identify which measurement locations would reduce model uncertainty the most, so each new monitor is placed where it delivers the greatest value to inference.

Team

The right mathematical combination for this exact problem.

Leonie Mueck

Co-founder & CEO

Leonie started her career solving the Schrödinger equation so accurately that computations were often too large for classical computers. That fascination with hard computational problems took her from a PhD in quantum chemistry to the editorial desk at Nature, where she handled research across the physical sciences as Senior Editor. She then moved into deep tech product leadership: first as CPO at quantum computing startup Riverlane, then as VP Product at nPlan, where she built probabilistic intelligence products for infrastructure, forecasting outcomes on some of the world's largest construction and energy projects. That experience taught her what it takes to turn rigorous mathematics into tools that real engineers trust and buy. She founded Loom Light because the electricity grid deserves the same.

Deepanshu Kush

Co-founder & CTO

Deepanshu has spent his career proving what computers fundamentally can and cannot do. After studying mathematics at IIT Bombay, he completed a PhD in computational complexity theory at the University of Toronto, where he established new fundamental limits on algorithms for core graph problems. He is now a postdoctoral research associate in Computer Science at the University of Cambridge, working on algebraic aspects of computation. His research sits at the frontier of theoretical computer science, combinatorics, and their connections to other areas of mathematics. At Loom Light, he's channelling that rigour into a different kind of network problem: bringing provably sound mathematical methods to power grid modelling, where the gap between what models assume and what physics demands has real consequences.