GridCORTEX Live · Scenario Demo #5  ·  ← All Demos
On this page What you are watching The business case Run this at your utility Where you see it and how you say yes

The Rate Case Synthetic Data · Simulation

A $1.2 billion, five-year capital plan heads into a commission that disallowed 8% of the last one. Watch GridCORTEX score all 240 candidate projects by risk-reduction-per-dollar, expose the plan sitting 23% below the efficient frontier, and (with a human approving every move) reallocate the same budget onto the frontier, then generate the testimony-ready evidence pack that survives cross-examination. Same dollars. More risk retired. Zero disallowed.

WEEK 0
PLAN ASSEMBLY
⏳ DECISION POINT: TIME SLOWED
SYNTHETIC DATA
In current plan Swapped in (optimized) Swapped out Not funded Efficient frontier

Same $1.2 billion. Two very different orders.

What risk-based capital allocation is worth in front of a commission
,
Risk retired, same budget
,
Disallowed capital
,
Data request turnaround
The Plan: Risk & Reliability
WithoutWith GridCORTEXΔ
The Case: Regulatory & Cost
WithoutWith GridCORTEXΔ
Illustrative simulation on synthetic data; project costs, risk scores, and regulatory outcomes are placeholders. In a GridCORTEX pilot, the frontier is computed from YOUR asset twins, outage history, and project catalog, and backtested against your last filed plan. See UC 14.2 "Demo and Proof Plan."
240
Candidate projects
61
Risk retired (index)
$1.20B
Five-year budget
HIGH
Disallowance exposure
Intelligence Feed, read-only · human-in-the-loop
W0
Optimize
File
Hearing
Order · W16
The Validated Use Cases Behind This Scenario
UC 14.2
Grid Investment Justification
Every project quantified by risk retired per dollar; the efficient frontier your capital plan should sit on.
UC 14.4
Data Request Response Factory
47 intervenor questions answered in days, from the same model that built the plan, the filing and the evidence never disagree.
UC 4.4
Asset End-of-Life Economics
Why 38 age-based replacements came out of the plan: the twins say those assets have life left.
187 UCs
One Framework
The Rate Case is one of 187 validated use cases across 10 solution areas and 23 utility domains.
Inside the Demo
What you are watching, and what it proves

The scenario follows a fictional utility taking a $1.2 billion, five-year infrastructure spending plan into its state utility commission, the regulator that decides whether customers' rates can pay for that spending. Last time, the commission refused to let 8% of the plan be recovered from customers (a "disallowance", which shareholders absorb), and it has warned it will look hard at projects justified only by equipment age. The plan is 240 candidate projects gathered from nine departments' wish lists, and the simulation runs 16 weeks, from assembling the plan to the commission's final ruling. In Week 1, GridCORTEX reads the working computer models of the utility's real equipment (fed by oil tests that reveal a transformer's internal health, loading data, and inspections), ten years of outage records, wildfire and flood exposure by location, and demand growth. It then scores every one of the 240 projects the same way: how much risk does each dollar spent actually remove? The answer lands in Week 1.6: the current plan removes 61 risk points, but the same $1.2B, allocated to the best projects, would remove 75. The plan is 23% below the best available line, meaning nearly a quarter of its risk-reduction potential is being wasted. The cause has a name: 38 funded projects replace equipment purely because it is old, even though its condition data says it is healthy, while the territory's genuinely riskiest equipment sits unfunded.

Two decision points ask for human approval. The first, around Week 3, is the reallocation: 38 age-only projects out, 51 higher-risk projects in (burying lines in wildfire zones, rebuilding the worst-performing local circuits, and 12 new tie switches, which let a neighborhood be fed from a second direction when its usual line fails). Same budget, and every swap carries a written justification. Approved, the portfolio moves from 213 to 226 projects. The projected payoff: the average customer's outage time drops 9 minutes per year, and the modeled chance of utility equipment starting a wildfire drops 31% in the highest-risk zones. The second decision, around Week 5, is the evidence pack: 214 per-project exhibits totaling 1,900 pages, a methods document written for the hearing room, every number traceable back to the sensor reading or record behind it, and pre-drafted answers to the 40 questions this commission has historically asked, mined from its past cases.

Then the case plays out. The plan is filed in Week 6. In Week 8, 47 formal written questions arrive from the commission staff and outside challengers; they are answered from the same model in 4 days, where the same job historically took six weeks across nine departments. At the Week 11 hearing, a staff engineer cross-examines the risk methods for three hours, and every challenged number traces cleanly to an equipment reading, an outage record, or a work order. The ending, in Week 14: the plan is approved with zero dollars disallowed, the ruling citing "a transparent, quantified risk methodology." Skip the approvals and the same case ends in Week 15 with $96 million disallowed, because "the equipment was old" did not survive cross-examination.

Without GridCORTEX

The plan is nine departments' lists stapled together, never scored on one common risk scale, with equipment age standing in for actual risk and filing numbers living in spreadsheets that disagree with each other. Consumer advocates and other outside challengers attack the 38 healthy-equipment replacements as wasteful spending, "replacement by birthday, not by risk," and the utility's rebuttal can only cite engineering judgment, because the numbers were never computed. The commission staff recommends cutting 8%, and the ruling takes $96M out of the plan. Shareholders absorb the loss, the reliability work that money funded slips a full multi-year cycle, preparing the filing costs 3,800 staff-hours, answering the formal questions takes 6 weeks across 9 departments, and the next rate request starts from a credibility hole.

With GridCORTEX

The software reads the equipment condition data, outage history, and hazard maps, scores all 240 projects on one risk-per-dollar scale (use case UC 14.2), and computes the best possible allocation of the same budget. Equipment lifetime economics (UC 4.4) show which age-based replacements do not earn their slot, and the question-response factory (UC 14.4) answers all 47 formal questions in 4 days from the same model that built the plan, so the filing and the evidence can never disagree. Humans decide everything: the planning committee approves every project swap, and the regulatory affairs team owns the filing. The result: the same $1.2B removes 23% more risk, filing preparation drops to 940 staff-hours, cross-examination finds no gaps, and the ruling approves the plan with $0 disallowed.

The key numbers (KPIs), side by side
KPIWithout GridCORTEXWith GridCORTEXDelta
Risk retired ($1.2B)how much risk the $1.2 billion actually removes, scored on one comparable scale61 index pts75 index pts+23%
Plan positionwhere the plan sits against the best possible risk-removed-per-dollar allocation23% below frontierON the frontierno risk-reduction wasted
Projected SAIDI trajectorySAIDI is the industry measure of outage minutes the average customer suffers per yearflat−9 min / yrreliability up
Wildfire ignition risk (top zones)the modeled chance that utility equipment starts a fire in the highest-risk areasbaseline−31%resilience up
Healthy-asset replacements fundedprojects that replace equipment because it is old, even though its condition data says it is healthy380spending follows risk only
Worst-risk unfunded projectsthe highest-risk fixes the original plan left out entirelystay unfunded51 fundedgap closed
New tie switches into the networkswitches that let a neighborhood be fed from a second direction when its usual line fails212more ways to restore power
Capital disallowedspending the commission refuses to let the utility recover from customers; shareholders absorb it$96M$0−$96M
Filing preparationstaff time to assemble the regulatory filing and its evidence3,800 staff-hours940 staff-hours−75%
Data request turnaroundhow fast the utility answers the formal written questions regulators and challengers ask6 weeks · 9 departments4 days · one model−93%
Hearing exposurehow the plan holds up under live cross-examination in the hearing roommethodology challengedevery number tracedno gaps found
Settlement positionwhether the utility must negotiate its plan down to avoid a worse rulingweak; staff recommends cutnone neededfull approval
Next-cycle starting pointthe reputation the utility carries into its next rate requestcredibility repairprecedent settrust carries forward
Reliability work slippedapproved reliability projects delayed because their funding was cutone full cyclenonecustomers win
Live numbers (KPIs) on the dashboard
Candidate projectsThe number of projects in play. It starts at 240 candidates and settles at 226 funded projects once the swap (38 out, 51 in) is approved. The count matters less than what is inside it: after the swap, every funded project earns its place on risk.
Risk retired (index)The plan's total risk-removal score on the one comparable scale. Higher is better: 61 is the original stapled-together plan, and 75 is the same money doing 23% more good.
Five-year budgetThe fixed $1.20B. This number never moving is the point of the demo: the improvement comes from choosing better projects, not from asking for more money.
Disallowance exposureThe gauge of how much spending the commission might refuse to let the utility recover. LOW is the good reading, earned by the evidence pack; HIGH is the age-based defense, and it hardens into a real $96M loss if the recommendations are ignored.

The Business Case: Safety, Hours, and Cost

A utility does not buy a demo. It buys a safety exposure that goes away and a cost that goes down. Below is that case for every use case behind The Rate Case, written the way a plant manager, a safety lead, and a CFO each need to read it. Every hour and every dollar is a formula you run with your own rates and volumes. There are no vendor benchmarks in here and no invented percentages. If a number is not yours, it is not a number.
UC 14.2 Grid Investment Justification Generator

What happens today, without this

A capital planning analyst maintains the project workbook: cost estimate, load forecast, asset condition scores, outage history, and alternatives considered. When a filing needs the justification, the analyst exports tables and writes narrative in a word processor, then regulatory affairs rewrites that narrative into the framework the commission actually uses, whether that is resilience, equity, or emissions. Every figure in the prose is checked back to the workbook by eye. When the cost estimate moves, and it always moves, the same numbers have to be found and edited by hand in several paragraphs and an executive summary.

What it replaces or shrinks

  • Manual transcription of project workbook figures into narrative prose
  • The rewrite pass where regulatory affairs translates engineering language into the commission's framework
  • Hand checking each narrative figure back to the spreadsheet and the asset system of record
  • Manual re-editing of narratives after a cost estimate, scope, or in service date change
  • Shrinks the search through prior filings for the language and positions you have already defended
  • Shrinks the executive summary rewrite that happens every time a number moves

Why it is safer

The safety effect is indirect and downstream, and it should not be counted in the business case. Better justified investments get approved, and some of those investments are the hardening and automation projects that remove field exposure. That is a real chain but it is long, and the honest position is that the drafting work itself changes nobody's exposure.

Counted in units you already track:

  • Road miles driven, moved only in that fewer in person planning and drafting workshops are needed to reconcile numbers
  • Elevated work hours and energized area entries: changed only downstream if and when a funded project actually removes the work, and we recommend you do not count that here
  • Confined space entries: unchanged by this use case

Man-hours it gives back

Drafting and reconciliation hours come back to capital planning, and the regulatory writers stop spending their time translating and start spending it on framing and strategy.

HOURS AVOIDED PER YEAR = justification narratives per filing year x current drafting hours each, plus review cycles per narrative x hours per cycle x reviewers in the chain, plus scope or estimate changes per year x rework hours per change, minus the planner and regulatory reviewer time still spent on judgment, framing, and the argument itself.

The numbers we need from you to run that formula:

  • Number of investment justification narratives produced per filing year
  • Current drafting hours per narrative and the number of reviewers and review cycles each goes through
  • Cost estimate or scope changes per year that trigger narrative rework, and the hours each rework costs
  • Consultant fees currently paid for narrative preparation, if any
  • Loaded hourly rates for a capital planning analyst, a regulatory writer, and an engineering reviewer

Where the dollars come from

Cost driverHow it is calculated, from a rate you supply
Capital planning labordrafting and reconciliation hours avoided x your loaded planner rate
Regulatory writing and reviewtranslation and review hours avoided x your loaded regulatory writer and attorney rates
Consultant narrative preparationconsultant hours or fixed fees you stop paying for narrative work x your contracted rate
Rework from figure mismatchescorrection cycles avoided x hours per cycle x the loaded rates of the people in the chain, plus the cost of any supplemental filing a mismatch would have forced
Capital timingyour own carrying cost of a project that slips a rate cycle because its justification was not ready. You supply the carrying rate and the probability. We will not estimate either.

Reliability and maintenance

Reliability
This does not move a reliability metric by itself. What it affects is whether the reliability and resilience investments your engineers have already justified technically get funded on the schedule they were planned for, which is a real but indirect connection and should be presented that way.
Maintenance
The maintenance effect is on the document set, not on plant. Because every figure traces to the workbook and the asset system, a change in the estimate propagates instead of being hunted, and the narrative library stays consistent with what you have actually filed.

What else it moves

ComplianceEvery figure in the narrative traces to a source record, which is the first thing a prudence review or a discovery request asks you to demonstrate.
CustomerA clearer, consistent explanation of what customers receive for a given investment, in the framework the commission uses, rather than engineering prose that intervenors reinterpret for you.
WorkforcePlanners spend their time on alternatives analysis and estimating rather than on prose formatting, which is what you hired them for.

What it costs you, stated honestly

You pay for the scoped engagement that builds and runs this, for the integration that reads your project workbooks, asset records, and prior filings, and for the time your planners and regulatory writers spend verifying the first set of generated narratives line by line. Expect that verification to be slow at first and to get faster once the team trusts the traceability. Budget the first filing season as a review cost, not a savings.

How to build the payback case

Payback is normally driven by planner and regulatory writer hours plus any consultant narrative fees you stop paying. Capital timing is the biggest number in the model and the least defensible one, so present it separately and let your finance team decide whether to count it at all.

This is a planning model built from your narrative counts, drafting hours, review chains, and loaded rates, not a vendor claim. Re-run it with the actual edit effort recorded in your first filing season.
UC 14.4 Rate Case Data Request Response Factory

What happens today, without this

During an active rate case, discovery analysts work a queue of hundreds and sometimes thousands of data requests. Each one is assigned to a subject matter expert, often an engineer or an accountant pulled off their normal work, who searches for the underlying workpaper or record, drafts an answer in the template, and routes it to an attorney. Deadlines live on a spreadsheet that drives a daily status call. Whether two answers contradict each other depends on whether the reviewing attorney happens to remember the earlier one. Through the peak of discovery, weekends disappear for the case team and for the experts they keep pulling in.

What it replaces or shrinks

  • Manual routing of each data request to the right subject matter expert and the daily chasing that follows
  • Manual retrieval of the workpapers, testimony, and prior answers that support each response
  • Attorney memory as the consistency mechanism across hundreds of answers
  • The spreadsheet deadline tracker and the daily status call built around reading it aloud
  • Shrinks the first draft, which today the expert writes from scratch rather than editing from a cited draft
  • Shrinks the rework and supplemental responses caused by an inconsistency discovered after service

Why it is safer

The mechanism is fatigue and diverted attention, not physical exposure, and we will not dress it up as anything else. Peak discovery runs the case team and its experts on sustained overtime for weeks, and several of those experts are operating and planning engineers whose day job is approving and scoping field work. Hours returned to them are hours available for the work that does carry exposure.

Counted in units you already track:

  • Night driving hours for the case team and its experts during peak discovery weeks
  • Road miles driven to a case war room, where one is stood up in a separate location from normal offices
  • Energized area entries and elevated work hours: unchanged directly, though engineer hours returned to operations are hours available to plan and supervise that work properly

Man-hours it gives back

Research and drafting hours come back to the subject matter experts who are pulled off engineering and accounting work, and attorney time shifts from hunting for inconsistencies to judging the ones that are flagged.

HOURS AVOIDED PER YEAR = data requests per case x subject matter expert research hours per request, plus attorney review hours per request, plus consistency review hours per batch x batches per case, plus deadline tracking and status call hours per week x case weeks, minus the expert and attorney time still spent verifying and releasing each drafted response, which stays with the humans by design.

The numbers we need from you to run that formula:

  • Data request volume and case duration in weeks from your last comparable rate case
  • Subject matter expert research hours and attorney review hours per data request
  • Number of responses in that case that required correction or supplement after service, and the hours each correction cost
  • Contract or temporary discovery support weeks purchased in that case, and the agency rate
  • Loaded hourly rates for a subject matter expert, a discovery analyst, and an in house attorney, plus your outside counsel billed rate

Where the dollars come from

Cost driverHow it is calculated, from a rate you supply
Subject matter expert laborresearch hours avoided x the loaded rate of the group the expert comes from, which is usually engineering or accounting, not legal
Attorney reviewreview and consistency checking hours avoided x your loaded in house rate and your outside counsel billed rate, split the way your case is actually staffed
Contract discovery supporttemporary analyst weeks avoided x your agency rate
Rework and supplemental responsescorrections avoided x hours per correction x the loaded rates of everyone in the correction chain
Case exposureyour own estimate of what one inconsistent answer costs when it becomes cross examination material. Your legal team sizes this, not us, and many utilities choose to leave it out of the base case entirely.

Reliability and maintenance

Reliability
This does not touch reliability metrics. The operational connection worth naming is that the experts consumed by discovery are frequently the same engineers who plan, scope, and approve field work, so a rate case quietly builds an engineering backlog. Returning their hours shortens that backlog, which is a real effect but not one to put a SAIDI number on.
Maintenance
The answer library is maintained across cases rather than abandoned in a folder of PDFs at the end of each one, so the next case starts from a curated record of what you have already said, under oath, on every recurring topic.

What else it moves

ComplianceEvery response carries its evidence and its consistency check on the record, so the file you hand to an auditor or to the next case team explains itself.
WorkforceThe weekend burn through peak discovery is a retention problem for both the regulatory team and the engineers repeatedly conscripted into it. This is the single most common complaint from rate case staff and it is worth naming in the business case.

What it costs you, stated honestly

You pay for the scoped engagement that builds and runs this, for ingesting your testimony, workpapers, and the answer record from prior cases, and for the integration into your document management system. The largest cost you carry is your own experts' and attorneys' time to verify drafted responses closely during the first batches, until the team has calibrated how much checking each type of request actually needs. Do not plan to skip that stage.

How to build the payback case

Payback is carried almost entirely by subject matter expert hours and attorney review hours in a single active case, which is why utilities usually build this case on their last rate case and not on an annual average. Case exposure and rework are real but keep them as upside.

This is a planning model built from your last rate case's data request volume, effort per request, and loaded rates, not a vendor claim. Re-run it against the actuals from your first batch of live responses before you extend it to the whole case.
UC 4.4 Asset End-of-Life Economics Optimizer

What happens today, without this

The capital plan is assembled once a year by an asset management director working from lists each department submits. Run to failure, replace, and refurbish get decided asset class by asset class, usually by whoever owns that class, and the tradeoff is argued in a meeting rather than computed. Lead times, outage cost, and remaining life live in three different systems. When the budget number moves, the plan is trimmed from the bottom of the list instead of re optimized, which quietly changes the risk you are carrying without anyone deciding to.

What it replaces or shrinks

  • The manual roll up of departmental capital submissions into a single plan
  • Asset by asset argument over replace versus refurbish versus run to failure
  • The separate spreadsheet tracking supplier lead times against planned in service dates
  • The bottom of the list trim that stands in for reprioritizing under a budget cut
  • Shrinks hand built budget scenarios, since finance still sets the number and still decides

Why it is safer

This one is indirect and should be described honestly: the optimizer never touches a work site. What it changes is how much of the fleet is deliberately allowed to run to failure, and every run to failure decision that turns out wrong becomes an emergency job. Fewer of those means fewer crews working unplanned, at night, on equipment nobody scoped in advance.

Counted in units you already track:

  • Switching operations performed on emergency rather than planned work orders
  • Night driving hours associated with emergent replacement work
  • Permits to work issued under emergency provisions rather than normal planning
  • Energized area entries for unplanned substation and field replacements

Man-hours it gives back

Plan assembly and scenario building hours come back to asset management and capital planning, and the director spends the season defending a plan instead of building one.

HOURS AVOIDED PER YEAR = planning cycles per year x hours spent assembling and reconciling the plan x people involved, plus budget scenarios requested per cycle x hours per scenario, minus the review hours the director and finance still spend adjudicating the ranked output asset by asset.

The numbers we need from you to run that formula:

  • Hours spent assembling the capital plan per cycle and how many people are involved
  • Budget scenarios built per cycle and the hours each one takes
  • Your cost of an unplanned outage by asset class, or your best current estimate of it
  • Current supplier lead times by asset class and your installed cost per unit
  • Loaded hourly rates for asset management staff and capital planning analysts

Where the dollars come from

Cost driverHow it is calculated, from a rate you supply
Deferred capitalassets moved to a later year or to refurbishment x your installed cost per unit x your cost of capital x years deferred
Refurbishment versus replacementunits refurbished instead of replaced x the difference between your refurbishment cost and your installed replacement cost, net of the remaining life you are willing to credit a refurbished unit
Planning laborplan assembly and scenario hours avoided x your loaded rate for asset management and capital planning staff
Risk weighted outage exposureyour cost per unplanned outage by asset class x the change in expected failures between the current plan and the ranked plan, computed with your own failure rates
Lead time exposureunits pulled earlier to beat a lead time x your cost of carrying that asset early, weighed against your own cost of being caught short

Reliability and maintenance

Reliability
This does not move a reliability index directly. What it moves is how much failure risk you carry per capital dollar and where you choose to carry it. Stated in reliability terms, the honest framing is expected unplanned outages per year under one plan versus another, computed from your own failure rates rather than ours.
Maintenance
Refurbishment becomes a real option with a real remaining life credit instead of a fallback when capital runs short, which lets the maintenance organization plan shop and outage capacity a year ahead. Run to failure becomes an explicit, documented choice on named assets rather than the default for everything that did not get funded.

What else it moves

ComplianceEvery deferral and every run to failure choice carries a written basis, which is exactly what a prudence review asks for when a deferred asset later fails.
Insurance and riskA documented, risk weighted capital plan is a stronger position with an insurer or a rating agency than a plan assembled from departmental asks.
WorkforceA plan that can be re optimized when the budget moves saves the planning group its worst weeks of the year, which are currently spent rebuilding it by hand.

What it costs you, stated honestly

You pay for the scoped engagement that builds and runs this, for integration into your capital planning and asset systems, and for the internal work of agreeing on inputs, particularly your cost per unplanned outage by asset class. That last item is a negotiation between asset management and finance and it usually takes longer than the integration does.

How to build the payback case

Payback is dominated by deferred and avoided capital rather than labor, because the dollars per decision are large. The credibility of the whole case rests on whether finance accepts your outage cost inputs, so settle those before you build anything.

This is an optimization run on your numbers, your lead times, and your own risk appetite, not a vendor claim about savings. Re run it against actuals after one full budget cycle, including the decisions you overrode and why.
Each of these opens in full on the use case page, alongside the integration plan, the data ask, the path to production, and the operator console. Open the use case library.
For Your Architects and Data Owners
Run this at your utility

What is this, exactly? It is AI software: intelligent agents and models built and delivered by SoftServe, running on NVIDIA accelerated computing. It is not a hardware appliance and it does not replace the systems you run today. It deploys in your own cloud or on your premises, connects read-only to your existing systems, and recommends; your people approve every action, starting in shadow mode until it earns trust.

A document generator for capital planning and regulatory teams. It takes project spreadsheets and produces regulatory-grade investment justification narratives, each traceable to your data and consistent with prior filed positions. The demo above uses synthetic data; everything below describes what the real deployment needs from your organization.

Systems it connects to

Your systemTypical productsHow we connect
Asset / work management (EAM/CMMS)IBM Maximo, SAP PM, Oracle WAMscheduled file export (CSV or CIM XML)
Planning and study toolsCYME, Synergi, PSS/Escheduled file export (CSV or CIM XML)
Project schedulingOracle Primavera P6, Microsoft Projectscheduled file export (CSV or CIM XML)
Document and knowledge storesSharePoint, OpenTextdocument upload
Financial and enterprise resource planning (ERP)SAP S/4HANA, Oracle EBSscheduled file export (CSV or CIM XML)
Customer Information System (CIS) / billingOracle CC&B, SAP IS-Uscheduled file export (CSV or CIM XML)
Regulatory docket sourcesstate commission e-filing portalsread-only API

Data it needs from you

How it runs on your systems

Runs in your own cloud account on GPU instances with read-only connections through your existing data zone. No system of record is changed; the output is a document your planners edit and own. The pilot generates justifications for three real projects alongside the manual versions.

Path to production

Weeks 1-3
Set up file exports and load prior filings; data access approvals are the usual gate
Weeks 4-9
Pilot: generate justifications for three pending capital projects and compare with manually written versions on quality and completeness
Weeks 10-11
Evaluation and go or no-go decision with the comparison scores in hand
Months 3-5
Hardening: refresh schedules, templates per jurisdiction, and planner training
Months 5-7
In production: every capital project entering a filing gets a generated first-draft justification inside the planning workflow

What we need from your team

Full integration, data, and timeline detail for each use case in this scenario: UC 14.2 · UC 14.4 · UC 4.4
For Your Operators and Dispatchers
Where you will see it and how you say yes

The Approve button you just clicked in the demo above is the real workflow. This is what it looks like on the screen of a capital planning analyst in the GridCORTEX console:

GridCORTEX ConsoleSigned in: a capital planning analyst
Notifications
Justification narrative ready for the $48M substation rebuild, aligned to resilience goals, traceable to 6 source tables
Daily model refresh complete; all connected feeds healthy
Recommendation
Accept investment justification narrative for the $48M substation rebuild
  • Every figure traces to the project spreadsheet and EAM records
  • Consistent with resilience positions in 3 prior filings
  • Covers 3 pending projects in one drafting pass
✓ Accept narrative draftModifyDecline
After you approve: The narrative is saved to the document store and routed to regulatory affairs for expert edit, and an audit entry records who approved it and why.
Computed from data as of 17:42:10 local; every card shows the timestamp of the data behind it.

What happens when you hit approve

Approve saves the narrative to the document store as a draft and routes it to regulatory affairs for expert edit through your existing review workflow. GridCORTEX files nothing; your team owns the final document.

How you tell it what it cannot see

The planner points at the project spreadsheet and picks the goal alignment (resilience, equity, or emissions); supporting data pulls automatically from EAM and planning tools.

Live data, not stale data

Project data is read from EAM and planning tools at generation time and prior filings refresh daily; the draft shows the as-of date of every source table.

Where it lives day to day

Lives in the GridCORTEX console with drafts filed in the document store; email push when a project narrative is ready. The console runs in a browser beside your existing screens on day one; embedding into your own systems is a roadmap step once the read-only phase has earned trust. Approve, Modify, and Decline are all captured in an audit trail your compliance team can pull, and GridCORTEX never blocks or overrides anything in the systems you run today.

The Gap: Why Your Existing Systems Don't Already Do This

The fair question from any utility planning shop: "We have an EAM, planning spreadsheets, consultants, and decades of rate-case experience, what's new here?" Here's the honest answer.

What you own keeps doing its job

  • EAM (Maximo/SAP), the system of record for assets, work, and cost history. Nothing changes.
  • Department capital planning, engineers still propose projects; their judgment stays central.
  • Rate-case counsel & regulatory affairs, strategy, testimony, and the filing itself remain theirs.
  • Planning consultants, benchmarking and industry context keep their place.
  • The prudence standard, the commission's test doesn't change; your ability to meet it does.

The gap GridCORTEX fills, above them, not instead of them

  • Bottom-up plans optimize departments, not the system. 240 projects assembled from 9 department lists have never been scored on ONE risk scale. The frontier only exists when every project is comparable; that computation is the gap.
  • Age is not risk. 38 projects replaced assets the twins rate healthy, while worse actuarial risk sat unfunded. No spreadsheet fuses DGA trends, loading history, outage records, and climate exposure into a per-project risk-per-dollar figure.
  • The evidence pack IS the model. When testimony, exhibits, and data-request responses generate from the same model that ranked the projects, cross-examination cannot find daylight between them. Manually assembled cases always have daylight.
  • Data requests in days, not weeks. 47 intervenor questions are queries against a living model, not a scramble across nine departments' spreadsheets.
  • The audit trail is native. Every ranking decision carries its data lineage (NeMo Relay traces); the methodology transparency commissions have started demanding by name.
Accent, don't replace: GridCORTEX reads your EAM, twins, outage history, and project catalog · computes the frontier above them · and hands your planners the reallocation and your regulatory team the evidence. The engineers still decide. The commission finally sees why.
Under the Hood: What GridCORTEX Took Into Account in This Scenario

When someone asks "what did it actually calculate?", this is the list. In the simulation these factors drive the storyline; in a pilot they are computed from your EAM, asset twins, OMS history, GIS, and financial systems.

📊 Per-Project Risk Quantification

  • Probability of failure per asset from health twins, DGA, loading history, inspection results, age as one input among many, not the proxy for all
  • Consequence of failure: customers affected, critical loads, SAIDI/SAIFI contribution, wildfire and flood exposure at that location
  • Risk retired per dollar for all 240 projects on one comparable scale, replacements, undergrounding, ties, automation, vegetation
  • Portfolio interactions: projects that overlap, defer, or amplify each other

📈 The Efficient Frontier

  • Optimal portfolio at every budget level, what $1.0B, $1.2B, $1.4B each buy in risk retired
  • The current plan's position vs. the frontier, the 23% gap, decomposed to the specific projects causing it
  • Swap analysis: 38 out (healthy-asset replacements), 51 in (worst risk-per-dollar unfunded work), constraint-aware (crew capacity, outage windows, geographic balance)
  • Sensitivity: how the frontier moves under storm-frequency and load-growth scenarios

🏛️ The Evidence Pack

  • Per-project justification exhibits: risk quantification, alternatives considered, deferral consequences
  • Methodology documentation written for a hearing room, with every number traceable to source systems (Relay lineage)
  • Pre-drafted responses to the historically likely data requests, mined from prior dockets
  • Consistency guarantee: filing, workpapers, and DR responses all generate from one model, no daylight for cross-examination

⚖️ Regulatory Intelligence

  • This commission's precedent: what survived and what was disallowed in comparable dockets (UC 14.3)
  • Intervenor pattern analysis: who challenges what, historically
  • Prudence-standard framing per project class, reliability, resilience, or growth
  • Runs on the NVIDIA Agent Toolkit: cuOpt for the portfolio optimization, AI-Q for docket research, Relay for the audit trail regulators now ask about by name

Presenter's one-liner: "It put all 240 projects on one risk scale, showed the plan sitting 23% below the efficient frontier, moved it there with the same dollars, and then wrote the evidence pack from the same model, so when the intervenors pushed, every number traced. Same budget, more risk retired, nothing disallowed. That's what you just watched."

GridCORTEX Live Scenario Demo · Synthetic data throughout, no utility, commission, or docket depicted is real · GridCORTEX connects read-only to the systems you already run · SoftServe + NVIDIA · Created by Ronnie Mauldin, NVIDIA Solutions Director, Power & Utilities, SoftServe · JUL 2026