Methodology

Section 1

Two axes, never merged

Every report shows two numbers: a readiness score (0–100) and a confidence band (High / Medium / Low). Readiness measures how strong the current decision setup is under the inputs provided. Confidence measures how complete and defensible the evidence base is. Missing evidence lowers confidence first, readiness second — because an honestly incomplete project should not read as bankable or dismissed.

Section 2

Eight-component scoring rubric

Readiness is a weighted score of eight components; component weights are fixed:

Each component is the sub-weighted mean of a small number of sub-checks. Each sub-check is an ordered decision table: the customer’s inputs meet exactly one rule, which emits one of five fixed band values (100 / 70 / 40 / 25 / 10). No qualitative judgment at runtime — same intake plus same pinned rubric equals the same score, always.

"Assumption set ready for the next diligence step" means the submitted assumptions meet the stated completeness and consistency thresholds under the cited rubric. It does not mean the project is feasible, safe, financeable, permitted, investment-ready, bankable, or likely to succeed.

Section 3

Source hierarchy

The benchmark set is derived from public techno-economic sources, in this priority order:

1. 1.Official public techno-economic datasets: PNNL Grid Energy Storage Cost and Performance, NREL Annual Technology Baseline (ATB), IEA storage summaries where recent.
2. 2.Official government or national-lab reports (DOE).
3. 3.Official market rules or tariff documents (interconnection and procurement).
4. 4.Customer-provided project inputs (never a benchmark source — always the audit subject).

Every source we cite carries five fields: source name, source date, geography, currency year where relevant, and version or retrieval date. Vendor materials, supplier price lists, and privately-sourced pricing are excluded from the primary benchmark.

DurationX does not sell storage systems, rank vendors, accept supplier referral fees, or receive commissions from technology suppliers. The benchmark may include public, licensed, and clearly identified supplier-originated evidence; supplier-originated evidence is labeled and does not become "independent" merely because DurationX uses it.

Section 4

Current data coverage

Ten technology classes are in scope. Seven — both lithium-ion chemistries, vanadium redox flow, thermal, compressed-air, gravity-based, and hydrogen storage — have cost-curve coverage drawn from the public sources above. Three classes — iron-air, liquid-air energy storage (LAES), and zinc-bromine flow — do not yet have a qualifying independent cost source; public figures for these are limited to single-vendor claims or wide, inconsistent secondary estimates, not benchmark-grade data. An audit against one of these three classes is scored on every other component as normal, but the CAPEX-benchmark comparison for that class is marked not evaluable rather than estimated.

Procurement lead-time data (how long equipment delivery typically takes) does not yet have a qualifying independent source for any technology class. This sub-check is not scored against any figure until a reliable source is identified — it is never estimated or approximated.

Section 5

Reproducibility and verification

For a pinned intake, dataset, rubric, rules, and normalization inputs, the numeric scoring calculation is deterministic. Explanatory narrative may be AI-assisted and can vary; it is constrained by the stored calculation record and reviewed before release.

Every delivered report pins the exact dataset, scoring-rubric, template, and prompt versions used to produce it, plus the underlying model and a verification reference. Report metadata is signed with Ed25519 over a canonical JSON payload that includes the SHA-256 hash of the PDF file. Because rubric, dataset, rules, and template versions are revised over time, multiple versions can be active across different reports at once — this page does not carry a single current version number. The exact versions and evaluation date that apply to a given audit are shown only inside that report.

The public verifier at /verify re-reads the PDF bytes from private storage, recomputes the SHA-256 hash, and re-checks the signature. A tampered file or tampered metadata fails. The verifier never returns customer content — only valid or invalid.

Section 6

AI usage and independent review

The primary numeric score, band mapping, top-failure ranking, and required-next-inputs list are produced by the deterministic engine — never by AI. AI is used only to translate the deterministic result into decision language (a written narrative and a committee-ready memo), and to run a second-pass compliance review on the assembled draft. A separate deterministic scan runs alongside the AI compliance pass; either layer blocking sends the draft to human review.

Every report is manually quality-checked before release. Automatic delivery without human review never happens. “Human-reviewed” and “manually quality-checked” mean exactly this, and nothing broader:

Before release, a person checks the report for input-to-output consistency, source/provenance display, prohibited claims, unresolved compliance flags, calculation reconciliation, and document integrity. This quality-control review is not an engineering review, investment recommendation, legal opinion, safety certification, or independent verification of every customer-provided fact.

DurationX evaluates a submitted assumption set using version-pinned deterministic scoring rules and versioned benchmark data. The score measures assumption completeness and internal consistency under the stated rubric; it is not a project-success probability or professional certification.

Explanatory narrative and a separate compliance review are assisted by Anthropic’s commercial API. The AI does not choose the numeric score. A person reviews each report before release for calculation reconciliation, unsupported or prohibited claims, provenance display, unresolved compliance findings, and document integrity. This quality-control review is not project-specific engineering, safety, financial, legal, or procurement advice.

A separate independent subject-matter reviewer is intended to review the identified methodology, benchmark compilation rules, rubric, and golden cases under a published scope and conflict-of-interest declaration. The reviewer does not certify individual customer projects.

The identified methodology, rubric, compiler rules, and benchmark dataset version were reviewed within the scope stated in the published review note by an independent energy-storage subject-matter reviewer. That review does not certify any individual customer project or replace project-specific engineering, safety, commercial, legal, or financial diligence. No independent methodology review has been completed as of this writing — the paragraph above describes the intended process, not a completed review. The current review note, covered versions, date, conditions, and expiry are available at [PUBLIC REVIEW NOTE URL — NOT YET PUBLISHED; DO NOT LINK LIVE UNTIL A REAL SIGNED REVIEW EXISTS].

Three roles are kept separate and are never collapsed into one another: Report quality reviewer: checks a specific report’s quality-control checklist; no specialist licence is implied. Methodology reviewer: independently reviews the versioned benchmark/scoring framework under a written scope and conflict-of-interest declaration. Customer advisers: licensed engineers, fire/safety professionals, interconnection specialists, lawyers, tax advisers, financial advisers, insurers, lenders, and procurement advisers retained by the customer for project-specific diligence.

Section 7

Providers and data-flow

Section 8

Data policy

Customer project data is confidential by default. Raw customer data is not reused for model improvement without explicit opt-in; the opt-in default is off. Deletion requests are executed within thirty days of receipt with an audit-trail record kept.