Every Domain Has Its Substrate: A Walkthrough Across Five Professions
The CTI case study makes a claim that's easy to nod past: every domain has its TSS — the accumulated vocabulary the experts actually reason in. Cycling has TSS, CTL, ATL, TSB. Your field has its equivalent. This article is a worked walkthrough across six professions, designed so that if you work in one of them, you'll recognise your section immediately and finish it already drafting your own substrate.
It's not exhaustive. It's a starting frame. Skim to your section — the six are independent.
What a Substrate Is, Concretely
A substrate has three layers, and an AI has to be grounded in all three before it can do real domain work.
Quantitative substrate — the metrics, frameworks, and calculations the field reasons in. Cycling's PMC. Accounting's materiality. Construction's bracing tables. The numerical vocabulary you'd find in a textbook, plus the firm's specific calibrations of it.
Subjective substrate — what the metrics miss. The "this doesn't smell right" pattern recognition built up over years. The instincts that don't make it into reports but show up in decisions.
Procedural substrate — how an expert actually responds. The shape of a good answer. The order of operations. The decision tree no one's written down.
Plus three things that wrap around all three layers:
Question archetypes. The kinds of questions that come up in the work, sorted into the categories that change how you'd answer them.
Constraints and safety boundaries. What the expert refuses to do. What gets escalated. What's outside scope. These matter as much as what the AI can do.
The grounding constraint. What every output has to be tied back to so it's honest rather than plausible.
Below, six professions. If you work in one of them, the goal is that you finish your section already drafting yours.
Accounting (Tax / Audit / Advisory)
Quantitative substrate. The relevant tax statute (Income Tax Act 2007 in NZ; IRC in the US; your jurisdiction's equivalent). Accounting standards (NZ IFRS / IFRS / GAAP). Materiality thresholds — the firm's actual calibrations, not the textbook ones. The audit risk model (inherent × control × detection). Depreciation and amortisation conventions. Transfer-pricing rules where relevant. The firm's chart-of-accounts standards. Engagement profitability ratios — realisation, utilisation.
Subjective substrate. "This balance sheet doesn't smell right." The patterns a senior partner recognises that take a junior years to pick up — related-party transactions structured oddly, revenue recognition that happens to track management bonus thresholds, working-capital movements that suggest liquidity stress before the cash-flow does. Client temperament: who can handle a hard finding directly, who needs the conversation walked.
Procedural substrate. How a partner triages a tax-planning question. The order of operations in a year-end engagement. When to escalate to peer review. How to phrase a contentious finding in a management letter so it lands without rupturing the relationship. The "we've seen this before" reflex on aggressive structures.
Question archetypes. Tax planning and structuring. Year-end close support. Audit-finding interpretation. Compliance deadline tracking. Client onboarding and engagement scoping. Industry-specific recurring patterns (farming, tech, property). Off-topic — anything legal-advice-shaped, anything investment-advice-shaped.
Constraints. No individualised tax advice without partner sign-off. No legal opinions. No pronouncements on contentious estate planning. AML/CFT flags follow the firm's protocol, not the AI's reasoning. Professional skepticism in audit cannot be replaced by an AI summary.
What grounding looks like. Every recommendation traceable to the firm's prior engagements with this client (or comparable ones), the relevant statute, and the partner's documented position. Not generic tax advice scraped from the web.
Wealth Management
Quantitative substrate. Portfolio metrics: Sharpe, Sortino, max drawdown, tracking error, beta. Asset-allocation frameworks: strategic-tactical splits, glide paths, risk parity. Tax-aware structures: KiwiSaver / PIE / PIR (NZ); 401(k) / IRA / Roth (US); ISA / SIPP (UK); the CGT and inheritance-tax thresholds in force. Cash-flow modelling, Monte Carlo retirement projections, sequence-of-returns risk. Trust and estate structures. Fee and platform-cost schedules.
Subjective substrate. The adviser's read on the gap between stated risk tolerance and actual risk capacity. Behavioural patterns: who panics in a drawdown, who chases yield, who confuses concentration risk with conviction. Family-dynamics read on estate-planning friction. Knowing which provider's fact-sheet is reliable and which one buries the fee schedule three pages in.
Procedural substrate. The shape of an annual review. The order of operations after a major life event — inheritance, redundancy, divorce, business sale. When to bring in a tax specialist, an estate lawyer, an insurance specialist. How to phrase a risk warning that holds up to regulator review (FMA / FANZ in NZ; FCA in the UK; SEC / FINRA in the US).
Question archetypes. Portfolio review. Withdrawal-strategy planning. Tax-efficiency questions. Major-life-event response. Product comparison and platform selection. Off-topic — legal advice, insurance underwriting, anything that crosses into product recommendation outside the firm's authorised menu.
Constraints. No product recommendations outside the authorised investment menu. No tax opinions beyond firm scope. No predictions of market direction. Suitability rationale captured per the regulator's framework, every time. AML/KYC protocols are not bypassable. Fiduciary duty is not delegable to AI.
What grounding looks like. Every recommendation tied to the client's actual portfolio, documented goals, the suitability assessment on file, and the firm's investment-committee positions. Not generic personal-finance advice.
Law Practice
Quantitative substrate. The controlling statutes and binding authorities in each practice area. Limitation periods, statutory deadlines, court timetables. Quantum tables and settlement ranges from prior comparable matters. Costs schedules — court costs, billing rates, the firm's realisation and utilisation. Statutory thresholds that change the analysis (jurisdictional thresholds, summary-judgment thresholds, Companies Act notification thresholds, Privacy Act breach-notification triggers). The matter-management metrics partners actually steer on: WIP, lock-up days, leverage, profit per equity partner.
Subjective substrate. "This deal smells off." The patterns a senior partner picks up on that take a junior years to develop — earnouts structured to hide risk, indemnity caps that don't cover the actual exposure, reps that don't track the diligence findings, limitation-period and waiver issues that are about to bite. The judge or arbitrator's predilections — who's procedural, who's commercial, who'll take a long view. The counterparty firm's negotiating posture: which firms argue in good faith, which are positional. Reading a witness on whether their evidence will hold up under cross. Client temperament: who wants reassurance, who wants direct counsel, who'll fold under regulatory pressure and who'll fight.
Procedural substrate. The shape of a competent advice memo (issue → facts → analysis → conclusion). The order of operations in a transaction: term sheet → DD → drafting → negotiation → completion → post-completion. The order of operations in litigation: pleadings → interlocutories → discovery → briefs → hearing → judgment → enforcement (or settlement at any stage). Privilege protocols — what's solicitor-client, what's litigation privilege, what loses privilege when it's circulated. How to phrase advice that's clear without overstating certainty. When to brief counsel versus handle in-house. The conflict-check protocol. The "sleep on it before sending" reflex on drafting written in heat.
Question archetypes. Contract review and negotiation. Statutory and regulatory interpretation. Litigation strategy and risk assessment. Due-diligence summarisation. Precedent and template selection. Drafting (clauses, advice memos, letters of demand, opinions). Compliance interpretation. Off-topic — anything amounting to legal advice without admitted-lawyer sign-off, anything that crosses into financial or tax advice the firm doesn't authorise.
Constraints. No legal advice without admitted-practitioner sign-off, in a jurisdiction the firm is admitted to practise in. Privilege must be preserved — outputs that touch privileged material need careful handling and never get exposed to a third-party model that retains data. Conflict checks are protocol, not preference. Court-imposed deadlines are absolute — they get surfaced, never absorbed. Ethical judgments that belong to the partner (when to withdraw representation, when to disclose to a tribunal, candour duties) are not delegable. AML/CFT obligations are statutory and follow firm protocol. Citations to authorities must be verifiable — case-citation hallucination is a known and career-ending failure mode for legal AI, and the system has to cite from the firm's verified precedent database, not generate.
What grounding looks like. Every recommendation traceable to the firm's prior matters on the issue, the controlling statute and binding authorities (verifiably cited), the matter's specific facts on file, and the partner's documented position. Not generic legal commentary, and never an unverified citation.
Environmental Consultancy
Quantitative substrate. Site-assessment frameworks (Phase I / Phase II ESA, Preliminary Site Investigation). Contaminated-land standards (NES-CS in NZ, RBSL/CCME in North America, your jurisdiction's equivalent). Trigger values for soil, sediment, groundwater, surface water. Modelling tools and their assumptions: dispersion (AERMOD), groundwater (MODFLOW), noise (SoundPLAN). Regulatory frameworks (RMA, NEPA, Clean Air Act). HHRA / ERA risk-assessment frameworks.
Subjective substrate. "I've seen this site before." Pattern recognition for likely contaminants given historical land use. Field instincts — which monitoring well looks suspicious, which sample is unrepresentative, which iwi or hapū consultation is going to need more time. Knowing which council officer is risk-averse on which issue. The estimator's smell test on a scope that came in too lean.
Procedural substrate. The shape of a Phase I assessment. How to structure a consent application narrative. When to recommend additional sampling versus accept the data as adequate. How to write a finding that survives an expert-witness challenge in the Environment Court.
Question archetypes. Site-assessment scoping. Contaminant pathway analysis. Consent or permit application support. Environmental impact statement drafting. Regulatory interpretation. Iwi and community engagement comms. Off-topic — anything that crosses into legal advice or that would amount to certification.
Constraints. No certification of findings — that's the licensed engineer or scientist's call. No definitive predictions of regulatory decisions. Iwi and Treaty-settlement matters defer to the relevant team and tikanga. Any contamination above trigger values gets surfaced for licensed review, not absorbed into a recommendation.
What grounding looks like. Every recommendation tied to the actual site data, the relevant standard, the consultancy's prior comparable assessments, and the licensed practitioner whose name will go on the report.
Residential Construction / Builders
Quantitative substrate. Building codes (NZ Building Code; IBC/IRC; your jurisdiction). Bracing and lateral-load calculations. Span tables. Material take-offs and waste factors. Pricing: SQM rates, labour productivity assumptions, sub-trade rate cards. Programme dependencies — foundation cure, frame, cladding, lockup, lining. Margin and overhead percentages. Retention schedules. The H&S risk register the firm actually uses on site.
Subjective substrate. The site-visit read: "this clay subgrade is going to need engineered fill." Sub-trade reliability — which framer can handle a tight programme, which sparky is going to leave you waiting two weeks. Client temperament: who's a fixed-price-and-walk-away versus who needs weekly visits. Knowing which BCO is fussy about which detail. The estimator's smell test on a price that came in too low.
Procedural substrate. The shape of a variation conversation with a client. The order of operations in a typical build. When to call the engineer versus judgement-call it. How to write a defect notice that survives a building dispute. The pre-line walkthrough.
Question archetypes. Estimating and take-off support. Programme and sequencing decisions. Variation pricing and comms. Code-compliance interpretation. Client communication drafting — variations, delays, defect responses. H&S incident response framing. Off-topic — Producer Statements, engineering sign-off, contract-dispute legal positioning.
Constraints. No structural-design certification — that's the CPEng's call. Consent-condition interpretation defers to the council engineer. Weathertightness risk gets flagged for senior review, not adjudicated. Contractual disputes go to legal. H&S incident reporting protocols are not optional.
What grounding looks like. Every recommendation tied to the actual job's specs and programme, the firm's standard details, prior comparable jobs, and what was agreed in writing. Not generic construction advice.
Logistics and Supply Chain
Quantitative substrate. Network metrics: OTIF, fill rate, lead time, cost-per-mile, inventory turnover, demurrage and detention exposure. Forecasting models: ABC classification, exponential smoothing, ARIMA. Routing maths: VRP variants, line-haul utilisation, dock-door scheduling. SLA thresholds for each customer tier. Carrier-rate cards in force.
Subjective substrate. The dispatcher's instinct that "this driver isn't going to make it through customs by 5." The reliability ranking of carriers that's not in any system — who handles a peak-season exception calmly, who falls over. Knowing which lanes have weather risk in which season, which ports have a labour-action history, which customer's procurement team always pushes back on the recovery invoice. The "we always pre-position there in October" patterns.
Procedural substrate. Exception triage decision tree: delay confirmed → reroute attempt → customer comms → cost-recovery path. The order of comms when something goes wrong: which customer first, which carrier, which exec. The shape of a peak-season standup. How to phrase a service-failure root-cause to a customer in a way that preserves the relationship.
Question archetypes. Exception triage. Capacity and routing decisions. Customer-service comms drafting. Carrier performance review. Forecast adjustment. Tender response support. Off-topic — anything that crosses safety regulation or commits to rates outside authorised tariffs.
Constraints. No commitments to rates outside approved tariffs. Dangerous-goods classification stays with a certified DGSA. Customs and compliance protocols are not bypassable. Hours-of-service and driver-safety rules are statutory, not preference — no overrides.
What grounding looks like. Every recommendation tied to the actual network state right now, the carrier's documented performance against this customer, and the contract terms in force. Not generic supply-chain best practices.
Now Do This For Yours
If you read your section and recognised it, the next step is to draft your own — quickly, on paper, before perfectionism kicks in.
Two prompts that tend to unstick people:
Pick a recurring question your senior people answer well, and ask: what would the answer have to be grounded in to be defensible? Whatever that list of inputs is, that's most of your substrate. The metrics, the standards, the prior cases, the firm's documented position — write them down.
Pick something a junior gets wrong in their first six months, and ask: what's the senior pattern they don't have yet? That's almost always procedural or subjective substrate that hasn't been written down — and it's the highest-leverage thing to surface, because it's the thing that's currently locked inside specific individuals.
You don't need a perfect map. You need enough to know what the AI has to be grounded in, what it has to refuse to do, and what kind of question it has to recognise.
That's the deliverable of an Orbital Map engagement — a structured version of the exercise above, scoped to your business, ending with a concrete plan. You walk away with the artefact whether or not we keep working together.
Email: info@orbital.co.nz
Read the CTI case study · Map → Architect → Build, in practice · orbital.co.nz