Trade Policy Intelligence / Independent product case
Tariff Impact Navigator
The useful answer is not the tariff headline. It is the trace from policy evidence to exposure, scenario, and accountable response.
How a fragile no-code experiment became a tested multi-workflow prototype designed for repeatable procurement analysis.
- My mandate
- AI Product & Portfolio Lead · decision trace, evaluation gates, and scale-up direction
- Verified product evidence
- Delivered a working prototype combining policy research, impact analysis, scenario planning, and reporting.
- Policy intelligence
- Scenario product
- Deterministic + generative AI
- Trust before automation
- Primary user
- A procurement, category, finance, or trade-risk leader responding to a policy development.
- Decision enabled
- Whether the exposure is real or potential, which scenario requires response, and who should validate, mitigate, or monitor it next.
- My mandate
- Connect a volatile external-policy problem to a bounded, testable business workflow and define the trust gates required before automation and enterprise handoff.
- Two evidence layers
- External policy plus exposure data
- Multi-turn
- Research, calculation, and scenarios
- Quality loop
- Regression and human review
Evidence first
What is proven, what I changed, and what remains open.
A 90-second evidence map for hiring review. Synthetic product views explain mechanics; they never count as outcome proof.
- Verified now
- A working prototype connecting current-policy research, deterministic exposure calculation, scenario comparison, and source-backed communication.
- Next evidence gate
- SME-led UAT, governed refresh, enterprise data connection, and acceptance evidence before automated monitoring.
User / workflow evidence
Verified recordRequirements and prototype review showed that policy news alone could not answer which material or business exposure mattered, while the earlier workflow was inconsistent and difficult to scale.
Product decision
Verified recordI separated policy truth from exposure math, treated scenarios as explicit assumptions rather than forecasts, and held automated refresh behind an evidence gate.
AI / system boundary
Supported synthesisAI retrieves and interprets policy evidence; deterministic logic resolves and calculates exposure; the accountable owner validates assumptions, exceptions, and the communication decision.
Evaluation → change
Verified recordGrounded-research checks, calculation regression, repeated variants, model-assisted review, and human product review converted relevance, status, exposure, and communication failures into separate release controls.
Outcome / boundary
Verified recordThe bounded policy-to-impact workflow and trust-before-automation roadmap are evidenced. Real-time refresh, production adoption, and realized savings are not claimed.
AI product decision record
The choices behind the product, architecture, and release gate.
Use AI for changing policy evidence; use deterministic computation for exposure and scenario math.
AI fit
Supported synthesisUse an LLM to find, interpret, and explain policy evidence while code calculates business exposure.
Policy language is unstructured and changes over time, but financial exposure must remain reproducible.
Alternative consideredPure rules cannot interpret every policy variation; model-generated arithmetic is too fragile for the decision.
Knowledge & context
Supported synthesisUse dated RAG over approved primary policy sources, then resolve entities and rates into a governed exposure model.
Freshness, jurisdiction, effective date, and source authority determine whether the answer is valid.
Alternative consideredModel memory or undated web search cannot support a current-policy claim.
System architecture
Supported synthesisUse a sequential research → resolve → calculate → compare → communicate workflow with explicit checkpoints.
Each step has a different error class and needs a visible handoff before the next one compounds it.
Alternative consideredAutonomous monitoring, multi-agent routing, or MCP-connected actions remain behind freshness, permission, and SME acceptance gates.
Evaluation & release
Verified recordSeparate policy groundedness, calculation regression, scenario assumptions, repeated variants, and human communication review.
A current policy answer can still yield wrong exposure, and correct math can still communicate the wrong decision.
Alternative consideredOne combined score would obscure which control failed and whether the product is safe to refresh automatically.
Evidence I still need from the private project record3 open items
- 01
SME UAT findings and accepted thresholds.
- 02
A current-policy freshness and fallback receipt.
- 03
Measured decision-time, exposure-quality, or operational-use evidence.
The product contract
One user moment, carried all the way to a decision.
A tested policy-to-impact workflow that connects current trade developments with material exposure, scenario analysis, and an accountable business brief.
- 01 / User
- A procurement, category, finance, or trade-risk leader responding to a policy development.
- 02 / Trigger
- A new or changing trade measure may affect material exposure and leadership needs a defensible scenario before acting.
- 03 / Inputs
- Policy question · origin and destination · material or category · timing · exposure lens · scenario rate
- 04 / Product action
- Classify policy status and timing, keep external evidence separate from business exposure, resolve the calculation inputs, run deterministic scenarios, and explain the implications with assumptions visible.
- 05 / Output
- A source-backed policy record, exposure calculation, scenario comparison, audit trail, management brief, owner, and proposed next action.
- 06 / Human decision
- Whether the exposure is real or potential, which scenario requires response, and who should validate, mitigate, or monitor it next.
Customer-grade product walkthrough
See one decision move through the product.
A new trade measure is announced. A category leader needs to know whether it is effective or potential, what exposure may be affected, and how a changed rate would alter the scenario.
Establish what changed before calculating what it might mean.
The workflow distinguishes an effective measure from a proposal, threat, agreement, or de-escalation and retains the source date.
A fictional notice proposes an additional duty on composite material moving from Region A to Region B.
Illustrative event · status and effective timing not yet confirmed
How the product handles this state
- 01
Prioritize official evidence over repeated reporting.
- 02
Classify status, trade direction, category, and timing.
- 03
Separate confirmed facts from emerging interpretation.
Decision signals
- Policy status
- ProposedNot yet an effective rate.
- Trade direction
- Region A → BSynthetic origin and destination.
- Timing
- Review window openEffective date remains unresolved.
The event is tracked as a proposed measure with unresolved timing, so downstream calculations must be labelled as scenarios.
- Proposal is not represented as current policy.
- Direction and category are explicit.
- Source date travels with every downstream output.
Which fictional spend lanes could be affected if the proposed measure becomes effective?
Synthetic material and spend data · direct and upstream lanes
How the product handles this state
- 01
Resolve material and trade-direction matches.
- 02
Separate direct from upstream exposure.
- 03
Flag exemptions and missing classification data.
Decision signals
- Matched spend
- $12.4MSynthetic annual exposure used only for this walkthrough.
- Supply lanes
- 2 matchedOne direct and one upstream lane.
- Classification gap
- 18% unverifiedSynthetic spend requires manual category review.
The proposed measure could touch two fictional supply lanes, but unverified classification prevents the product from presenting the full amount as confirmed exposure.
- Matched and unverified spend remain separate.
- Direct and upstream lanes are not combined silently.
- No rate has been applied yet.
Apply an illustrative 10% duty to verified matched spend only.
Synthetic assumption · no claim that this is a live or expected rate
How the product handles this state
- 01
Use only verified matched spend.
- 02
Apply the explicit scenario rate.
- 03
Retain exclusions, formula, and aggregation lens.
Decision signals
- Verified base
- $10.2MSynthetic matched spend after excluding unverified classification.
- Scenario rate
- 10%Illustrative assumption, not a policy forecast.
- Gross impact
- $1.02MSynthetic arithmetic before mitigation or pass-through.
If the illustrative 10% rate applied to verified matched spend, the gross pre-mitigation impact would be $1.02M in this synthetic scenario.
- Formula and base remain inspectable.
- Unverified spend is excluded, not estimated.
- No mitigation or supplier pass-through is assumed.
Compare 5%, 10%, and 15% illustrative rates with no mitigation and partial sourcing mitigation.
Synthetic what-if analysis · not a probability model
How the product handles this state
- 01
Change rate and mitigation assumptions explicitly.
- 02
Recalculate using the same verified exposure base.
- 03
Map each case to a different response threshold.
Decision signals
- 5% case
- $0.51MSynthetic gross pre-mitigation impact.
- 10% case
- $1.02MSynthetic gross pre-mitigation impact.
- 15% case
- $1.53MSynthetic gross pre-mitigation impact.
The response threshold changes materially across the illustrative range, making policy confirmation and exposure classification the next highest-value work.
- Scenarios are conditional, not forecast probabilities.
- Mitigation assumptions remain user-editable.
- Decision thresholds are tied to observable changes.
Prepare actions for proposal, confirmed-policy, and high-impact threshold states.
Synthetic response plan · business and trade review required
How the product handles this state
- 01
Define actions by trigger state.
- 02
Assign accountable owners.
- 03
Separate reversible preparation from irreversible commitment.
Decision signals
- While proposed
- Validate inputsClose classification gaps and monitor official status.
- If confirmed
- Engage suppliersTest pass-through, origin, and specification options.
- If threshold crossed
- Activate alternativesEscalate sourcing and finance response.
Prepare reversible evidence and supplier actions now; reserve sourcing changes for a confirmed policy and an approved impact threshold.
- Policy, exposure, and action owners are distinct.
- Each escalation has a visible trigger.
- Legal and trade interpretation stays human-owned.
Prepare the policy-to-impact brief for category, finance, and trade review.
Synthetic business communication · not legal or financial advice
How the product handles this state
- 01
Separate confirmed facts from scenarios.
- 02
Attach formula, inputs, and evidence gaps.
- 03
Record the trigger, owner, and next review date.
Decision signals
- Policy truth
- Proposal onlyNo effective measure is claimed.
- Impact basis
- $10.2M verifiedSynthetic matched base; unverified spend excluded.
- Decision state
- Review pendingNo autonomous action or approval.
Monitor the proposal, close the exposure classification gap, and prepare trigger-based supplier actions without treating the illustrative rate as expected policy.
- External fact and internal scenario remain distinct.
- Calculation is reproducible.
- Accountable owners and review gates are explicit.
All policy events, materials, rates, spend values, sources, and outputs shown here are synthetic. This public-safe walkthrough demonstrates product logic, not live legal advice, employer exposure, or production coverage.
Showing Classify the policy, step 1 of 6.The complete product
More than a generated answer.
The product earns trust by combining a defined decision contract, inspectable evidence, deterministic controls, AI assistance, and an accountable handoff.
Policy-state intelligence
Classifies a development as effective, proposed, threatened, agreed, or de-escalating with timing and trade direction attached.
The product prevents a headline from being treated as an implemented rate or a settled forecast.
Evidence separation
Keeps external policy truth, internal exposure data, and scenario assumptions as distinct reviewable layers.
Each layer has different ownership, freshness, and failure modes.
Exposure resolver
Clarifies origin, destination, material, tier, timing, exemption, business unit, and aggregation lens before calculation.
A policy rate alone does not reveal which spend or flow is affected.
Deterministic scenario engine
Applies an explicit rate and scope assumption, calculates exposure, and compares scenario deltas reproducibly.
Generative AI does not own the math or hide the assumptions behind a fluent answer.
Source-backed management brief
Explains the policy state, calculation basis, scenario implication, uncertainty, and recommended review path.
Leadership receives a decision record that can be challenged and updated as evidence changes.
Governed refresh and action
Defines how policy and exposure updates should be reviewed, versioned, assigned, and handed into the enterprise workflow.
Automation follows a trust and ownership model rather than turning changing news directly into action.
AI operating model
The model assists. The product controls. The human decides.
Separating responsibilities is both a system design and a product leadership choice. It defines what can be tested, what must be reviewed, and where accountability stays.
Protect exposure math, scenario reproducibility, and auditability.
- Policy status and effective-date fields
- Origin, destination, category, tier, and exemption rules
- Exposure aggregation and rate application
- Scenario delta and version record
Find, classify, and communicate changing policy evidence.
- Policy retrieval and relevance filtering
- Event and uncertainty classification
- Multi-turn intent routing
- Source-backed management synthesis
Own the assumptions, exceptions, and business response.
- Confirm exposure scope and data
- Validate policy interpretation
- Approve the scenario and communication
- Assign mitigation or monitoring action
The broken workflow
From policy change to material exposure and scenario response
Rapid policy changes forced procurement teams to repeatedly interpret external news, update tariff assumptions, calculate exposure, and rebuild communications across materials and geographies.
The external facts changed faster than a manual tracker could support.
Teams needed current, reputable policy evidence while distinguishing measures already in effect from proposals, threats, agreements, or de-escalation.
A policy announcement did not reveal which business exposure mattered.
The analysis still had to resolve trade direction, material context, tier, spend, exemptions, and the user’s aggregation lens.
The earlier no-code experience was inconsistent and difficult to scale.
A custom workflow was needed to route research and calculations separately, preserve assumptions, and test the output against reviewable evidence.
Product decisions and rationale
Product judgment lives in the choices and boundaries.
These records reconstruct the evidence-backed product logic: direction, competing alternative, rationale, and consequence. They are not presented as verbatim decision minutes.
One decision trace from policy evidence through exposure, scenario, communication, and owner action.
- Rejected alternative
- Optimize a standalone news summarizer that stops before business consequence.
- Why
- The user value begins when a verified event can be connected to a reviewable business decision.
- Product consequence
- Research, calculation, scenario, and reporting became one accountable product workflow.
Use AI for research, classification, and explanation; use reproducible logic for calculation and aggregation.
- Rejected alternative
- Ask the model to infer and calculate the final impact inside a narrative response.
- Why
- Calculation correctness, repeatability, and auditability are non-negotiable in a high-consequence workflow.
- Product consequence
- The evaluation model could test math independently from language quality.
Label the policy state and let the user compare named rate and scope assumptions.
- Rejected alternative
- Present one probable future as the expected outcome.
- Why
- The product must support decisions under uncertainty without fabricating policy certainty.
- Product consequence
- Assumptions, deltas, and evidence changes remain visible and updatable.
Prove the bounded routing, calculation, fallback, and review model before automating rates and exposure refresh.
- Rejected alternative
- Scale ingestion and access while core failure modes remained difficult to observe.
- Why
- Automation multiplies both useful throughput and unverified error.
- Product consequence
- UAT, freshness, auditability, ownership, and fallback became explicit investment gates.
Evaluation → product change
A failure is useful only when it changes the product.
The bounded prototype completed functional, regression, model-assisted, and human-supervised evaluation. The public case uses synthetic exposure and omits source names, formulas tied to employer data, scores, and test volumes.
A public announcement contains a proposed rate, an uncertain effective date, and possible exemptions while the business exposure record has incomplete origin and tier data.
- Initial failure
- A system can combine proposal and exposure into a precise-looking impact number that implies more policy certainty and data completeness than exists.
- Designed control
- Separate status, evidence, exposure, and scenario layers; require explicit assumptions; block or qualify calculations when policy or exposure fields are unresolved.
- Acceptance test
- The product must label the measure as potential, show which exposure assumptions are incomplete, and calculate only an explicitly named scenario with a traceable formula.
- Acceptance gate
- No output may present scenario impact as actual exposure unless policy status, effective scope, exposure fields, and calculation version are all reviewable.
What changed in the selected trade measure, which exposure could be affected, and how does the impact change under two explicit rate scenarios?
- Expected evidence
- Relevant policy evidence with status and timing, the correct exposure slice, the applicable assumptions, and reproducible scenario calculations.
- Expected behavior
- Exclude unrelated policy content, distinguish actual from potential, resolve or expose missing inputs, calculate outside the language model, and communicate the result with sources and uncertainty intact.
- Release gate
- Functional and regression checks must reproduce the calculation; model-assisted and human review must confirm grounded policy interpretation, uncertainty, completeness, and professional usefulness.
- 01Policy retrieval relevance
- 02Status and timing classification
- 03Exposure-scope correctness
- 04Formula and aggregation fidelity
- 05Scenario reproducibility
- 06Assumption visibility
- 07Multi-turn routing
- 08Business communication quality
My product leadership
From an ambiguous ask to an investable next gate.
Connect a volatile external-policy problem to a bounded, testable business workflow and define the trust gates required before automation and enterprise handoff.
- Team model
- Matrix collaboration across the product owner, procurement and trade SMEs, finance and exposure stakeholders, data, engineering, and AI delivery. No direct-report relationship is claimed.
- My decision rights
- I shaped the end-to-end decision trace, prototype scope, AI-versus-calculation boundary, evaluation model, product-owner checkpoints, and scale-up recommendation; business owners retained policy, financial, and investment accountability.
- Prototype delivery record
- The roadmap defined the transition from static bounded analysis to governed refresh, business validation, production-grade interface, fallback, auditability, and accountable ownership.
- 01
Reframed a fragile no-code experiment as a multi-workflow product joining policy, exposure, scenario, and communication.
- 02
Established separate evidence and test contracts for policy interpretation and deterministic impact calculation.
- 03
Made uncertainty, missing exposure fields, and unsupported policy claims explicit fallback states.
- 04
Used bounded workflow evidence to sequence SME UAT, governed data refresh, audit trail, ownership, and enterprise handoff.
Value without invented outcomes
Separate what worked from what scale must prove.
The prototype evidence supports product capability. Adoption, ROI, and realized business impact remain separate claims until measured and approved.
Teams repeatedly monitor changing policy, interpret status and timing, locate the relevant exposure, rebuild calculations, compare scenarios, and rewrite leadership communications.
The prototype joined policy research, impact calculation, scenario analysis, and reporting in one multi-turn workflow with repeated technical and human-supervised evaluation.
A scaled product should shorten the path from policy signal to reviewable exposure, reduce inconsistent assumptions, and improve the speed and traceability of mitigation decisions.
- Time from policy signal to reviewable scenario
- Policy-classification correction rate
- Calculation reproducibility
- Exposure-coverage completeness
- SME usefulness and revision rate
- Time to assigned mitigation or monitoring action
Portfolio leverage
Specialist where it matters. Shared where it scales.
Policy-state semantics, exposure mapping, deterministic scenario logic, and high-consequence review require a specialist product contract beyond generic research or chat.
- Identity and access
- Retrieval and citations
- Evaluation and observability
- Review, action assignment, and enterprise handoff patterns
- Policy status and timing model
- Trade direction and exposure semantics
- Scenario calculation and audit trail
- Risk communication and mitigation workflow
Automate refresh and broaden access only after policy usefulness, exposure interpretation, calculation fidelity, fallback, and ownership pass SME-led UAT.
Evidence boundary
Core workflow proven. Scale is a separate product decision.
What exists now
- Working prototype joining current-policy research, exposure calculation, scenario planning, and reporting.
- Multi-turn routing between research and impact workflows with a consolidated response.
- Repeated functional, regression, automated, and human-supervised testing.
What must become true next
- SME UAT for policy relevance, impact interpretation, and ease of use.
- Governed automation for policy rates and exposure-data refresh.
- Production-grade interface, fallback, audit trail, ownership, and handoff.
What this case does not imply
- No claim of live production use, continuous real-time coverage, or realized cost avoidance.
- No internal spend, material, supplier, policy-source, prompt, architecture, or quality-score details are published.
Evidence register
The work behind the visible product.
These records map each public claim to the approved requirements, demonstrated workflow, evaluation practice, or prototype-delivery record behind it. They are evidence references, not public copies of protected source files.
Policy-to-impact contract
Research, status, exposure, scenario, communication, uncertainty, and non-goals.
Verified project evidenceResearch and calculation split
Separate policy evidence and deterministic exposure paths joined in a reviewable brief.
Public-safe reconstructionDual quality system
Policy relevance and classification plus calculation fidelity, regression, and human usefulness review.
Verified project evidenceTrust-before-automation roadmap
SME UAT, data refresh, audit trail, fallback, ownership, product UI, and enterprise integration.
Verified project evidenceNext product gate
The remaining work is explicit.
- 01
Validate news usefulness and impact interpretation with SMEs
- 02
Automate governed rate and exposure data refresh
- 03
Harden fallback, auditability, and enterprise handoff