INDEPENDENT PRODUCT CONCEPT

Shopping Aodh

A buyer-side decision companion that turns a stated need into three evidence-backed propositions, makes trade-offs visible and stops before purchase.

Prototype acceptedStudy enrolment open

Visit the Aodh site

Role: Independent product lead across product thesis, buyer journeys, trust boundaries, decision logic and concept prototyping.
Maturity boundary: The buyer-side thesis and synthetic fixture-only interface prototype are implemented as a publicly accessible concept and research stimulus. Formal enrolment is open, but no participant sessions or findings have been completed. No production application, live commerce, payments, persistence, durable memory or autonomous purchasing exists.

CONCEPT PROTOTYPE

An interaction hypothesis, not a shopping engine.

Synthetic concept prototype · September 2026These supplied captures show the public landing page and fixture-only mobile prototype, using illustrative products, merchants, prices, evidence and outcomes. The prototype is a research stimulus, not a working shopping service. There is no live search, account, persistence, checkout, payment or purchasing authority.

Shopping Aodh's black, ivory and gold landing page with a buyer-side brief and an illustrative decision paper. — **01 · The buyer-side proposition**The public landing page. Aodh keeps the brief; the person keeps the decision.
Visit the Aodh landing page ↗View full-size image ↗

Aodh mobile memorandum introducing the buyer's brief and a fictional walking-shoe mission. — **02 · Start with the brief**The mobile entry point introduces a fictional mission and the buyer-side promise.View full-size image ↗

Aodh mobile brief separating waterproofing, UK size 11, budget and delivery as hard constraints. — **03 · Make constraints explicit**A stated need becomes hard constraints and preferences before any search.View full-size image ↗

Aodh asks whether a wide toe box is essential or preferred and explains how the answer changes the options. — **04 · Ask what matters**One clarification, only when the answer could change the decision.View full-size image ↗

Aodh's illustrative evidence receipt showing the exact shoe variant, merchant reference and product-view placeholders. — **05 · Inspect the receipt**A claim stays attached to its source and exact variant. The displayed evidence is illustrative.View full-size image ↗

CONTEXT

Commerce systems are largely designed to help merchants convert demand. Shopping Aodh asks what changes when an AI system is accountable to the quality of one buyer's decision instead of transaction volume.

MY CONTRIBUTION

I developed a buyer-side product thesis and synthetic Buyer Mission concept that separates hard constraints from preferences, returns three distinct propositions and exposes the evidence, uncertainty and trade-offs behind each recommendation.

WHAT IS TRUE NOW

A verified fixture-only mobile prototype is accepted as the stimulus for a six-session comprehension study. Formal information, consent and scheduling are open; no participant findings exist yet.

Buyer-side allegiance
Three, not thirty
Receipts before confidence

CONTEXT & PROBLEM

The buyer needs an agent with the right allegiance.

Search, recommendation and checkout can make buying easier without making the decision better. The deeper question is whether an agent can represent the buyer's constraints, preferences and longer-term interests.

That may mean recommending the cheaper option, a local or second-hand alternative, waiting, repairing what already exists or making no transaction at all.

BUYER MISSION

Name the need before opening the catalogue.

A Buyer Mission begins with the problem in the person's own words, then separates hard constraints such as fit, budget and delivery from preferences such as local availability, durability or style.

The agent should ask only when an answer can materially change the decision.

DECISION EXPERIENCE

Three, not thirty.

The concept returns a small set of distinct propositions rather than another ranked catalogue: best overall fit, lower cost, or an option that serves a different priority.

Each proposition states why it belongs, which constraints it meets and what trade-off the buyer would accept.

EVIDENCE & TRUST

Generated prose is not evidence.

Every material claim should retain a route to its source, freshness and confidence. Missing or mixed evidence should remain visible rather than being smoothed into persuasive copy.

The current concept is recommend-only and stops before purchase. Authority over transactions would have to be earned through observed usefulness and explicit user choice.

MATURITY & NEXT EVIDENCE

An accepted prototype; the evidence is still ahead.

The publicly accessible fixture-only prototype makes the proposition testable without committing to product architecture or live integrations. Its interaction mechanics and access have been verified, and it is accepted for a six-session moderated comprehension study.

Formal enrolment is open, but no session or finding has been recorded. The next gate is observed evidence that buyers understand the need-first, three-proposition, receipts-led relationship before any later experiment is authorised.

EVIDENCE & BOUNDARIES

The private repository records the buyer-side thesis, accepted fixture-only stimulus, issued study materials and formal enrolment state—not a working shopping service.
The supplied screens use synthetic products, prices and evidence. They do not depict live offers, merchant integrations or working commerce.
Prototype mechanics and public concept access are verified, but no participant session, comprehension finding, market result or engineering foundation is claimed.

WHAT I CARRY FORWARD

A useful shopping agent may sometimes recommend no transaction.

The next gate is the moderated comprehension study—not more interface detail. Participant evidence must show whether people understand the buyer-side allegiance, visible trade-offs and claim-level receipts before the concept earns a wider build.

Explore all selected work