Almost every retail support contact is about a specific order. An assistant that cannot see order status, carrier tracking, returns history and stock position is answering a different question from the one being asked.
All E-Commerce & Retail →
They are built over the help centre. That makes them able to explain the returns policy and unable to answer “where is my order”, which is widely reported as the most common contact reason in retail. The customer gets a policy paragraph when they wanted a delivery date, and the deflection statistics look fine while satisfaction falls.
The fix is integration rather than a better model. The agent needs read access to the order management system, the carrier tracking feed, the returns system and stock availability — and, for real deflection, write access to a bounded set of actions: initiate a return, reissue a label, update a delivery address before dispatch, apply a goodwill credit within a defined limit.
That write access is where the engineering seriousness is. Every action needs a permission boundary, a value limit, an audit record and a rollback path. An agent that can issue refunds without a cap is not an efficiency; it is an incident waiting for a prompt-injection attempt in a customer message.
authenticated session
order · account · history
OMS · carrier · stock
within a permission envelope
action + reason logged
with full context
It depends almost entirely on integration depth rather than on the model. An agent that can see orders and take bounded actions resolves a large share of routine contacts; one over a help centre resolves very few. We would rather scope the integration properly than quote a rate we cannot stand behind on your systems.
Within a value limit you set, with every action logged and reversible, and with the limit enforced in the tool layer rather than in the prompt. Below a threshold the goodwill cost of automating is far lower than the handling cost of not doing so — but the threshold is a commercial decision, not a technical one.
By escalating early. Frustration detection is one of the more reliable classification tasks available, and the correct response to it is a person, not a better-phrased apology.
The integration is the product. The conversational part is the easy half.
30-minute technical call · no deck
What we built, what stage it is at, and a link to the live thing wherever there is one.
yourOS is an operating system with an AI at its heart. You talk to it like a person, out loud or typed. It makes your calls, plans your days and works on your projects with a crew of agents, on your own private server. Our own product, built from the first commit; the waitlist is open.
Website, backend and app assets for Sonora, a free AI sound-therapy app on iOS and Android published by Cognitive AI.
Brand, website, prototype, apps on five platforms, the AI backend and the algorithm-intelligence pipeline for Podswap, a social growth engine that runs without a human in the loop.
In closed beta: Roxy, a private AI assistant with permanent memory running on infrastructure the user owns. Brand, site, product, backend and conversational design.
Live at coherence.com: brand identity generated with AI agents we directed, the motion system and website for the group behind Sonora, AboutAI, WakeUp and MudShadows. Agent work remains in build.
Live at domainbooth.com for DomainBooth, a premium domain brokerage: a new animated mark, every page redesigned and rebuilt with designed mobile layouts, and a custom CMS for its sales record, featured names, press and enquiries.
Apps, platforms and campaigns for these teams, long before the AI work. Every one is written up on the work page — what we did, and where our part ended.
