Case studies
What we've built.
Every engagement delivered under a signed statement of work. Case studies below reflect real client problems, systems built, and outcomes measured.
Aug – Nov 2025
Conversational Voice Ordering System
Independent Restaurant Client
Problem
A busy small-business restaurant was losing 15-20% of call-in orders during peak lunch hours. Calls went unanswered, wait times stretched while staff juggled the phone, and employees who should have been preparing food were tied up taking orders. The restaurant needed a conversational phone system that could take orders in natural language, price them correctly, and route them to the kitchen, freeing staff to focus on the work they were hired to do.
Solution
An AI voice agent that answers the phone, sounds natural and conversational, takes the order, confirms each item and modifier back to the customer, calculates the total with tax and fees, provides an accurate pickup time, and logs the order for kitchen staff. Available every hour of every day. No missed calls. No held orders.
Flow
Call answered → order taken in natural conversation → items and price confirmed back to customer → pickup ETA provided → order logged and routed to kitchen.
Outcome
The system was built, tested, and validated end-to-end in staging. Voice quality, order accuracy, and operational fit all met the bar for launch. Production rollout was deferred due to an external platform integration constraint on the client's side.
Sep 2025
Multi-Location SKU Reconciliation
Multi-Location Convenience Client (3 retail locations)
0
SKUs audited
0.0%
of catalog flagged
0
price mismatches surfaced
Problem
Three retail locations ran the same point-of-sale system but maintained their product data independently. Pricing, categorization, and item descriptions had developed discrepancies over time across locations. The client had no consolidated view of the scope of the problem or where the financial impact was concentrated.
Solution
Collected raw SKU exports from each location, cleaned and normalized the data, then mapped every SKU into an organized master reconciliation sheet. Built an accompanying Excel dashboard for fast investigation: single-cell scan-code lookup, side-by-side 3-location comparison, and automated flagging across description, department, pricing, and price-group fields.
Findings
Of 11,608 unique SKUs, 4,737 flagged with at least one mismatch (40.8%). 1,890 retail price mismatches, with 96 single-SKU price spreads exceeding $5. Mean spread $1.24, median $0.40.
Outcome
The dashboard put every mismatch in front of the client in a format that was fast to investigate and easy to act on. The client used it to systematically standardize pricebooks across all three locations without needing to manually comb through 11,608 individual items.
In progress
Restaurant Intelligence
Internal product, deploying soon
What it is
A question-and-answer tool that lets a restaurant operator ask plain questions about their own business and get answers backed by their real numbers. It looks at their sales history alongside what's happening locally, then tells them what's coming and how to staff and stock for it.
Problem
Operators have their sales data and a rough sense of the local calendar, but nothing puts the two together. There's no single place that turns months of orders into clear patterns, lines them up against the events that actually change how busy a week gets, and shows where each answer came from. A generic chatbot will just make something up, which is the last thing you want behind a staffing or ordering call.
Where it stands
The core is built and working against live sales data. An operator can ask a question and get a sourced answer, pull up a sales dashboard, and see a forward-looking calendar of local events with a read on how each one is likely to affect traffic. What's left is tightening the pieces that make it dependable enough to hand to a client.
How it works
The rule it runs on is that it never guesses. Every answer has to point back to a real source, and anything it can't back up it declines to answer rather than fill in the blank. That one rule is what makes it usable in an actual operating decision instead of a novelty.
In progress
Marketing Operations Platform
Deploying to two independent restaurant clients soon
What it is
One platform that runs a local business's whole marketing operation in a single place: its website, social posts, email and texts, review replies, online ordering, and the reporting that ties it all together. Each business switches on only the parts it needs.
Problem
A small operator usually pays for a handful of separate services to keep any marketing going, and still ends up with a few generic posts a month for the money. Everything lives in a different tool, the content is thin, and more often than not the business doesn't even own its own website when it's done.
Where it stands
The first business is being built out now, starting with the content, the owner's approval step, posting to social and email, and online ordering. Catering, text marketing, and a reporting dashboard follow. It's built to be highly customizable, so each client gets a setup tuned to their own marketing needs.
How it works
At the center is a content engine that drafts as many posts as needed for each channel, far more than the services it replaces, and checks its own work so the posts don't all start to sound alike. Nothing goes out on its own. The owner sees the day's queue on their phone and approves, edits, or skips in a couple of minutes, and nothing publishes without that sign-off.