A marketing site, booking platform, and MCP server for Dallas Sport Collective, a six-trainer gym in North Texas. An athlete can book from whichever AI they already use, and the owner approves with a tap.
Enterprise plumbing for a gym with six trainers
So the first build was the front door. Athletes create their own accounts, sign the waiver on the way in, and the owner assigns each new member to a trainer before anyone books a session.
Athlete login and registration. A hundred-plus people moving off text threads and a spreadsheet and onto one roster the software can work with.
Book a session from your own AI.
An athlete never has to open the app. They ask whichever AI they already use, and it reads their real schedule and can put in a session request.
Eleven tools cover the gym overview, the program list, trainer profiles and availability, the athlete's own sessions and pending requests, slot suggestions, booking requests, and cancellations. Reads come back instantly, and a write only ever creates a pending request the owner has to approve. Connecting runs through an OAuth consent screen with short-lived, rotating tokens, and access revokes from the dashboard in one tap.
The athlete asks their own AI, and the AI asks the gym
Then the activity around it, the full trainer roster and the program menu. The same trainer data feeds the MCP server, so a connected AI describes a coach from the actual record.
Dashboard, trainer bios, and the program list. Each trainer expands to specialties and certifications. The programs run from strength and speed work to onsite physical therapy, prenatal fitness, and Combine prep.
Managing a packed week from a phone, between sessions.
The queue where every request lands, a week calendar with the session count per day, and a member list flagging waiver and trainer-assignment status.
The owner can say a whole week out loud: schedule Marcus with Scott every Monday, Wednesday, and Friday at 3pm for a month. The scheduler proposes the batch, accepts the ten clean slots, flags the three it skipped for conflicts, and waits for a "commit" before a single session lands.
However a booking comes in, it goes through the same checks
A palette with no color in it, one type family doing all the work, photography shot on the actual gym floor, and the same kit at every size.
Pure black for type and structure, pure white for the ground, and a short ramp of greys for everything between. No accent color, because the photography and the weight of the type bring all the contrast the brand needs. Type is mostly one family. Avenir Next runs the brand voice: Heavy for the wordmark and section heads, Demi Bold for subheads and CTAs, Medium for the body. A monospace sits underneath for the technical labels, the MCP URLs and session times.
The mark
Paired studyTexts and notes and a spreadsheet.
The platform is live at both locations. Athletes sign in and book, the owner approves from a queue or schedules a month in one batch, and a connected AI reads the schedule as it actually is.
Product Design
AI Integration
Full-Stack Engineering
Vercel
Model Context Protocol
OAuth 2.0
Claude + ChatGPT