Jason Dicken

AI-assisted application developer

I build real-world software with AI.

Restaurant TechnologyBusiness AutomationAI AgentsCustom Applications

I combine over 25 years of restaurant industry experience with modern AI-assisted development to turn complex business problems into practical, working software. Using tools including Claude Code and Codex, I design, develop, test, and deploy applications that help businesses operate more efficiently.

Tools and practice

  • Claude Code
  • Codex
  • AI agent orchestration
  • Workflow automation
  • API integrations
  • Application development
  • Business systems

Evansville, Indiana · open to remote W-2 roles and contract work

Featured projects

Restaurant software and business systems I've built and run

Each one names its real status. "Production" means it runs a real business today; nothing here is described as customer-deployed unless it is.

01

Restaurant technology · AI-powered operations

Cobblestone POS + Daisy

A restaurant point-of-sale I built and ran my own shop on, with Daisy, an AI assistant who answers the owner's questions from live shop data.

  • Point of sale, online ordering and a merchant site
  • Digital menu boards and a DoorDash integration
  • Bar inventory that depletes stock from sales
  • Daisy: sales, food cost and mid-shift troubleshooting
Production · my own shopCase study →

02

Customer loyalty · restaurant marketing automation

Cobblestone Perks

Loyalty and marketing for local restaurants: customers join on a counter tablet and earn rewards, and Claude-powered agents plan and write the campaigns.

  • In-store sign-up kiosk, no customer app
  • Points and check-in rewards, redeemed at the counter
  • Email, SMS and a shared marketing calendar
  • AI marketing agents that suggest, write and analyze
ProductionCase study →

03

AI agent orchestration · business automation

Cobblestone CRM

A custom sales CRM where an orchestrator agent, Oreo, directs 20 specialists, and no message reaches a customer until a person approves it.

  • Seven-stage sales pipeline and lead scoring
  • Orchestrator over 20 specialist agents
  • Human approval on every email, text and proposal
  • 30+ scheduled jobs, Telegram, Android companion app
Production · runs my business dailyCase study →

04

Restaurant inventory · AI-assisted development

Cobblestone Galley

Offline-first inventory and ordering for barge and towboat galleys, built by two AI coding agents working in one codebase under a written coordination protocol.

  • Inventory, PAR levels and purchasing
  • Chef requests, captain approves, purchase order goes out
  • Works offline on a shared galley tablet
  • Two coding agents coordinated with a baton protocol
Active developmentCase study →

How I build software

AI writes most of the code. I'm responsible for whether it's right.

Claude Code and Codex speed up the implementation. The requirements, the decisions, the testing and the final result are mine.

  1. Discover

    Understand the business problem, the workflow, the users and the requirements.

  2. Architect

    Plan features, data, integrations, automation and the user experience.

  3. Develop

    Direct Claude Code, Codex and coordinated agents against written requirements.

  4. Test & validate

    Run the workflows, find the bugs, verify the integrations, send it back.

  5. Deploy & improve

    Ship it, run it, fix what breaks in real use, and keep improving it.

The full process, stage by stage →

Beyond the prompt

Generating code is the easy part

An agent will write a thousand lines on request. Getting software that does the right thing, and keeps doing it, takes everything else.

Understanding the business

Knowing that an allergy question isn't a support ticket, or that a barge galley's "vendor" is a shopper with a receipt, not a warehouse with a price list.

Breaking the problem down

Turning "we need a CRM" into data models, approval rules and jobs an agent can build one piece at a time.

Managing the agents

Handoff documents, dated decision logs, and one writer at a time, so parallel agents don't overwrite each other.

Evaluating the output

Reading what was built against what was asked for. Agent code that looks right and passes a glance is where the expensive bugs are.

Debugging production

When a job runs five hours early or a page 500s with an empty log, finding the cause in the running system.

Delivering reliably

Testing, deploying, running it daily and owning the fix. Two of these systems have run real businesses day to day.

Additional AI & development projects

Evaluation, prompt testing and publishing

A support assistant that knows when to stop talking

TypeScript · Claude API · LLM-as-judge · public repo
Complete as an evaluation

A shop's chat assistant handles the easy questions well. What matters is the ones it shouldn't answer: allergies, refunds, angry customers. I wrote four prompt versions and tested each against 40 development cases: 27/40 → 40/40. On nine fresh questions written from real customer messages, the final prompt passed 4/9. That gap is why it isn't called customer-ready.

Read the case study · Public repository

The Owner's Notebook

Python · openpyxl · static-site pipeline
Published

A library of food-cost, waste and par-level guides, calculators and Excel worksheets for restaurant owners, produced by an automated publishing pipeline. When the first version read like generic AI writing, I rebuilt the pipeline instead of editing the output.

For restaurant software teams

Restaurant industry experience meets AI-powered software development

POS, ordering, loyalty, inventory and AI assistants, built by someone who has worked the line, done the ordering and signed the payroll.

Work with me

Open to remote employment, contract and freelance work

Restaurant applications, AI agents and automation, or custom business software. If you have a problem that needs a working system, tell me about it.