Agentic engineer. Product judgment. Practical delivery.

Software shaped by the work, not the other way around.

Practical software starts with the shape of the work: the awkward handoffs, edge cases, and operational gaps that off-the-shelf tools rarely fit. I bring domain judgment and an agentic build loop that compresses the path from real workflow pain to a working software surface. MindServe and ShelfFinder are the current proof.

Start a conversation See the work

20 yearsoperator-side workflow and implementation judgment

Azuredeployment target for practical software surfaces

AI loopsClaude, Codex, and an agentic loop to production

Atlier presentation layerRound One

Suite surfaceSoftware surface

MindServe

Cafeteria operations software, with StockSense as the central data layer.

Work surface

Voice surfaceSoftware surface

ShelfFinder

Voice-first grocery navigation shaped around natural shopping intent.

Work surface

Agentic work layerEmerging product

ProjectDesk by Atlier

A shared command surface for building with agents, from first local setup to cloud-coordinated work.

First product

Builder arc

The work came first. The build loop came later.

For two decades I worked close to real operational software: implementations, support, training, and the recurring gap between how work happens and how systems expect it to happen. Agentic engineering changed my role in that gap. I can now turn the workflow judgment I earned in operations into working software surfaces.

Operational judgmentYears spent with operators, edge cases, implementations, support, and the practical friction most software misses.

Agentic build loopClaude, Codex, Linear, and Azure compress the path from workflow judgment to a working software surface.

Public proofThe site shows live surfaces, curated proof repositories, and architecture notes without exposing production source.

Current work

The apps on the desk

These are not sales claims or polished case studies. They are software surfaces I use to show how I think, design, organize systems, and build.

MindServe

Software surface

Cafeteria operations software. StockSense is the central data layer; RetailMind, QuickServe, and MealMind are application surfaces around it.

Backend brainStockSenseInventory, recipes, costing, purchasing, and AI-assisted invoice import.

FIFO costing
vendor invoice import
multi-tenant facility scope

Self-serviceRetailMindEmployee and guest ordering surface connected to StockSense.

kiosk and mobile ordering
menu data from StockSense
guest-facing flow

Cashier POSQuickServePIN-based cashier workflow, shifts, payments, and Build-It customization.

cashier-first workflow
shift operations
customizable item builds

Meal orderingMealMindPhone-start employee and guest meal ordering surface for guided cafeteria workflows.

guest-facing flow
facility and location scoped
guided meal start

Read the proof story ->

ShelfFinder

Software surface

Grocery navigation for people who want to say the list, refine the trip, and get store-aware direction without wrestling a search box.

Voice-first groceryShelfFinderSay the list, refine the trip, get a store-aware route.

multi-item parsing
store-aware routes
Web Speech and Deepgram
intent over keyword search

Read the ShelfFinder proof story ->

ProjectDesk

Emerging product

Atlier's first concrete product surface: a shared command desk for projects, queues, agents, handoffs, and proof-bearing development.

Local command companionProjectDesk DesktopFor builders getting started: a signed Windows desk that can see local repos, run local proof, and keep agent work visible beside the machine doing the work.

beginner-friendly local surface
repo and installer awareness
desktop MCP connector
build and walk support

Shared command surfaceProjectDesk CloudFor deeper agentic development: a hosted desk where project state, queues, handoffs, and proof can live beyond one laptop.

Postgres-backed shared truth
operator and agent queues
road-ready project visibility
API and MCP command path

Read the ProjectDesk proof story ->

Technical proof repositories

Curated proof, not production source.

These public, sanitized repositories are prepared for technical conversations. They show architecture, ADRs, operating judgment, security posture, and selected safe excerpts without exposing the production code.

Public proof repo

Grocery

Clean Architecture, ADRs, operations, and selected safe code excerpts.

Clean Architecture
ADR digest
safe code excerpts

Open proof repo ->Public proof repo

MealMind

Employee and guest meal ordering, protected data boundaries, voice, and security posture.

guided ordering flow
security posture
voice and AI notes

Open proof repo ->Public proof repo

MindServe

Suite architecture, tenancy, operating model, and intelligence-layer direction.

suite architecture
tenant boundaries
operating model

Open proof repo ->

How I work

Agentic engineering, product judgment, practical delivery.

Find the real workflow.Start with operator pain, constraints, and the moments software usually misses.
Spec with AI as a thinking partner.Use Claude for architecture, edge cases, narrative, and ruthless scope discipline.
Compress the delivery loop.Keep production source private, expose curated proof when useful, track work in Project Desk, execute with Codex or Claude Code against the repo, deploy on Azure, and use the running surface until the unclear parts become obvious.

Doorways

Different reasons to start a conversation.

Hire me

Bring me into the work.

For teams that need an agentic engineer with product judgment, workflow sense, and a practical path from idea to working software.

Talk about a role

Bring me in

Consulting, project-scoped.

For workflow design, integration thinking, internal tools, prototypes, or AI-assisted build execution that needs practical judgment.

Request a scoping call

Partner with me

Advisor, fractional, or build partner.

For founders or small teams who need agentic engineering, product judgment, implementation sense, and a clear-eyed build partner when the fit is right.

Check availability

Agent-readable layer

The structured truth ships with the page.

Humans get the work surface. Agents get the same context as structured data in the page head - who Justin is, how he builds with agents, what he is working on, and how to reach him.

View agent context

MindServeSoftware surface: Cafeteria operations software: StockSense as the data layer, with RetailMind, QuickServe, and MealMind as application surfaces.
ShelfFinderSoftware surface: Voice-first grocery navigation that turns a spoken list into a store-aware shopping route.
ProjectDeskEmerging product: Agentic work surface by Atlier: desktop and cloud desks for queues, handoffs, decisions, and proof-bearing development.
MethodIn daily use: Product judgment first, AI as architecture partner, agentic engineering loops, verified by using the software surface.
Proof reposPublic: Curated public proof repositories exist for Grocery, MealMind, and MindServe. They show architecture, ADRs, operations, and selected safe excerpts without exposing the production source.