AI Agent Development
Work that eats hours of someone's week and follows rules you could write down — but never quite the same way twice.
- RAG over your own data
- In-product and internal agents
- Human approval gates
- Evals & run logs
Senior-led engineering studio
From plain English to production software.
We design and build AI agents, automations, and custom software that do real operational work — architected and shipped by senior engineers.
Task from the client, in their wordsReconcile yesterday's parts orders against supplier invoices and flag any mismatch over $50.
PLANFour steps: pull orders, pull invoices, match on PO, diff line totals.
TOOLdealer_api.orders(date="2026-10-27") → 142 records
TOOLsupplier.invoices(date="2026-10-27") → 138 records
STEPMatched 136 on PO number. 6 orders and 2 invoices unmatched.
STEP4 line-total mismatches over $50. Largest $412.80 on PO-88412.
HOLDAwaiting your approval before posting adjustments to the ERP.
DONEApproved. 4 adjustments posted. Summary emailed to parts@.
Senior-led engineeringArchitecture and delivery, not account management
AI agents in productionBuilt and deployed, not prototyped
Integration and modernizationSystems that have to keep running while they change
Security, data, and complianceLeast-privilege access, clear data boundaries, auditable logs
What we build
Complexity in. Clarity out.
Four kinds of work. Most projects start in one and pull in a second.
Business Process Automation
A process held together by spreadsheets, email threads, and one person who knows how it actually works.
- n8n & custom pipelines
- Marketing & analytics reporting
- Exception handling
- Monitoring & alerting
Custom Software & Integrations
Two systems that should talk to each other, and a vendor who says it isn't supported.
- Integration architecture
- API clients & webhooks
- Data mapping & reconciliation
- Tests against live sandboxes
AI-Assisted Engineering
An application that still works but nobody wants to touch, and a team that can't afford to stop shipping to fix it.
- Code review & test generation
- Issue triage & release checks
- Incremental migration
- Architecture assessment
How we work
AI moves fast. Judgment decides where.
Five stages. AI-assisted implementation compresses the middle; experienced engineering judgment governs the parts where being wrong is expensive.
- 01
Discover
Understand the actual problem, the constraints, and what "done" means to you.
HUMAN-LED - 02
Architect
Decide the shape: data flow, failure modes, security boundaries, what stays manual.
HUMAN-LED - 03
Build
AI-assisted implementation against the agreed architecture, reviewed every step.
AI-ACCELERATED - 04
Validate
Tests, evals, edge cases, and a security pass before anything touches production.
AI-ACCELERATED - 05
Deliver
Deployed, documented, and handed over so your team can maintain it without us.
HUMAN-LED
Experience
Where we've shipped.
Deliberately narrow. These are the domains we know well enough to answer straight in the first conversation.
01
Automotive aftermarket
The deepest domain. Dealer service, estimation, parts ordering and eCommerce — where a quiet integration failure costs money every day it goes unnoticed.
02
AI agents and automation
The core of the practice. Tool access, retrieval over your own data, approval gates, and run logs you can audit afterwards.
03
Systems integration
Connecting platforms never designed to talk to each other, and making the seam survive bad data, rate limits, and silent API changes.
04
Architecture and modernization
Systems that still work but have become expensive to change. Assessed, planned, and migrated without stopping delivery.
Why SmashGlass
A studio built around senior judgement.
No bench, no junior team, and no account layer between you and the people writing your software.
- Executive-level technical judgment
- Architecture calls made by someone who has owned the outcome.
- Hands-on delivery
- The engineer who scopes your project is the one who writes it.
- Production engineering
- Systems that run unattended and recover from failure.
- AI agent architecture
- Tool design, approval gates, evals, run observability.
- Reliability
- Testing and hardening are in scope, not a change order.
- Direct collaboration
- One channel. Straight answers about what is hard.
01
02
03
04
05
06
Start a project
Let's build something intelligent.
Tell us what's slow, breaking, or not getting done. You'll get a straight answer about whether it's worth building and roughly what it costs — usually within a day.