AI-assisted development is radically changing software engineering flows and roles, though as a hybrid problem-solver, I've been more or less working this way my whole digital career. I've contributed as facilitator, researcher, designer, architect, developer, tester and manager — whatever my team needed to succeed at the time.
With AI, I'm just more the product owner than ever before, especially in my own house.
House Rules
Ship quality fastDeliver aligned, useable work as fast as possible for feedback and alignment, repeat and refine on cadence against established measures.
Measurable goalsEstablish early and constantly deliver on what matters to customer most.
Where code is enoughDeterministic code does what must be done the same every time. Models run only where judgment pays, so products use less compute & incur less cost.
Agents in harnessUse LLMs only with clearly bounded roles, consistent skills/context and clearly defined outcomes set for every token spent.
Learned in enterprise
If that sounds like nothing new, it's because building on-brand custom software on large teams of humans teaches many efficiencies that also align with creating efficient, reliable LLM agents & systems.
Here's where I learned mine.
Global accountingCollaborative real-time accounting appGreenfield web app built to serve 500,000+ concurrent users. First front-end hire, interim designer & delivery lead for 20+ team, leading early Angular 2+, NgRx adoption and building first UI component library resuable across modules.
Regulated healthcare0-1 in four weeksFirst AI-native build: client-facing testing tool, made with early agentic support by me as effective product owner; shipped in four weeks to unblock a flagship rollout.
Healthcare ITMission critical modernizationLed larger team to move live, patient care product from on-prem to AWS, legacy code to latest frameworks and test suites with zero customer disruption. Architected branded UI component library for all Angular apps in modernizing this one, cutting UI development time over 50% in soe cases.
Real-time collaborationPandemic pivotWhen COVID closed core-business IRL training, I helped drive our product's rapid pivot to a virtual classroom experience, helping company maintain value delivery & revenue through lockdowns and demonstratin resilience of UI component and state management architecture decisions.
AI Case Studies
Agents in harness
Remember your lessons.
Individually defined agents also share agency skills and policies: what 'ready' and 'done' mean, language and coding standards, and more. All work moves forward through gates managed by agents or human review & curation. Every lesson learned flows back into collected agency wisdom for the next work to be done. Simple 'one-way' enterprise UI engineering pattern:
Buttons & form elements are essentially design tokens themselves; their UX consistency is an easy way to understand trust-building in design, because users should always know where to click next whatever their intent.
In this model, branding, focus, keyboard and disabled states live inside one button component, so accessibility and performance concerns get solved once and every instance inherits solution when published.
Simialrly, data flows down through inputs and events flow back up, so any team can use it without knowing how it's built. Tailor UI is built up of reusable UI primitives in the same way.
One-way architecture like this is also a common state-management pattern. We're applying same conceptual flow in building an agent harness that will deliver reliable work.
How big is this agency?
25
roles
126
policies
72
skills
13
gates to ship
Ship quality fast
Work products use single source of truth.
Our in-house communications use the same flows we build for clients so turnaround is quick, clear and consistent. Established brand fundamentals drive every new work product, from visual design to brand voice. We build master artifacts in HTML/SVG and CSS so we can rapidly iterate and deliver expressive, brand-aligned docs in any desired format for review, approval and implementation.
JHC Proposals HTML/PDF
JHC Design Documents HTML/PDF
JHC Social Carousels HTML/PDF
Heather Reilly - Speaker Kit HTML/PDF
Rockstar Blends - Wholesale HTML/PDF
Rockstar Blends - Live Events PDF/Print
Measurable goals
$148.00/month to $8.50
Our first ecommerce solutions for Rockstar Blends wanted a faster customer experience, an easier administrative backend and a lower monthly bill, setting a clear roadmap for ecommerce development in Tailor, our house style website builder. We shipped first live version in September without any business disruption.
Lighthouse 12.8.2, mobile, three runs each, November 2, 2026; the rented shop's 70 is PageSpeed Insights, June 12, 2026. Bands are Google's own ratings.
Where code is enough.
90% less post-production time.
Established podcast took 4-5 hours of human time to review, prepare search-optimized summary for submission to podcast platforms and craft optimized blog post with highlight quotes. Social content and reels took another 4-5 hours per episode. New "podcast pipeline" application drafts every episode's titles, summary, blog post, quote cards and reels from automated transcripts. Human review & adjustment time down to around 30 minutes per episode from 'stop recording' to 'published on Apple, Spotify, blog and social'.
Application flow:
Measurable outcomes
8 hours of raw video.
Rockstar Blends founder co-hosted an all-day online summit live with multiple panels, speakers and topics - leaving her one 8 hour video file to convert into communications and social content. We quickly adapted our podcast capabilities to create a longform video editor that prepares full length videos for publication, and then creates search-optimized short videos and social content. Code transcribes, agents find the speakers, the search terms and complete thoughts for code to structure and present for human review. In phase 2, code generates reels from approved phase 1 structured data, and agents generate summary texts, captions, alt and hash tags. On final creative approval, loader ships selected videos to YouTube with search optimized titles, captions, etc.
The video editor's final run: the compressed long-form video, the blog post and 19 reels with credits and captions, 5 hours of a person's time.