An LLM brain with real tools
The model reasons; durable tools fetch data, write code, run checks, open pull requests, and report evidence.
01 / Shipped work
Every card is a shipped system or the architecture behind one: real screenshots, real diagrams, releases you can trace. No stock photos, no mockups.
IndepAI
Deterministic FIRE math, Supabase data, and an AI coach that works strictly inside user consent.
HSK WebKD
A WebKD architecture path across NestJS modules, RCP and TKD device domains, Postgres, Redis, and Helm release gates.
Agentic framework
Research agents, code agents, review gates, quality control, and delivery evidence in one repeatable loop.
Kontenero
Lead intake, validation, Supabase storage, and Slack follow-up. A container-rental funnel the operator can trust.
Hanbud
Catalog discovery, product detail, cart behavior, inquiry logic, and PL and UA content paths for a real buyer journey.
IndepAI architecture
The product layer, AI coach boundary, deterministic calculators, Supabase persistence, and consent flows mapped as one system.
02 / Agent infrastructure
We build agents the way we build production services: tools, memory, review gates, telemetry, rollback. Your team runs it after we leave. It isn’t a demo that dies after the pilot.
Skills encoded from your company
Your sales, support, operations, and engineering patterns become reusable agent skills with clear boundaries.
Human gates stay explicit
Agents inspect, draft, test, summarize. Anything touching production keeps approvals, logs, and a rollback plan.
03 / How we work
Built for companies with devices, data, legacy systems, compliance pressure, and AI ambitions. Teams that still have to ship every week.
Model the domain
Actors, data, jobs, devices, queues, approvals, owners, all named before the first line of code.
Build the slice
One route, one workflow, one integration, one release path. The smallest real system beats the broadest slide deck.
Gate autonomy
Agents accelerate discovery, writing, testing, documentation. Review boundaries stay explicit and human.
Leave proof behind
Every engagement ends with diagrams, runbooks, dashboards, and prompts your team keeps.
04 / Focus areas
The sweet spot: product thinking, backend architecture, cloud operations, and AI agent workflows meeting in one hard problem.
AI products with deterministic business logic
Autonomous agents for company operations
Kubernetes and Helm production platforms
NestJS backends and integration layers
Design systems and conversion pages
Documentation ready for a public case study
06 / Next step
We start with a fixed-price, two-week audit: we map the domain, ship a working slice, and leave documentation your team keeps, whatever you decide next.
fixed price · two weeks · yours to keep