Four engagements.
One engineer.
Each engagement begins with a scope document and ends with production-ready code. Pricing is fixed or capped. Every deliverable is async-first — daily Loom updates, never status meetings.
Fixing the mess.
/ what it is
AI code generators ship fast, but they leave fragile, unmaintainable systems. I open your repo, trace the architecture, profile the database queries, check the auth implementation, and identify every place the AI hallucinated an API that doesn't exist or skipped an edge case that will break in production.
You get a severity-ranked remediation plan — so you know exactly what to fix first, what it costs, and what to ignore./ what I deliver
- Audit report — architecture, security, performance, and AI-generated code assessment. 8–15 pages, branded, readable by non-engineers.
- Remediation plan — severity-ranked, with estimated effort per fix and a recommended sequence.
- 15-min Loom walkthrough — key findings explained visually, on screen.
- Fixed-price remediation quote — if you want me to fix what I found.
/ what I check
- Security — auth, RLS, input validation, API protection, secrets management.
- Architecture — component coupling, state management, module boundaries.
- Performance — bundle analysis, query efficiency, Core Web Vitals.
- AI code quality — hallucination patterns, missing edge cases, inconsistent patterns.
/ pricing tiers
- Wedge Audit (small codebase, <20 files) — 48 hours, $900.
- Standard Audit (production app, 20–80 files) — 5 business days, $2,400–$3,200.
- Deep Audit (complex app, 80+ files, infra review) — 10 business days, $4,500–$6,000.
If you already know exactly what's broken and just need someone to fix it, skip the audit and book a Sprint MVP or retainer. The audit pays off when the answer isn't obvious.
Production AI workflows.
/ what it is
Not generic chatbots. I build specific, production-grade AI workflows: customer support that triages itself, documents that process themselves, knowledge bases your team can query in plain English, data extraction pipelines that replace manual spreadsheet work. Integrated into your existing infrastructure. Guardrailed. Production-safe.
You get an AI system that works reliably in production — not a demo that breaks with real data./ what I deliver
- Agent scoping document — input/output spec, success criteria, cost model.
- Technical architecture blueprint — LLM selection, pipeline design, data flow.
- Production agent code — deployed, tested, with guardrails and fallbacks.
- Prompt library — all system prompts, versioned, documented.
- Monitoring setup — logging, cost tracking, error alerting.
- 30-day post-launch support — bug fixes and prompt tuning included.
/ complexity tiers
- Simple (single LLM call + structured output) — 1–2 weeks, $6,000–$8,000.
- Standard (multi-step pipeline + RAG + tool use) — 3–4 weeks, $14,000–$20,000.
- Complex (multi-agent orchestration + production UI) — 5–6 weeks, $22,000–$28,000.
/ what I need from you
- A clear problem statement: what manual process are we automating?
- Sample data or documents the agent will process.
- Access to existing systems the agent needs to integrate with.
- One stakeholder who can define "success" in measurable terms.
If you want a chatbot that answers generic questions from a PDF, use an off-the-shelf tool. I build custom AI systems for specific business workflows where reliability and integration matter.
Sprint MVP builds.
/ what it is
For seed-stage founders who need to show investors a working product, not a pitch deck. From zero to a venture-grade V1 — auth, payments, database, core business logic, and responsive UI. Type-safe, secure, tested. Shipped with boutique-agency quality at a fraction of the cost and timeline.
A traditional agency quotes 3 months and $60k. I ship in 4 weeks at a third of the cost./ what I deliver
- Up to 5 dynamic views, fully responsive, with real data.
- Auth + payments — Supabase Auth, Stripe checkout, subscription logic.
- Database + API — PostgreSQL schema, RLS policies, server actions.
- Testing — 80% coverage on critical user paths (Vitest).
- Deployment — production-ready on Vercel, documentation, codebase walkthrough Loom.
- 30-day post-launch support — bug fixes and critical patches included.
/ how it starts
- $900 Architecture Sprint — 48h prototype, DB schema, technical blueprint. Credited if you proceed.
- Contract + 40% upfront — MSA + SOW signed before first line of code.
- Daily Loom updates — progress visible every day, staging link updated daily.
- 30% at mid-milestone, 30% on delivery — IP transfers to you on final payment.
/ the stack
- Next.js 15 — App Router, TypeScript strict, React Server Components.
- Supabase — PostgreSQL, Auth, RLS, Edge Functions.
- Stripe — checkout, subscriptions, billing portal.
- Vercel — deployment, preview URLs, edge network.
- PostHog — analytics. Resend — transactional email.
If you need a landing page, use Framer. If you need a simple internal tool, use Retool. I build custom production applications where architecture, security, and scale matter.
Velocity retainer.
/ what it is
For teams that shipped a V1 and need an embedded engineer for the next 90 days. Feature development, bug fixes, database migrations, performance tuning, and architecture guidance — delivered weekly, asynchronously, with direct Slack access.
/ what you get
- Weekly feature releases — 1–3 features per week, prioritized via shared Linear board.
- Bug fixes — critical within 24h, non-critical within the sprint.
- Architecture reviews — bi-weekly 15-min Loom on codebase health.
- Direct Slack access — for technical questions and architecture advice.
- Monthly CWV review — performance monitoring and query optimization.
/ what it isn't
- Not a full-time seat. Not a fractional CTO arrangement.
- Not 24/7 on-call. I'm one person; the rate reflects it.
- Not ad-hoc meetings. Async-first, Loom-driven, daily staging updates.
/ how to start
- Sprint MVP or Audit first. Retainer makes sense after I know your codebase.
- Three-month minimum, then month-to-month with 30-day notice.
- Cancel any time after the first three. No exit theatrics.
If you need someone to ship features 40 hours a week, hire a full-time engineer. The retainer is for maintaining velocity and architecture, not replacing an engineering team.