Agent operations system for shipping workflows
Distributed AI operating environment for delegating, checking, and shipping workflow implementation work.
Timeline: Built iteratively as the operating layer for real agent work across multiple machines.
Team: Solo builder/operator.
Stack: OpenClaw, LiteLLM, vLLM, Docker, systemd, Caddy, Tailscale, GPG vaults, Windows, Linux, macOS
Problem: AI implementation work was fragmented across chats, tools, machines, credentials, browsers, codebases, and deployment environments. The system needed memory, task routing, model fallback, browser access, and verification discipline.
What Kenneth built:
- Designed a multi-host agent operating model with memory/wiki context, tool permissions, sub-agent delegation, scheduled jobs, and verification rules.
- Routed workloads by host capability: local coordination, GPU/model serving, media processing, browser automation, and infrastructure operations.
- Integrated cloud model usage with local fallback through LiteLLM/vLLM and OpenAI-compatible endpoints.
- Created SOPs for build checks, smoke tests, browser checks, endpoint validation, blocker reporting, and deploy verification.
Architecture: Request -> OpenClaw orchestration -> tools/sub-agents -> local/cloud models -> verification gates -> deploy/report.
Reliability: Uses permissioned tools, vault-based secrets, build/lint/smoke gates, deployment checks, and explicit blocker reporting.
Tradeoffs: Private by design: host access, credentials, logs, and customer/business data cannot be public proof artifacts.
Business impact: Turns AI work from ad hoc chat output into a repeatable operating system for building, debugging, deploying, and auditing software/business workflows.
Proof: Architecture notes, repeated deploy/build validation logs, and public proof surfaces.
CRM automation that recovers follow-up
Follow-up automation architecture for inbound business conversations.
Timeline: Built as CRM and follow-up automation inside a broader business operations stack.
Team: Solo builder/operator.
Stack: Next.js, Supabase, webhooks, WhatsApp architecture, Vercel, TypeScript
Problem: Manual WhatsApp follow-up creates missed leads, weak context, and repeated operator work. The system needed structured capture, classification, logging, and follow-up scheduling.
What Kenneth built:
- Implemented inbound classification, contact/profile upsert, conversation logging, message logging, and follow-up scheduling.
- Built webhook routes, inbox UI, simulated outbound fallback, cache fixes, local build checks, smoke tests, and production endpoint validation.
- Kept private contact data, conversations, credentials, and business logs out of public proof surfaces.
Architecture: Inbound WhatsApp/webhook event -> classification -> Supabase contact/profile upsert -> conversation/message log -> follow-up schedule -> inbox UI.
Reliability: Local build checks, smoke tests, endpoint validation, no-store cache headers, and private-data boundaries.
Tradeoffs: Public case study describes architecture and scope without exposing real customers, phone numbers, private messages, or credentials.
Business impact: Turns repeated follow-up into a trackable CRM workflow with clearer ownership, history, and next actions.
Proof: Scoped case-study details, deployment/process validation notes, and sanitized proof screenshots.
Public AI interaction surface
Public AI agent interaction surface built to feel like a product, not a prompt box.
Timeline: Prototype-to-public demo sprint; current public surface is live.
Team: Solo builder.
Stack: Next.js, TypeScript, Vercel, AI workflow architecture
Problem: Agent demos often look like internal tools. The project needed a public surface that could communicate AI workflow value quickly without exposing private backend actions.
What Kenneth built:
- Built a public agent/chat product surface with responsive UI and production deployment.
- Structured the experience around product proof instead of a generic chat interface.
- Kept private agent actions, credentials, and production logs out of the public surface.
Architecture: Browser UI -> Next.js app -> private AI workflow/backend layer -> deployment on Vercel.
Reliability: Public route is smoke-tested after deploy; private actions and credentials are intentionally not exposed.
Tradeoffs: Kept the public demo lightweight instead of exposing private backend controls or logs.
Business impact: Provides a live AI-workflow proof link that can be inspected before a sprint conversation.
Proof: Live demo and screenshot proof page.
Customer-facing mobile workflow
Customer-facing mobile and SaaS workflows for onboarding, check-ins, chat, logs, plans, and AI-assisted estimates.
Timeline: Built and captured through product QA flows in 2026.
Team: Founder-led / solo implementation.
Stack: React Native, Expo, Next.js, React, TypeScript, Supabase, Postgres, Vercel, AI estimate foundations
Problem: Customer workflows often split communication, tracking, admin tools, and AI assistance across disconnected surfaces. The product needed one coherent workflow for daily use and operational follow-up.
What Kenneth built:
- Built mobile app surfaces for dashboard, chat, profile, plan, appointments, food diary, meal categories, and progress.
- Built SaaS/admin surfaces for CRM, leads, appointments, onboarding, integrations, patient portal, and role-based workflows.
- Implemented AI estimate foundations and product flows while keeping private health, billing, and admin data out of public proof.
Architecture: Mobile app + SaaS surfaces -> private product/backend layer -> role-based workflows -> public marketing/SEO surface.
Reliability: Public proof uses screenshots and scoped descriptions; private customer data, backend logs, and production credentials are not exposed.
Tradeoffs: Public proof shows product surfaces and flows instead of production customer data or private clinical workflows.
Business impact: Shows that Kenneth can ship customer-facing workflows, not only internal dashboards or automation scripts. Public metrics are currently limited to build scope and verifiable surfaces until customer ROI data is approved for publication.
Proof: Live public surface, mobile screenshot set, and scoped case-study details.