About

I build calm, transparent workflow systems for operator-owned outcomes.

The operator should not carry the chaos of automation. My work turns toolchains into clear workflow states: what agents and tools can do, what needs judgment, and what must stop with a reason.

Clear
No decisions pending

The operator can step away.

Review
Approval needed

Judgment is required before action.

Stop
Blocked with reason

The system explains why it paused.

One operating story

The biography only matters where it explains the work.

The biography matters only where it explains the work: why control comes before scale, how the method protects the operator, what the engagement promises, and how the wider system contributes.

01 / 04 Power needs control

Pressure made the operating principle concrete.

Machines, emergency medicine, veterinary care, and platform systems all taught the same lesson: capability becomes useful when ownership, protocols, and recovery stay visible.

I grew up between two reference points: a Porsche 930 Turbo and emergency medicine. One taught me that power needs control. The other taught me that when pressure rises, clear protocols matter more than improvisation.

Later, as an equine veterinary technician, I learned what continuity of care, logging, and operating discipline actually feel like in the real world. That stays with me in systems work now.

Today that shows up as calm, transparent, reliable workflow systems: fast where the rules are clear, visible where judgment is required, and recoverable when something goes wrong.

I am a Senior Systems Architect on the Marketplace Team at Webflow. That work keeps the problems concrete: brittle handoffs, unclear ownership, internal tools, onboarding systems, integrations, and platform infrastructure that have to survive real operators.

Evidence
  • Porsche 930 Turbo
  • Emergency medicine
  • Continuity of care
  • Webflow systems work
02 / 04 Protect the operator

Map, classify, control, then brief.

The Calm Operator Method keeps the workflow understandable before agent capacity expands.

01
Map the operating path

Find the workflow your team still completes or covers by hand and name the handoffs, owners, and failure modes.

02
Classify the judgment states

Separate safe work from approval-needed work and actions that should be blocked with an inspectable reason.

03
Ship the control layer

Use MCP, skills, runbooks, release checks, and trust receipts to make the workflow portable and controlled.

04
Brief the operator

Surface only the state that needs attention so the human returns for judgment, not constant monitoring.

Receipts
workflow mapjudgment statescontrol layeroperator brief
03 / 04 Keep the work narrow

One operating path should become trustworthy before the system grows.

The engagement removes unnecessary complexity, names the decision owner, and leaves the client with controls, evidence, and working software.

ApproachStart with the cleanup loop

Most teams need one workflow that stops creating manual recovery work before they need a larger AI initiative.

MethodSubtract before automating

The Subtractive Triad removes duplication, excess, and disconnection so automation has fewer failure paths.

Client contractBring the workflow and owner

Clients bring the operating constraints and decision owner. I bring diagnosis, controls, runbooks, evidence, and working software.

Salesforce, HubSpot, Notion, Slack, Procore, Webflow, MCP, and internal systems are useful only when ownership and recovery stay clear.

Receipts
cleanup loopSubtractive Triadclient-owned path
04 / 04 Each property has one job

The rest of CREATE SOMETHING sharpens the operating work.

Philosophy, research, experiments, and agency delivery remain distinct while passing useful evidence between one another.

CREATE SOMETHING operates as a connected system. Each property has a distinct job, and each one sharpens the others:

  • .ltd — Philosophy and principles
  • .io — Research and validated patterns
  • .space — Tools and experiments
  • .agency — Calm, transparent workflow systems, reliability controls, and enterprise extension (you are here)

Client work informs the research. Research sharpens the operating model. The operating model raises the bar on client work.

I am also building WORKWAY. When clients need fuller system development and onboarding than .agency is meant to carry, I provide a direct referral path to trusted partners, including Half Dozen.

Read the philosophyInspect the researchExplore the tools
Start with one workflow

Bring one workflow your team is ready to delegate.

I map the signals, decision owner, allowed actions, approval pauses, stop conditions, and proof record before AI runs it.

Talk through one workflow See the service path →
Owner
Workflow owner
Authority
Mapped control states
Proof
Safer first path
State
review
  1. 01 / Bring One workflow

    The manual operating path that should not need constant rescue.

  2. 02 / Map Control states

    What can run, what needs approval, and what should stop.

  3. 03 / Leave A safer first path

    The operating boundary before a production build starts.

Performance system

Make the handoff faster without losing the judgment.

Start with one workflow that still needs manual rescue. We make the owner, allowed actions, approval pauses, and proof record visible before a build expands what automation can do.

Outcome Routine work moves. Judgment stays with the operator.

Evidence can be prepared before review while approval, rejection, and consequential action remain with a named person.

Worked example Marketplace template review

The system prepared 49 of 50 selected evidence packets before a human reviewed the templates.

  1. Map the frictionSee the systems, handoffs, and decision owner.
  2. Test one pathLet routine work move while consequential work pauses.
  3. Keep the proofReview what ran, what stopped, and what needs recovery.
Map one workflow See the complete workflow Review field proof