Recovery · UK wellness brand
2,151 profiles recovered and verified.
A discrepancy between Shopify and Klaviyo led to an account-wide suppression event. I recovered eligible profiles and verified their status server-side.
Read the investigationReceived a letter from me?
Open the free two-numbers checkSystems engineering / David Bentley
Your business runs between the tools.
I find where work breaks down, connect systems and build useful business tools, AI workflows and organisational knowledge systems. Start with the work you need. Keep responsibility and ownership clear.
A few sentences is enough. No technical brief required.
From an investigation / 01
The form looked successful.
The submission wasn’t.
- What the visitor saw
- “Sent”
- What the server returned
- Rejected · 403
A sign-up form showed success while its server rejected the request. Checking the handoff exposed what the interface did not.
One named builder: David Bentley
Agreed scope and approval
Your accounts and source code
A documented handover
01 / Selected work
Find the problem.
Build the useful part.
Different tasks, the same discipline: understand the business decision, follow the information and make the work checkable.
Deployed tools · Sofema
Tools for a training decision.
A Course Finder and Training ROI Calculator built for Sofema Aviation Services and deployed on its own site. Two practical tools, separate from the knowledge system still in development.
Explore the training toolsSupervised AI email workflow
Campaigns prepared.
The founder decides.
AI supports the commercial thinking, writes the emails and builds campaigns inside Klaviyo through its API. I direct the working sessions. Every send waits for the founder’s approval.
See the approval boundaryInvestigations, business tools, supervised AI, knowledge-system development and supporting research. The diagrams are explanatory, not client screenshots. Explore Selected Work.
02 / What I build
Connect the systems.
Make the work usable.
Three capabilities, shaped around a specific business need. You do not need to commission all three.
Integrations and business tools
Connect existing systems, investigate failed handoffs and build useful interfaces. Add appropriately scoped checks where the business needs them.
AI workflows and agents
Give AI a defined job, suitable information and bounded actions. Decide who approves consequential work and what happens when an exception needs a person.
Organisational knowledge systems
Make approved information, procedures and decisions usable by people and AI. Link sources, name owners, distinguish current from superseded information and make corrections possible.
03 / Ways to start
Start with the work
actually needed.
A known build can be scoped directly. An unexplained problem may need investigation. Clarifying the objective is part of engineering, not automatically another paid product.
You know what you need
Scope the useful part.
A business tool, an integration, one task for an agent or a recurring question for a knowledge system. Bring the job, the relevant systems or sources, and the person responsible.
Talk through the workSomething does not add up
Investigate the workflow.
When the cause is unknown, inspect the relevant handoffs and authorised evidence. Investigation and implementation have their own agreed scopes.
Find a suitable starting pointShopify and Klaviyo counts
Check the figures.
Compare your own counts with the free tool. Or have me verify the agreed figures from authorised evidence and record the result for £150 fixed. That check is not diagnosis or repair.
Free or verified system checkA question that public evidence can answer? The outside-in analysis remains a separate option. See prices and scope. Already speaking to me on Upwork? Keep our conversation there.
04 / Ownership is part of the design
The work stays
with your business.
- Your accounts and infrastructure.Access is issued by you, limited to the agreed job and revocable.
- A named human at the boundary.Approval points are designed around actions that change business records or reach customers.
- Source code, documentation and handover.An agreed check that another engineer can understand the system and take it forward.
Where customer data is processed by an AI model, my delivery policy is an open-weight model on private infrastructure in a region you choose. Messaging channels and integrations have separate data paths, agreed for the engagement.
Third-party services, hosting, maintenance and support are identified in the scope.
David Bentley
Founder and engineer.
Working directly with you.
One person accountable for delivery.
The person doing the work
Business understanding.
Engineering accountability.
I spent years building marketing funnels before moving deeper into software and AI engineering. I look at how customers move through a business as well as how information moves through its software.
That matters when a technically successful automation can still produce the wrong business result.
A conversation, not a technical brief
Talk through
one workflow.
Tell me what you are trying to improve, what you are still managing by hand, or what is not adding up. A few sentences is enough. No technical brief required.
Talk through one workflow david@higherself.aiNo paid consultation is required for an initial fit-check message. Any paid work is scoped and priced in writing before it starts.