AI Deploy Network
DC

AI Deploy Network / Builder

Duran Classen

I direct AI to build and test working systems for small businesses

South AfricaCape TownFounderAvailable Now

Published evidence

2 AI Deployments

2 publicly identified

2 Case Studies

Published implementation narratives

01

About Duran

I build working systems by directing AI tools, then I test them against real numbers before I call them done. Live work includes a booking system for a Cape Town automotive workshop that now gets found on Google, a free quiz app with privacy-safe tracking, and a public prompt-injection gate for AI agents. I run my own scheduled automations for reporting, monitoring and job triage. Based in Cape Town, working remotely.

Professional profile

Location
Cape Town, South Africa
Time zone
Africa/Johannesburg
Work mode
Remote
Availability
Available Now

02

Proven on the network

Implementation records and publicly available work, where published.

2 AI Deployments delivered, including 2 publicly identified implementations available to inspect.

03

What Duran builds

Implementation domains listed on this profile. Evidence-supported items are identified separately below.

Specialisations

Agentic Workflow Automation

AI Evaluation & Testing

AI Security & Safety

Intelligent Automation

Prompt & Context Engineering

Builder-listed deployment types

  • AI Agent
  • AI Evaluation Framework
  • Workflow Automation

04

AI Deployments

Real AI implementations demonstrated through evidence.

01 / AI DeploymentPublished record

Inbox Guard: a gate that stops AI agents acting on instructions hidden in emails

An open-source provenance gate for tool-calling AI agents. It checks in code where every value in a proposed action came from, and holds or blocks actions driven by text the agent merely read. Public on GitHub since 6 October 2026.

Cybersecurity · AI Agent · AI Evaluation Framework

View Deployment
02 / AI DeploymentPublished record

Online booking and lead system for an automotive workshop

A booking wizard, staff dashboard and instant WhatsApp alerts for an automotive service workshop in Cape Town, plus fault-based service pages that get the workshop found in Google and AI search. Live since 24 August 2026.

Automotive · Workflow Automation

View Deployment

05

Implementation capabilities

Evidence-supported means linked to a published Deployment or Case Study; other capabilities are Builder declared.

Evidence-supported

  • AI Agent2 records
  • AI Evaluation Framework2 records
  • Workflow Automation2 records

Builder declared

  • Agentic Workflow Automation
  • AI Evaluation & Testing
  • AI Security & Safety
  • Intelligent Automation
  • Prompt & Context Engineering

06

Industry experience

Published Deployments support the listed counts. Other industries are Builder declared.

Automotive

1 published Deployment

Cybersecurity

1 published Deployment

E-Commerce

Builder declared

Marketing & Advertising

Builder declared

Professional Services

Builder declared

07

Case Studies

Published narratives of implementation and results.

Automotive · Workflow Automation

Online booking and lead system for an automotive workshop

Online booking, a staff dashboard and instant WhatsApp alerts for a busy Cape Town steering and suspension workshop. Live since 24 August 2026 and found on Google at an average position of 5.1.

Read case study

Cybersecurity · AI Agent · AI Evaluation Framework

Inbox Guard: a gate that stops AI agents acting on instructions hidden in emails

A provenance gate between an AI email agent and its tools, so an email cannot make the agent forward, send or pay. The first version lost to an adaptive attacker in round 2; after the fix, 0 of 20 rounds.

Read case study

08

Trust & verification

A closer look at how this profile and its evidence are reviewed.

Community Member

AI Case Studies verified

Published evidence is reviewed against the AI Deploy Network Evidence Standard.

How verification works
Community

Verified Builder

Independently reviewed by AI Deploy Labs against the platform Evidence Standard.

  • AI Case Studies Verified
How this is verifiedWhat the platform has established, and what remains builder-declared.
Identity and organisation
Identity checks confirm that the person presenting this profile controls the account and the professional identifiers attached to it, such as a LinkedIn profile. Organisation membership is confirmed by the organisation, not self-declared by the builder.
AI Deployments
An approved AI Deployment is an implementation record the builder submitted and the platform reviewed against the Evidence Standard before publication. Approval confirms the record is complete, coherent and consistent with the supporting material provided — it is not an audit of the client's systems.
Business outcomes
Outcome figures are recorded by the builder on the deployment or case study that produced them, and are reviewed at publication. Aggregates shown on this profile are calculated from those approved records only.
Evidence
Supporting evidence comes from the records the builder published on this platform: approved AI Deployments, published AI Case Studies, verification outcomes and organisation participation.
Currency
Older evidence continues to count and is never removed. Recency is presented separately through Professional Currency so that current expertise can be assessed alongside historical work.
Traceability
Every figure on this profile can be followed to the record that produced it. Open the linked AI Deployment or AI Case Study to read the outcome exactly as it was reported.

The platform does not independently audit client systems or financial records. How this is verified

Ready to discuss your AI implementation?

Tell Duran Classen what you are trying to automate and the outcome you need. Your message goes directly to the builder, with a copy kept in your Organisation Workspace.