Benjamin Nwandu.Let’s talk
All projects

Developer tooling

In Development

Voice AI Workflow Builder

From a natural-language requirement to a validated, platform-neutral automation workflow.

Live demo

Compile a requirement now.

This runs the real compiler in your browser — no model, no backend, no key. Describe an agent and it emits an importable n8n workflow, or refuses and tells you why.

Try

The compiler reads your requirement against a fixed capability vocabulary. No model runs — so it cannot invent a capability, and it will refuse anything it does not recognise.

01 / THE PROBLEM

Why this matters.

Turning a conversational use case into an automation requires translating business intent into precise steps, integrations, and safeguards.

02 / THE DIRECTION

The proposed solution.

A capability-first compiler architecture: describe the use case, validate a typed specification, then compile through a platform adapter. n8n is the first intended output target; future adapters are architectural possibilities.

My role.

Designing and developing the workflow builder. Individual features remain subject to implementation and verification.

03 / ARCHITECTURE

How the pieces connect.

Conceptual flow — proposed architecture

  1. 01Natural-language requirement
  2. 02UseCaseSpec
  3. 03WorkflowSpec
  4. 04Platform adapter
  5. 05n8n workflow

04 / ENGINEERING DECISIONS

Designed with intent.

  • Separate business intent from platform-specific configuration.
  • Treat appointment scheduling, lead qualification, and customer support as composable capabilities.
  • Use deterministic validation and human approval before consequential execution.

05 / EVALUATION APPROACH

What needs to hold true.

  • Validate required fields and unsupported capabilities.
  • Test compilation against representative scheduling, qualification, and support cases.
  • Reject invalid specifications rather than generate misleading workflows.

Technology direction.

n8n · plannedTyped specifications · plannedAPIs · planned

Let’s build something useful

Good conversations.
Better systems.

Have a conversational AI challenge, an automation idea, or a role in mind?