AI Engineering × AutomationPortfolio — Selected work

I’m Manyeya, an AI engineer. I build agents and automation that do real work — and interfaces that make them feel effortlessly human.

Explore selected work
Portrait of Manyeya Khutso Siema
Fig. 01 — The person behind the pixels
Designed to be used. Engineered to keep running.Scroll to discover South Africa · UTC+02
01 / Selected work

Ideas made real.(07)

Agents, music software, and developer tools
built to survive real use.

More experiments on GitHub
02 / The way I think

Powerful behind
the scenes.
Human at the surface.

Manyeya Khutso Siema
AI engineer. Designer’s eye.

Most AI products fail in the same place — not the model, but the seam between the model and the work. I build the part that closes it: agents and automation that hold up once real people depend on them.

Design and full-stack engineering came first, and that turned out to be the useful preparation. The hard part was never the inference call; it was everything around it. Based in South Africa. Building for people everywhere.

01

AI Engineering

Autonomous agents, LLM workflows and retrieval systems that hold up in production. Tool design, evals and the unglamorous plumbing that decides whether a model is useful or a demo.

LLMsAgentsRAGEvals
02

AI Automation

Work that runs itself. Connecting the tools a team already uses into orchestrated pipelines, with humans kept in the loop exactly where judgement is worth more than throughput.

OrchestrationWorkflowsIntegrationsQueues
03

Design & Software Engineering

The background underneath all of it: years of full-stack architecture and interface design. It is the reason the AI work ships as a product people can use, not a notebook.

TypeScriptNext.jsDesign SystemsFigma
03 / From idea to impact

A little curiosity.
A lot of care.

Good work is a conversation.
Here’s how I move it forward.

01

Map

Find the work worth automating. Which steps are repetitive, which need judgement, and where a model earns its keep instead of adding a new failure mode.

02

Prototype

A narrow end-to-end slice, fast. Real data, real prompts, real interface — enough to see whether the idea survives contact with how people actually work.

03

Build

Type-safe systems around the model: tool boundaries, retries, guardrails and an interface that makes the AI legible rather than mysterious.

04

Operate

Evals, tracing and cost monitoring after launch. Model behaviour drifts; the system that watches for it is part of the product, not an afterthought.

Have work that should run itself?Let’s make it happen.

Let’s build
something good.

Thoughtful projects start with a conversation.