Available for projects
๐Ÿ“ Nairobi, Kenya

Milena
Tanui AI Engineer ยท AI Agent Builder ยท LLM Evaluator ยท Automation Architect

I build intelligent AI agents and workflow automations โ€” from Python-powered multi-agent systems with CrewAI, to API-integrated pipelines in n8n, to prompt-engineered tools that ship fast and think on their own. I also evaluate LLM outputs and agent tool calls for quality, correctness, and reliability โ€” rating tool-calling responses, validating JSON schemas, and applying structured scoring frameworks on real annotation datasets.

3
AI Certifications
3+
Years in AI Ops
5+
Automation Tools
4
Live Projects
About

Python. Pipelines. Prompts.
Built with intention.

I'm Milena โ€” an AI Engineer, AI Agent Builder, and Automation Architect who builds across the full automation stack. I write Python to orchestrate multi-agent systems with CrewAI, integrate APIs and design pipelines in n8n, and apply prompt engineering to build tools that ship fast and think on their own.

My background includes leading a team of AI trainers at Scale AI as one of the project team leads โ€” one of the world's leading AI companies โ€” giving me a rare combination of hands-on building skills and a deep understanding of how AI systems learn and perform in the real world.

Based in Nairobi, Kenya, I have a particular focus on the African AI ecosystem โ€” tracking how AI is reshaping industries across the continent and building tools that put that intelligence directly in the hands of African builders and decision-makers.

I believe prompt engineering is a superpower. You don't need to write every line of code to build something powerful โ€” you need to know what to build and how to make it think.

๐ŸŽ“
AI for Everyone
DeepLearning.AI / Coursera
๐Ÿ› ๏ธ
Agentic AI Training Workshop
Attended ยท Kanz ยท Mar 2026
๐ŸŽ“
Elements of AI for Business
MinnaLearn / Reaktor
๐Ÿค– AI Agent Building
CrewAI Claude Python Prompt Engineering SerperDev SendGrid Replit Lovable
โšก Workflow Automation
Make Zapier n8n API Integration
๐Ÿ“‹ AI Data Annotation & Evaluation
LLM Output Evaluation Tool-Call QA JSON Schema Validation RLHF-Adjacent Scoring Multi-Dimensional Rating
Projects

What I've built.

No-Code ยท Automation

Team Issue Tracker

An end-to-end issue reporting automation built on Zapier. When a team member encounters a problem, a form submission triggers an automated chain โ€” logging to Google Sheets, sending a confirmation email to the reporter, and firing a Slack alert to the responsible stakeholder for immediate action.

Zapier Google Sheets Slack Email Automation No-Code
View on GitHub โ†’
Demo Video
Workflow Screenshots
Zapier Formatter Step
01 — Formatter
Text transform step setup
Zapier Full Workflow
02 — Full Flow
Google Forms โ†’ Sheets โ†’ Gmail โ†’ Slack
Zapier Dashboard
03 — Dashboard
Live published Zaps overview
Automation Workflow
01 Team member submits issue via Google Form
โ†“
02 Zapier trigger fires โ€” issue logged to Google Sheets automatically
โ†“
03 Confirmation email sent to the reporter
โ†“
โœ“ Slack alert fired to the responsible stakeholder for immediate action
Python ยท AI Agent

AI News Across Africa

A 4-agent CrewAI pipeline that autonomously researches the latest AI developments across Africa โ€” startups, funding, policy, tools, and events โ€” filters results for relevance, generates a structured weekly briefing, and delivers it as a formatted HTML email via SendGrid.

CrewAI Python SerperDev SendGrid Multi-Agent Africa Tech
View on GitHub โ†’
Screenshots
Agents Config
Image loading...
01 — Agents
agents.yaml โ€” roles, goals & backstories
Crew Running
Image loading...
02 — Execution
crewai run โ€” agents firing sequentially
Report Output
Image loading...
03 — Output
report.md โ€” categorized AI briefing
Agent Workflow
01 Researcher โ€” searches the web for the latest AI news across Africa using SerperDev
โ†“
02 Africa AI Filter โ€” curates results to keep only AI-relevant developments from African countries
โ†“
03 Reporting Analyst โ€” structures findings into a categorized briefing: startups, funding, policy, tools & events
โ†“
โœ“ Email Sender โ€” formats the report as HTML and delivers it to the recipient's inbox via SendGrid
How I Build

From idea to
working agent.

01

Define the Problem

I map out the workflow, identify what needs to think and what needs to automate, and design the architecture โ€” whether that's a multi-agent pipeline, an API integration, or a no-code automation chain.

Tools: Claude ยท Prompt Engineering ยท Python
02

Build the Intelligence

I write Python or configure agents in CrewAI for complex reasoning tasks, or build visual pipelines in n8n, Make, or Zapier for workflow automation โ€” picking the right tool for the job.

Tools: CrewAI ยท Python ยท n8n ยท Make ยท Zapier
03

Integrate & Connect

I wire up APIs, external services, and data sources to make the system functional end-to-end โ€” connecting search, email, databases, messaging, and AI models as required.

Tools: SerperDev ยท SendGrid ยท Claude API ยท Google Sheets ยท Slack ยท Gmail
04

Test, Deploy & Refine

I run the full pipeline end-to-end, validate outputs, and deploy. Interfaces are built with Replit or Lovable when needed, and every system is refined until it runs reliably without intervention.

Tools: Replit ยท Lovable ยท API Testing ยท Git

Let's build something
intelligent together.

Open to freelance projects, collaborations, and conversations about AI agents and automation. If your team has a workflow that should be smarter โ€” let's talk.