{{ b.cat }}
{{ project.name }}
{{ project.role }}
{{ project.desc }}
Pain point solved
{{ project.pain }}
Portrait
Cambridge, MA
Studied & worked at
Selected work
Below is a selection of projects I have built
preview
{{ preview.cat }}
{{ preview.name }}
{{ preview.role }}
{{ preview.desc }}
Pain point solved
{{ preview.pain }}
Case study
client_work
Custom AI system
Custom AI Agent
for Client Activation
I built a custom AI system that turns client context and research into proposals, interview guides, workshop materials and synthesis
Agent responsibilities
01
Client context
Puts approved client material in one brief and flags what is missing
02
Proposal
Prepares the story, scope, workplan and draft proposal
03
CXO interviews
Prepares interview guides and pulls the main themes from the notes
04
Facilitation material
Prepares agendas, exercises, participant packs and facilitator notes
05
Synthesis
Turns interviews and workshop outputs into a clear summary and next steps
Core elements
Claude Agent SDK
Runs specialist agents, each with a specific task
Node.js agent layer
Runs the agents and the supporting scripts
Scoped connectors
Connects the approved tools and sources the team uses
Workflow orchestration
Keeps the work connected from client context to synthesis
Reviewable artifacts
Creates drafts the team can review before sharing them
Why it matters[+]
Client work starts with notes, research and past documents in different places. The team needs to reuse that material while keeping the client context clear and reviewing every deliverable before sharing it
What I developed[+]
I built a system of specialist agents that share approved client context and templates. It prepares proposals, interview guides, workshop agendas, facilitation decks and follow-up documents
What it can produce[+]
It prepares drafts of research briefs, proposals, contracts, interview guides, workshop agendas, facilitation decks and synthesis documents
How it works[+]
Each agent has a specific task and uses approved sources and templates. People review the output before anything goes to a client
What it shows[+]
I use agents to handle parts of a real delivery process, while people keep control over the work that goes to clients
My team of AI Agents
Each agent holds its own brief and its own context
Aldrich
learning
Dora
research
Godin
positioning
Rawlings
knowledge
Gigi
chief of staff · dispatch
Stark
product & code
Crayon
design & UX
Cresus
finance & risk
Saimon
purchasing
Camus
writing
{{ agName }}
{{ agRole }}
{{ agDesc }}
Powered by Hermes Agentby Nous Research
agent
“I use my team of AI Agents to keep track of work, stay organised across the different parts of my life, manage investments and maintain my knowledge corpus.”
Background
Professional experience
Strategy Consulting
Africa · 2021—2025
McKinsey & Company
Engagement Manager — Led strategy, digital and operating-model work for governments and companies across Africa, including internet penetration, retail strategy and commercial due diligence
Private Equity
Paris · 2020
Amethis
Private Equity Analyst Intern — Assessed African investment opportunities through market research, financial analysis and due diligence
Investment Banking
Paris · 2018—2019
BNP Paribas CIB
M&A Analyst Intern — Built valuation analyses and pitch materials for industrial-sector M&A transactions
AI Building & Deployment
Boston · 2026
Keystone
AI Builder / Deployer · MBA Internship — Built agentic workflows able to produce client-facing documents with human approval gates
Education
Harvard Business School
2025—2027
MBA Candidate
ESSEC Business School
2017—2020
Master of Science in Management
ESTP
2014—2017
Electrical & Mechanical Engineering
Languages spoken
French, English
Served clients across the world
- Ivory Coast
- France
- Ghana
- Kenya
- Morocco
- Nigeria
- South Africa
- Togo
- United States
“Before becoming an AI builder, I developed my business acumen through roles in strategy consulting, investment banking and private equity.”
AI credentials
Here is a non-exhaustive selection of the training I have completed
agentic
Agentic development
Curriculum focus
How AI agents reason, use tools and work across frameworks such as LangChain, LlamaIndex and smolagents
Certificate Provider
Hugging Face
AI fluency
Applied AI fluency
Curriculum focus
How to identify where AI adds value in a task or process, use effective prompting to get the most from it, and assess its outputs with care
Certificate Provider
Anthropic
AI fluency
AI for small businesses
Curriculum focus
How to identify where a business can leverage AI, define the right use cases and adopt it responsibly while retaining human judgment
Certificate Provider
Anthropic
APPLICATIONS
Building AI applications
Curriculum focus
How to build Claude-powered applications with prompting, tool use, RAG, agents, MCP and production patterns
Certificate Provider
Anthropic
coding
Coding with agents
Curriculum focus
How to steer, configure, automate and verify long-running Claude Code sessions
Certificate Provider
Anthropic
PROMPT ENGINEERING
Prompting LLM
Curriculum focus
How prompt patterns unlock the capabilities of large language models in practical applications
Certificate Provider
Vanderbilt University via Coursera
Community contribution
JURY MEMBER - HARVARD CLAUDE CODE COMPETITION
I had the privilege of serving as one of four jury members for the Harvard Claude Code Competition
Harvard Claude Code Competition
#2 WINNING TEAM - HARVARD × MIT HACKATHON
On October 24, 2026, my team placed second at the Harvard × MIT hackathon, sponsored by Replit
Harvard × MIT × Replit
My AI stack
Here is a non-exhaustive selection of tools that I use
“My first rule when building with AI is not to be loyal to any provider. Each has its own strengths, so I built a system that lets me move between them.”
Essays
Read on SubstackAI Tool
Token economics
Reflection