I build AI agents that operations teams can leave running, then check what they did.

About

About me

Master in Management student at INSEAD and Physics graduate from Bath, building AI agent systems and the checks around them.

Selected project

Life Tracker agent system

A manager and a supervisor for headless Claude Code agents, so runs left alone overnight either finish properly or stop in a way I can see and resume.

• Python
• Claude Code
• Swift

Project

Objective Mind

A founder-accountability web app for small pods of founders, taken from HTML prototypes to a hosted product with sign-in, sync and AI briefings.

• Next.js 16
• React 19
• TypeScript

Project

Tearline

A company name or number goes in, and a tear sheet, capital structure, Excel model and references come out, with every figure tied to the document and page it came from.

• TypeScript
• Next.js
• React 19

Part of Life Tracker agent system

Polaris

A desktop dashboard that turns what my AI agents need from me into cards I can act on, such as questions to answer, commands to copy and run, and revision drills, served by a server only my own Mac can reach.

• Python
• JavaScript
• WebGL2

Part of Life Tracker agent system

Dreaming

A nightly job that asks a small AI model whether pairs of the day's notes are related, duplicated or in conflict, and leaves a short report by morning. The model has no tools and a hard cap, and any answer that does not quote the notes exactly is thrown away.

• Python
• Claude Code
• Claude Haiku

Part of Life Tracker agent system

knowledge bank and /initiate

A cited knowledge bank that every unattended agent draws on, and a handover routine that lets a cleared Claude Code session pick up where the last one stopped, from written state rather than memory.

• Python
• SQLite FTS5
• Claude Code hooks

Part of Life Tracker agent system

Steward, the managed agent runner

The runner behind every unattended Claude Code job. It winds a run down before the usage limit, resumes the same conversation after the reset, rotates a run whose context is too long into a fresh session, and feeds it all from a timed work queue.

• Python
• Bash
• launchd

Part of Life Tracker agent system

/build skill

Type one request and get a staged pipeline of unattended agent runs (discovery, research with adversarial review, a plan with acceptance tests, build, ship, final review), where each step opens only when a supervisor has checked the last one's work.

• Python
• Claude Code
• launchd

Part of Life Tracker agent system

Life Tracker voice layer

Voice notes from an iCloud drop folder, a call recorder that transcribes on the Mac, and Wispr Flow added as a voice layer, all feeding one system that says what it did with each note and where each transcript came from.

• Python
• Swift
• Core Audio

Part of Life Tracker agent system

LT Capture for iOS

A SwiftUI app that records a voice note, hands it to the life tracker through iCloud Drive in a fixed file protocol, and shows each note's real status read back from the Mac's receipt.

• Swift
• SwiftUI
• AVFoundation

Part of Life Tracker agent system

humaniser and writing-style system

A scorer, a written house guide and a review pass that every agent report goes through, measured against my own writing, with a compare step that fails any rewrite that loses a number, name or citation.

• Python
• Claude Code
• Markdown

Part of Life Tracker agent system

revision engine

A question-by-question practice engine that follows up until understanding breaks, keeps a weak-spot queue, and saves each answer to a sourced tracker before marking the next, in a chat session or on my dashboard.

• Python
• Claude Code
• Claude Sonnet