Case Studies.

We build and operate our own products with an AI agent fleet. Agents write the code, open pull requests, and run QA; a human sets direction and approves sensitive changes.

PR counts measured from our repositories on 24 Oct 2026.

Consumer AI / MCP platformJul 2026 – present

Dayze

A personal context layer for AI: a source-linked life graph that ChatGPT, Claude, Cursor, and Gemini can answer from over MCP. Built and operated end to end by our US sister company, Phi Digital LLC, with an AI agent fleet.

Assistants like ChatGPT and Claude forget who you are between conversations. The ask was ambiguous: make AI genuinely know a person's life without turning that into a privacy liability. That meant deciding what to store, how to prove where each fact came from, and how to let third-party AI clients read it safely.

OpenAIAnthropic ClaudeGoogle GeminiMCPOAuth 2.1
Read case study
EdTechAug 2026 – present

CFA Mock Exam

A CFA exam practice platform with computer-based-test style mocks, drills, and an on-screen BA II Plus calculator. Operated by the Phi team, with AI agents running content audits, security fixes, and QA.

An exam-prep product lives or dies on trust: every answer key must be right, paid content must stay paid, and scores must be real. With a large, partly generated question bank and a small team, the problem was how to keep content quality and security high while still shipping quickly.

ReactFirebase Auth / FirestoreNetlify FunctionsStripeKaTeX
Read case study
Crypto Trading PlatformSep 2026 – present

Coincess

A crypto trading interface with wallet connection and Hyperliquid DEX connectivity.

Build a fast, trustworthy trading UI on top of a decentralised exchange, where users sign orders from their own wallets and market data must stay live.

Next.jsTypeScriptHyperliquid SDKWalletConnectWebSocket
Read case study