A private multi-product AI platform powering Interview and Finahead, with shared account access and agent execution while keeping product data and workflows isolated.
React
TypeScript
NestJS
PostgreSQL
SQLite
AI Runtime
Area
AI products
Implementation focus
Two product journeys, shared account access and agent execution, product-owned data boundaries.
What you can inspect
Watch two product walkthroughs and read how the products keep their workflows and data separate.
Two products, distinct responsibilities.
The shared platform provides account access and agent execution. Interview and Finahead keep their own user tasks, data and rules.
Interview
Production deployed
Walkthrough uses demo candidate data.
Practice grounded in a candidate’s own material: résumé-based questions, follow-up rounds, saved progress, reports and focused practice.
Interview keeps its own session progress and candidate material while using the shared account and execution boundaries.
25-second walkthrough: résumé-based practice, a follow-up question and actionable feedback.Walkthrough in text
A candidate resumes a backend reliability practice round, answers with server-side ownership checks, then receives a follow-up asking for the exact tests behind that claim.
Finahead
Production deployed
Walkthrough uses synthetic financial data.
A personal finance workspace connecting transactions, forecasts, goals and scenario comparisons. The ledger’s versioned calculations remain separate from optional AI assistance.
The product is integrated with shared account access while retaining its own ledger ownership and command rules. A suggested change still needs the product’s permission and version checks.
29-second walkthrough: financial overview, purchase impact and assistant guidance.Walkthrough in text
The ledger compares an ¥8,000 laptop purchase with cash, investable funds and a travel goal. The assistant also flags a longer-horizon cash shortfall instead of recommending the purchase.
The problem
Shipping more than one AI product requires both a coherent user journey in each product and clear boundaries between shared infrastructure and product-specific data, permissions and behavior.
How the pieces fit
Two product journeys
Shared account access
Interview / Finahead · separate journeys
Product-owned data & sessions
Shared execution · Separate product boundaries
A conceptual map of the public-facing product relationship. The private repository and its internal deployment configuration are not published through this portfolio.
Key engineering decisions
Share access, keep products separate
Interview and Finahead use a shared account entry, but each product retains its own session and data boundary. One login does not imply a shared résumé, ledger or entitlement.
Keep the task in the product
Interview connects résumé-based practice, follow-up rounds and reports. Finahead connects a personal ledger, forecasts and scenario analysis. Agent execution supports those workflows without replacing their domain rules.
Separate deterministic work from model output
Financial calculations remain versioned, deterministic domain operations; optional AI assistance is a separate path. Interview preserves its session state and ties feedback to recorded answers.
Reliability & failure handling
Explicit ownership boundaries
Product services check authenticated ownership rather than accepting a client-selected account or ledger owner. Interview material and Finahead financial records remain product-scoped.
Recoverable workflows
Interview persists progress across interruptions. Finahead checks ledger versions and command identity so a repeated or stale change cannot silently become a new transaction.
Evidence & scope
What this case establishes
Interview and Finahead are two deployed products that share account access and agent execution while retaining their own user journeys and data boundaries.