Selected work

Professional work · AI systems · 2025 — 2026

Scout / 500 Acres

A support platform that pairs approved company knowledge with a secure workspace for staff.

Open live project
Role
Software engineering intern
Timeline
2025 — 2026
Stack
Next.js · TypeScript · Postgres + pgvector · OpenAI APIs · Jest · Vercel
Project at a glance
2 Next.js apps · 41 test files · Multi-instance control plane
Scout AI support system interface for 500 AcresView full image

Overview

Scout grew from a set of GPT-based helpers into a multi-instance runtime and control plane for chat, knowledge retrieval, configuration, and operational review.

Policies and operating answers lived across disconnected sources. Staff needed reliable retrieval and a secure way to update knowledge, inspect failures, and change assistant behavior without code deployments.

How it works

Follow the data from input to interface.

  1. Sources

    Staff ingest, review, and publish approved company knowledge.

  2. Retrieval

    PostgreSQL and pgvector retrieve relevant knowledge for each question.

  3. Answer

    The chat runtime uses retrieved context; staff review unresolved questions.

What I built

  • Built the Next.js chat runtime and a separate authenticated dashboard that proxies signed requests to control APIs.

  • Implemented Postgres-backed configuration, pgvector knowledge retrieval, document ingestion, and review and publishing workflows.

  • Added health checks, integration diagnostics, production preflight scripts, Jest coverage, and documented migration and rollback procedures.

Key choices

  • Separated the public runtime from the authenticated control plane so operational access and customer-facing traffic have distinct boundaries.

  • Stored per-instance behavior in Postgres while keeping infrastructure secrets in deployment configuration.

  • Added payload limits, rate limits, SSRF protections, retention controls, and encrypted storage for sensitive connector values.

Outcomes

  • Provides one reusable platform for multiple company instances, each with isolated configuration, knowledge, roles, and integrations.

  • Lets authorized staff test connections, review unresolved questions, manage knowledge, and adjust runtime behavior from the dashboard.

  • Supports production readiness checks through linting, builds, automated tests, health endpoints, and deployment smoke scripts.

Open project