AI AgentSaaS

Enterprise AI Agent Platform

A multi-tenant platform that combines custom agents, tools, and knowledge bases to build and operate AI assistants specialized for each company's operations.

Challenge

A multi-model AI agent platform was needed to leverage corporate knowledge and automate business operations. The design had to meet security, multi-tenancy, and scalability requirements while enabling no-code agent building.

Solution

Built a clean architecture-based backend and secure infrastructure on GCP. Integrated PydanticAI for agent execution, LlamaIndex + pgvector for RAG pipeline, and RestrictedPython for code sandboxing.

Result

Built a full-stack platform with 150+ frontend, 80+ backend, and 50+ infrastructure files.

Team

2 members, 4 months

Design, implementation, infrastructure, operations

Role

Responsible for everything from design to implementation, infrastructure, and operations.

Led frontend (Next.js), backend (FastAPI), and infrastructure (Terraform/GCP) end-to-end.

Tech Stack

FrontendNext.js / TypeScript / shadcn/ui / Framer Motion
BackendPython / FastAPI / SQLAlchemy
LLMPydanticAI / OpenAI / Anthropic / Google Gemini (LiteLLM)
RAGLlamaIndex / pgvector
DatabaseGCP / Cloud SQL
AuthBetter Auth / Google & Microsoft OAuth
InfrastructureGCP (Cloud Run, VPC, Secret Manager) / Terraform
CI/CDGitHub Actions / Workload Identity Federation

Key Features

01

Real-time AI chat via SSE: 6 types of streaming events displaying thought processes and tool execution status live

02

Multi-model support: Switch between OpenAI / Anthropic / Gemini through a unified interface

03

No-code agent builder: Freely configure system prompts, tools, and models

04

RAG knowledge base: Vectorize documents and improve AI response accuracy with semantic search

05

Code sandbox with RestrictedPython: Secure user code execution environment

06

Multi-tenancy: Structurally prevent cross-tenant access with workspace_id filtering across all tables

Technical Highlights

Clean Architecture

Unified dependency direction from domain → application → infrastructure → api, enabling LLM provider switching with only infrastructure layer changes.

Enterprise Security

Restricted backend to internal traffic only, implemented dual authentication with OIDC + user tokens, DB isolation via VPC, and secret management via Secret Manager.

Cost Optimization

Reduced development environment costs to 2-5% of production through Cloud Run scale-to-zero and environment-specific resource isolation. All infrastructure managed as code with Terraform.