AI and LLM apps

FeedbackIQ

AI-powered multi-tenant SaaS API that ingests feedback and classifies sentiment, themes and urgency with an LLM in background jobs.

Source

My role: Designer and sole developer
Stack: Laravel 11, PHP, MySQL, Redis, Gemini API, Docker, Pest

The problem

Classifying feedback with an LLM is slow; doing it inside the request would make ingestion endpoints slow and fragile.

The solution

Multi-tenant REST APIs with Sanctum authentication accept feedback and return HTTP 202 immediately, while queued Redis workers run asynchronous LLM sentiment classification.

Key features

Multi-tenant REST APIs with Laravel Sanctum authentication
Asynchronous LLM classification of sentiment, themes and urgency
Redis queue workers keep the ingest endpoint fast (HTTP 202)
Pest test coverage and OpenAPI documentation
Dockerized environment with CI

Related projects

Resolve AIEvaluation-driven AI customer operations agent using tool calling, hybrid RAG, policy guardrails and human-in-the-loop workflows.
Federal Forecasting AppREST APIs supporting government contracting forecasts, document discovery, downloads and mobile/web data access.

Next projectQA Management Platform