How we turned a fragile single‑machine RAG into a session‑aware, PostgreSQL‑backed chatbot running on Cloud Run with Vertex AI doing the heavy lifting.
Transforming a local Python automation into a scalable, serverless cloud application using Google Scheduler, Google Cloud Run and Telegram for on-demand execution.
By decoupling transcription from translation and implementing robust error handling, we can build specialized AI pipelines that outperform generic multimodal models in both accuracy and debuggability.
Building this bot has been a journey of trial and error, but seeing how these agents work together makes me excited for what’s next. This enhanced agent framework is our way of making the bot safer, smarter, and more user-friendly.
Discover how I built a personalized weekly AI digest using LLMs and an agentic workflow to cut through the noise and deliver the latest AI breakthroughs.
