Full Stack ML

#15 - Where Does the Time Go? Measuring Voice-to-Voice Latency with Pipecat, Modal and Twilio

We recently hit a one-second latency milestone with our inbound call application - but what’s actually happening under the hood during that second?

Feb 21 • JO Reyes

#14 - When the AI Calls You: Building an Outbound Voice Bot with Pipecat, Twilio, Deepgram and Modal

Building a full-featured outbound Voice AI application (using a Filipino English accent) with a $0 budget

Feb 13 • JO Reyes

1

#13 - Voice AI Over the Phone: A Practical Guide with Pipecat, Twilio, Deepgram and Modal

Building a full-featured inbound Voice AI application with a $0 budget

Feb 8 • JO Reyes

2

January 2026

#12 - A Developer’s Guide to Failure Analysis and Evaluation for Single-turn and Multi-turn Chatbots - Part 2

Stop Guessing and Start Auditing: How qualitative analysis turns "vibe checks" into engineering.

Jan 11 • JO Reyes

December 2025

#11 - A Developer’s Guide to Failure Analysis and Evaluation for Single-turn and Multi-turn Chatbots - Part 1

In this article, we’ll look at how failures emerge in LLM chatbot conversations, why they’re hard to detect, how to systematically analyse them using…

Dec 21, 2025 • JO Reyes

1

June 2025

#10 - Evals for AI: Why Your Application Needs More Than a Vibe

Go beyond vibe checks to ensure your applications work the way you intended

Jun 14, 2025 • JO Reyes

April 2025

#9 - Putting Our Bird Embedding Model to Work: Introducing the Web Frontend

To make our embedding model accessible and useful to a wider audience, we developed a modern front-end interface for similarity inference.

Apr 5, 2025 • JO Reyes

1

March 2025

#8 - From Training to Deployment: A Simple Approach to Serving Embedding Models

Now that our MLOps pipeline has trained and built our embedding model, it is now time to serve the model in a Docker container using FastAPI

Mar 22, 2025 • JO Reyes

February 2025

#7 - Streamline Your AI Workflow: A Factory Class for LLMs and Embedding Models

LLMFactory and EmbeddingModelFactory classes that will improve the developer experience of an AI Engineer

Feb 23, 2025 • JO Reyes

December 2024

#6 - Modelling with Metaflow and MLFlow

After building a model in a Jupyter Notebook, we port our code to be production-ready and we use Metaflow for orchestration and MLFlow for experiment…

Dec 2, 2024 • JO Reyes

2

October 2024

#5 - Let's build our image embedding model

Building an embedding model is not hard, and in this article we'll have a look at a couple of options

Oct 6, 2024 • JO Reyes

September 2024

#4 - So how do you build a vector embedding model?

This project explores a popular way to build a vector embedding model using your own custom dataset

Sep 29, 2024 • JO Reyes