Richard Thompson (@richardmthompson)

What 2 Years of Self-taught AI Engineering actually looks like

I have the logs, the version numbers, the line counts, the dead ends and the breakthroughs. This is what 2 years of self-taught AI engineering actually looks like. A year ago I published an article about a "One Year Syllabus For Learning Software an...

Nov 14, 2025 · 12 min readrichardmthompson.hashnode.dev

CORE-LOOP: Managing Complex Two-Way Voice Conversation via Agent / LLM

In building voice-enabled AI assistants, one of the most challenging aspects is how to manage the conversation lifecycle. I created Coherence to help users manifest their wishes through structured reflection practices. The app centers around a voice-...

Apr 22, 2025 · 19 min readrichardmthompson.hashnode.dev

Implementing AI-Assisted Concept Building in an Android Voice Interface

The Challenge I needed to create a system where users could verbally describe concepts related to their goals (or "wishes"), with an AI “brain” driving the conversation flow. My first version of the “Manifestation App” was a simple reflex agent. It r...

Mar 25, 2025 · 9 min readrichardmthompson.hashnode.dev

Designing a Flexible Cognitive Architecture for Human-Computer Interaction

In developing the Vox Manifestor app, I faced a fundamental challenge: how could I create an effective system for representing information exchanged between an AI assistant and a human user? As a cognitive scientist, I knew that the next generation o...

Dec 12, 2024 · 11 min readrichardmthompson.hashnode.dev

STATE-MACHINES: How to Begin Building an Agent from Scratch on Android

Conversational AI: The DNA of the next generation of operating system. The complexities of conversational agents varies according to how complex the task is. Ultimately, we will all be interacting with agents (operating systems) on our computers that...

Nov 27, 2024 · 16 min readrichardmthompson.hashnode.dev

Richard Thompson

About

Available for

Richard Thompson's blogs

What 2 Years of Self-taught AI Engineering actually looks like

CORE-LOOP: Managing Complex Two-Way Voice Conversation via Agent / LLM

Implementing AI-Assisted Concept Building in an Android Voice Interface

Designing a Flexible Cognitive Architecture for Human-Computer Interaction

STATE-MACHINES: How to Begin Building an Agent from Scratch on Android

Richard Thompson

About

Available for

Richard Thompson's blogs

What 2 Years of Self-taught AI Engineering actually looks like

CORE-LOOP: Managing Complex Two-Way Voice Conversation via Agent / LLM

Implementing AI-Assisted Concept Building in an Android Voice Interface

Designing a Flexible Cognitive Architecture for Human-Computer Interaction

STATE-MACHINES: How to Begin Building an Agent from Scratch on Android

Richard Thompson

About

Available for

Richard Thompson's blogs

What 2 Years of Self-taught AI Engineering actually looks like

CORE-LOOP: Managing Complex Two-Way Voice Conversation via Agent / LLM

Implementing AI-Assisted Concept Building in an Android Voice Interface

Designing a Flexible Cognitive Architecture for Human-Computer Interaction

STATE-MACHINES: How to Begin Building an Agent from Scratch on Android

Search Hashnode

Richard Thompson

About

Available for

Richard Thompson's blogs

What 2 Years of Self-taught AI Engineering actually looks like

CORE-LOOP: Managing Complex Two-Way Voice Conversation via Agent / LLM

Implementing AI-Assisted Concept Building in an Android Voice Interface

Designing a Flexible Cognitive Architecture for Human-Computer Interaction

STATE-MACHINES: How to Begin Building an Agent from Scratch on Android