Blog

Articles on AI workflows, MCP patterns, and what we have learned building Synapse.

April 24, 2026•

AILLMsTransformersAI EngineeringArchitecture

The Complete Journey of a Prompt: How LLMs Actually Process Your Input End-to-End

Most explanations cover one piece at a time. Here's the full data flow — from your prompt to the next generated token — traced through every component in order.

Read article

The Complete Journey of a Prompt: How LLMs Actually Process Your Input End-to-End

April 23, 2026•

AILLMs

What Is KV Cache and Why Does It Make LLM Inference Fast?

Every token an LLM generates reuses Keys and Values from everything that came before. The KV cache is what makes that reuse cheap. Here's how it works — and why inference slows down with longer context.

April 23, 2026•

AILLMs

Why Transformers Can't Tell Position Apart — and How RoPE Fixes It

Self-attention is blind to order. Shuffle the words in a sentence and you get identical attention scores. Positional embeddings solve this — but the way they do it determines whether your model can handle long contexts at inference time.

April 23, 2026•

AILLMs

What Actually Happens Inside a Transformer Block

Attention gets all the press. But a transformer block is more than attention — there's a feedforward network that holds most of the parameters, two residual connections, and a normalisation design that determines whether large-scale training is stable. Here's all of it, in order.

April 21, 2026•

AILLMs

Why Your LLM Can't Think Ahead: The Token-by-Token Reality of Text Generation

Most developers treat LLMs as black boxes that write answers. The reality is stranger and more mechanical — and understanding it changes how you build.

April 21, 2026•

AILLMs

Why One Attention Head Is Never Enough: Multi-Head Attention Explained

A single attention pass can only ask one question at a time. Multi-head attention runs several in parallel — each head specialising in a different type of relationship. Here's what that means in practice.

April 21, 2026•

AILLMs

The Mechanism That Makes LLMs Actually Understand Language: Self-Attention Explained

Static embeddings can't tell 'bank' the financial institution from 'bank' the riverbank. Self-attention is how language models fix that — by rewriting each token's meaning based on what surrounds it.

April 20, 2026•

AI AgentsAgent Harness

Your AI Agent Has a Brain. Does It Have Hands?

Most agent failures aren't model failures — they're harness failures. Here's what an agent harness is, why it matters, and how to stop over-engineering it.

April 19, 2026•

AILLMs

The Wall Between You and the Model: Tokens, Encoders, and Embeddings

GPT-4 can't count letters. Here's why — and how embeddings give token IDs the meaning the tokenizer strips away.

February 20, 2026•

AI AgentsMCP

WebMCP: Websites can now talk directly to AI agents

AI agents are terrible at browsing websites. WebMCP lets sites declare what an agent can do on a page — turning messy scraping into precise tool calls.

The missing piece for AI coding agents: Vercel's agent-browser

February 8, 2026•

AI AgentsBrowser Automation

The missing piece for AI coding agents: Vercel's agent-browser

AI agents can write code and run tests, but they can't see the website. Vercel's agent-browser finally closes the feedback loop.

January 19, 2026•

VercelAgent Browser

Testing AI Agents with Vercel's Agent Browser

A practical guide to using Vercel's new Agent Browser for AI-native web automation.

December 21, 2025•

ChatGPTApps

Developers can now submit apps to ChatGPT

OpenAI is opening app submissions for review and publication in ChatGPT, creating a new ecosystem for developers.

A better way of tool calling for AI agents

December 1, 2025•

AIMCP

A better way of tool calling for AI agents

Why asking an AI to write a program is better than asking it to press buttons—and how the Model Context Protocol makes it viable.

Stay in the loop

Synapse is your AI systems mentor.

It asks the kind of questions senior engineers do, sketches diagrams with you, and forces you to defend every architectural choice so your ideas are ready for interviews or production reviews.

Start a Synapse session Join the Discord