InLevel Up CodingbyJoshua Phillips·Jun 26The Palimpsest LibraryHow we rebuilt our documentation architecture around two first-class audiences: humans and the agents that work alongside them.
InLevel Up CodingbyJoshua Phillips·Jun 15Two Communities Are Building on MCP. They Think It Is Two Different Things.Two Communities Are Building on MCP. They Think It Is Two Different Things.
InLevel Up CodingbyJoshua Phillips·Jun 5MCP Is the Connective Tissue Your Agent Stack Is MissingA protocol-level explanation of why Model Context Protocol matters more than its mention volume suggests.
InGenerative AIbyJoshua Phillips·May 28Observability for AI Pipelines: What to Trace and WhyMost teams treat AI observability as a retrofit. It’s a design constraint.
InLevel Up CodingbyJoshua Phillips·May 20The AI Layer Is Not Your FrameworkWhy the runtime sits below LangChain and CrewAI, and what that distinction actually buys you.A response icon1A response icon1
InLevel Up CodingbyJoshua Phillips·May 13Why I Stopped Blaming the Model and Started Fixing the PipelineThe frustration with local LLMs in coding workflows is real, but the model is rarely the actual problem.
InGenerative AIbyJoshua Phillips·May 8I Expected Pulsar to Land on the Repo Shelf. It Didn’t.A weekend dogfood project ended up in HR, finance, and marketing. Here’s what I learned about building things you don’t expect to use.
InLevel Up CodingbyJoshua Phillips·May 6I Tried to Use My Own Product for Everything.A postmortem on three architectural wrong turns building a market intelligence agent, and the principle I should have started with.
Joshua Phillips·Apr 30Why Your RAG Pipeline Is Slower Than It Needs to BeWhy Your RAG Pipeline Is Slower Than It Needs to Be
Joshua Phillips·Apr 30Pulsar Told Us We Were Wrong About GoThe first time I ran Pulsar end to end, I sat down with the report expecting a list of content ideas. That was the whole point of the…