The knowledge hub
Every episode, supplement and Frontier Dispatch as a readable article — with the cinematic render, the full transcript, and the one idea that matters. 276 articles and counting.
08
The plumbing
26 articles#187Ep2:45
Giving a model knowledge it never learned (RAG).
RAG (retrieval-augmented generation) gives a model knowledge without retraining: retrieve the relevant text at query time and paste it…
#188Ep2:30
How semantic search actually finds things.
Semantic search finds text by meaning, not keywords: embed the query and every document into vectors (meaning is a direction), then…
#189Ep2:30
Keywords aren't dead (hybrid + rerank).
Semantic search blurs exact terms (names, codes, acronyms) while keyword search nails them; the best systems use hybrid (both) plus a…
#190Ep2:30
What a vector database is for.
A vector database stores millions of embedding vectors and finds the nearest ones to a query fast, using an approximate-nearest-neighbor…
#191Ep2:30
Chunking: the unsexy key to good RAG.
You can't embed a whole document as one vector — you split it into chunks, and chunk size, boundaries, and overlap largely determine RAG…
#192Ep2:30
Why RAG still hallucinates.
RAG grounds the model in retrieved text but doesn't guarantee truth — it still hallucinates when retrieval misses, when the model ignores…
#193Ep2:30
The 'infinite context' illusion.
Huge context windows tempt you to "just paste everything," but bigger context isn't free (costs more, slower), isn't perfect (models…
#194Ep2:45
RAG vs. long context vs. fine-tune.
Three ways to give a model knowledge or behavior: RAG (retrieve relevant text per query — for large/changing/private knowledge), long…
#195Ep2:30
Types of agent memory.
Since the model is stateless, agent memory is built outside it, in tiers: short-term (the context window) and long-term (an external…
#196Ep2:45
What MCP actually is.
MCP (the Model Context Protocol) is a standard, universal way to connect models to tools and data — one "plug" so any MCP app can use any…
#197Ep2:30
MCP: client, server, and what flows between.
MCP has two roles — a client (inside the host app the model runs in) and a server (wrapping a tool/data source) — exchanging a defined set…
#198Ep2:30
MCP's three offerings: tools, resources, prompts.
An MCP server can expose three kinds of things — tools (actions the model calls), resources (data the model reads), and prompts (reusable…
#199Ep3:00
[LAB] Wire your first MCP server.
An MCP server is small: pick a capability, write a plain function, describe it for MCP (name, description, input schema), register it with…
#200Ep2:30
MCP's security surface.
Connecting a model to tools and data via MCP opens a real security surface: untrusted servers (third-party code with access), prompt…
#201Ep2:30
Why agents need to talk to each other.
One agent hits limits — finite/rotting context, one perspective, one skillset — so complex work benefits from multiple specialized agents…
#202Ep2:45
What a 'harness' adds around a model.
A harness is everything wrapped around the raw model — the loop, tool execution, context assembly, memory, parsing, retries, guardrails…
#203Ep2:45
Inside a coding agent (Claude Code-class).
A coding agent is a concrete, powerful harness: it wraps a general model with file tools, a shell, codebase search, a think-act-observe…
#204Ep2:45
What the model ACTUALLY sees.
The model never sees the UI, your app, or a persistent "assistant" — on every call it sees only a flat blob of text the harness assembled…
#205Ep2:30
Skills: reusable capabilities for agents.
A skill is a packaged, reusable capability — instructions, and often a tool or reference file — that an agent loads on demand when it's…
#206Ep2:30
Hooks: injecting control into the loop.
A hook is custom code the harness runs at a defined point in the agent's loop — before/after a tool call, at the start/end of a turn…
#207Ep2:30
Rules and system instructions (and their limits).
Rules — standing instructions in the system prompt — powerfully shape an agent's behavior, but because the model is probabilistic they…
#208Ep2:30
Sandboxing: letting an agent run code safely.
A sandbox is an isolated environment where an agent's code and actions run, walled off from everything else — restricted filesystem…
#209Ep2:30
Multi-agent orchestration: swarms and roles.
Orchestration is coordinating multiple specialized agents toward one goal — usually an orchestrator that plans and delegates to role-based…
#210Ep2:30
Subagents: fresh context on demand.
A subagent is a fresh agent spawned to do one bounded job with a clean context, returning only a short summary — so the parent's window…
#211Ep2:30
Why more agents isn't always better.
Adding agents has diminishing then negative returns: coordination overhead grows and errors compound across a chain, so past a point more…
#212Ep2:30
The honest limits of memory and harnesses.
The harness is powerful but not magic: real systems still break in recurring ways — drift over long runs, stale or conflicting memory…