Understand important new AI systems and ideas through mechanism-first explainers on projects, protocols, research, and architecture debates.
Tutorials
Explore the mechanisms, tradeoffs, and implementation patterns within this AI engineering track.
“Everything is a plugin” is a claim about architecture, not a feature list. It says the agent loop itself is replaceable — and that is expensive to mean.
Read tutorial
The demo worked. Then the corpus grew, the questions started requiring synthesis across documents, and the same pipeline that felt magical last month now…
Read tutorial
The agent worked yesterday. Today it burns forty thousand tokens before it reads your first instruction, and the hook that used to register identity with a…
Read tutorial
Two projects both advertise "open source, model-agnostic, multi-channel, MCP support." A builder picks one, ships it, and discovers the real difference the…
Read tutorial
"Self-improving agent" is three different mechanisms wearing one coat. Pull the coat off and you find a memory that accumulates, a skill file that gets…
Read tutorial
Two seed-stage teams ship an LLM-backed product. Same headcount, same model access, same demo polish. Eighteen months later, one compounds while the other…
Read tutorial
Ask a system to synthesize five documents into one answer. It does the work. Ask the same question tomorrow, and it does the work again, from scratch, with…
Read tutorial
A coding agent is handed a fixed training script and a fixed success metric: make it run faster without breaking correctness. It rewrites, runs, times, and…
Read tutorial
Your agent has thirty tools, four MCP servers, and a plan-mode toggle. It still fumbles a routine refactor, and when it does, you cannot tell whether the…
Read tutorial
The loop that improves the harness can also edit the evaluator, the permissions, and the rollback path. That is the whole problem in one sentence.
Read tutorial
A team scaffolds an AGENTS.md with /init, the agent improves for a week, and then the file quietly becomes a 14k-token policy document that nobody reads…
Read tutorial
MCP answers "what can I call?" A2A answers "who can I hand this to?" Different questions, different failure modes.
Read tutorial
An agent that only works until the container restarts is not an agent. It is a demo with a heartbeat.
Read tutorial
A scanner that flags ten thousand findings and a researcher who proves three are both "finding vulnerabilities." Only one of them has evidence you can…
Read tutorial
The redesign did not delete state. It relocated it — and everything downstream follows from where it landed.
Read tutorial
Hop three. The context window is full. Half of it is plausible garbage — passages that matched the query, ranked well, and turned out to be useless. The…
Read tutorial
You have a routing step in an agent pipeline. Four possible destinations. The LLM call costs a full generation, 1–2 seconds, and a token bill. The answer…
Read tutorial