The library

11 pieces. Narrow them by what you are trying to solve.

Sorted newest first by default. Filter by subject or by the shape of the piece, or order by length when you have twenty minutes rather than an hour.

Topic
Format
Order11 pieces · 117 min
01Agent Evaluations Are Security SystemsEvaluation & safety511m

A realistic agent evaluation needs more than a benchmark and a score. It needs explicit scope, least-privileged tools, observable actions, stop conditions, and a recovery plan.

Evaluation & safety11 min read5 sources
02Beyond the Prompt: The Agent System Stack ExplainedAgent systems912m

Context, tools, memory, harnesses, loops, and evals are different layers of an AI agent system. Here is how they fit together—and why the model alone does not decide whether an agent works.

Agent systems12 min read9 sources
03Context Engineering: Why More Context Can Make an AI Agent WorseContext engineering411m

The model can only make its next decision from what is in front of it. Context engineering is the practice of keeping that working set current, relevant, and deliberately small.

Context engineering11 min read4 sources
04AI Agent Evals: How Do You Know an Agent Actually Works?Agent evaluation212m

A convincing final message is not proof of completion. Agent evaluations check the task, the actual environment, repeated trials, and the evidence left behind.

Agent evaluation12 min read2 sources
05Harness Engineering: Why a Better Model Is Not the Whole AnswerAgent systems511m

A capable model still needs a well-designed runtime around it. Harness engineering is the work of giving an agent useful context, tools, boundaries, state, and evidence of completion.

Agent systems11 min read5 sources
06Loop Engineering: What It Means—and Why It Is More Than Letting an Agent Run ForeverAgent systems510m

Loop engineering is an emerging label for designing repeated agent work: its trigger, state, feedback, boundaries, verification, and explicit ways to stop or hand off.

Agent systems10 min read5 sources
07Why an Agent Eval Can Pass on Monday and Fail on FridayAgent evaluation211m

A passing eval is evidence about one version of an agent system. When the model, context, tools, policies, or environment change, the evidence needs to be renewed.

Agent evaluation11 min read2 sources
08Autonomous Is Not Helpful: How Should We Evaluate Proactive AI Agents?Agent systems210m

An agent that can act without being asked is not automatically useful. The hard question is whether it noticed the right thing, had evidence, chose the right moment, and knew when to stay quiet.

Agent systems10 min read2 sources
09AI Agents, Explained: The Loop Behind the LabelAI agents39m

A beginner-friendly map of what makes a system agentic, how the model–tool loop works, and when a simpler workflow is the better design.

AI agents9 min read3 sources
10How Tool-Using AI Agents Work: A Weather Assistant, Step by StepTool use510m

Follow one tool call from a user request to a validated result, then see what changes when an agent can take actions instead of only reading data.

Tool use10 min read5 sources
11Agent Memory, Explained: Context, Retrieval, and StateContext & memory310m

Separate four mechanisms that are often called memory, then use the distinctions to design and test an agent that remembers the right things.

Context & memory10 min read3 sources

Prefer a reader? RSS · JSON Feed