The Harness Around the Model

A thread you can test

Agent Engineering

24 notes move from the word to a real choice at work — understand it first, then decide whether to use it.

READING THREADOPEN
24notes
HOW TO READStart where you are stuck, then follow the evidence and trade-offs

Each note stands alone, or becomes the next step in this thread.

The Harness Around the ModelNo login

THE QUESTION THIS PAGE ANSWERS

ANSWER FIRST

What is Agent Engineering, and which AI decisions does it change?

Four capabilities: Plan / Tool / Memory / Act — click to see real-world cases This page keeps the related concepts, common mistakes, and practical notes in one reading thread.

DECISION RULE

First decide whether you are blocked by a definition, a choice, or verification; then choose the closest of the 24 notes below.

TRY NEXT

Start with “Agent: AI That Gets Things Done,” then restate the conclusion using your own task.

WATCH FOR

Do not treat every method in a topic as interchangeable. The answer changes with the input, risk, and acceptance bar.

THIS QUESTION THREAD

Put the word back inside the choice it changes.

24 notes
Interactive

Agent: AI That Gets Things Done

Four capabilities: Plan / Tool / Memory / Act — click to see real-world cases

The Harness Around the Model 4 min →
Interactive

The Secret of Tool Calling

Model outputs JSON → framework parses & executes → result injected back; four-step flow visualization

The Harness Around the Model 3 min →
Deep Dive

5 Messages Behind One Conversation

Deconstructing the real Function Calling chain: the user sees 1 reply, but 5 API messages happen behind the scenes

The Harness Around the Model 3 min →
Deep Dive

The Art of Tool Descriptions

Same functionality, but good vs bad descriptions differ by 3× in success rate — a contrast experiment

The Harness Around the Model 3 min →
Deep Dive

Multi-Tool Orchestration: Parallel vs Serial

isConcurrencySafe determines whether tools can run in parallel; scheduling strategy visualization

The Harness Around the Model 3 min →
Deep Dive

MCP Protocol: The USB Port for Tools

Comparing stdio / SSE / Streamable HTTP transport methods; data-flow animation

The Harness Around the Model 3 min →
Animation

ReAct in Practice: Weather Query Full Chain

Thought / Action / Observation step-by-step demo; complete 7-step Agent chain

The Harness Around the Model 3 min →
Deep Dive

Short-Term Memory = Context Window

Message list visualization showing each message's Token usage and role label

The Harness Around the Model 3 min →
Deep Dive

Context Compression: Four Defense Lines

60% trim → 75% micro-compress → 85% fold → 95% emergency; drag the slider to watch the process

The Harness Around the Model 3 min →
Deep Dive

Long-Term Memory: Vector Retrieval

Embedding → vector database → semantic search; design decisions for topK and minScore

The Harness Around the Model 3 min →
Deep Dive

From Embeddings to Milvus

Semantic similarity, ANN, and the responsibility boundary of a vector database

The Harness Around the Model 3 min →
Deep Dive

The Milvus Mental Model

Collection, Schema, Entity, Index, Search, Query, and Load

The Harness Around the Model 3 min →
Hands-on

Hands-on Milvus

Connect, create, batch insert, index, search, query, and delete

The Harness Around the Model 3 min →
Deep Dive

From Retrieval to RAG

Chunking, filtering, hybrid search, RRF, reranking, and evaluation

The Harness Around the Model 3 min →
Deep Dive

ReAct Loop: Think → Act → Observe

A task to remove console.log goes through 14 iterations, including self-correction

The Harness Around the Model 3 min →
Deep Dive

5 Patterns of Agent Deadlock

Parameter format errors / hallucinated tools / infinite recursion / insufficient info / API exceptions

The Harness Around the Model 3 min →
Deep Dive

Permissions & Security

5 permission modes + LLM risk levels + Human-in-the-loop design

The Harness Around the Model 3 min →
Interactive

Skill: Helping Agents Avoid Detours

Skill = workflow instructions + tool-calling guidance; a "laundry on the balcony" analogy for good loops vs bad loops

The Harness Around the Model 3 min →
Deep Dive

The Essence of Skill

Good loop vs bad loop upgraded; how Skill changes an Agent's execution path

The Harness Around the Model 3 min →
Interactive

Scaffolding: From Prototype to Product

Simulate an Agent booking flights & hotels; full comparison with and without scaffolding; 5 key capabilities explained

The Harness Around the Model 3 min →
Deep Dive

5 Engineering Guardrails

Iteration cap, output truncation, timeout control, interrupt recovery, context emergency

The Harness Around the Model 3 min →
Deep Dive

Multi-Agent Collaboration

Sub-Agent dispatch, worker threads, parallel vs serial execution strategies

The Harness Around the Model 3 min →
Deep Dive

Observability

Event stream visualization, Token tracking, OpenTelemetry integration

The Harness Around the Model 3 min →
Recap

Agent Engineering Overview

From four capabilities to production deployment — the complete Agent knowledge map on one page

The Harness Around the Model 3 min →