The AI Cheat Sheet
Speak the language of agents. First pass = the short “remember” lines; details wait for later lessons.
How to read this lesson
This is the dictionary for the course. Read the intro and the remember line on each card, then move on.
- Come back to a card when a later lesson names that word (install, SOUL, tools…).
1 · Core stack
Four words name almost everything in this course.
LLM
Large Language Model — predicts the next bit of text. Pure chat is mostly text in → text out. It can sound smart without ever touching your files. In an agent setup it is only the brain.
Agent
A system: LLM brain plus tools and memory, driven by a loop the app runs (Think → Act → Observe). The loop is around the model, not a secret chip inside the weights.
Harness
The app frame that runs the loop: messages, tools, approvals, memory, gateway. Hermes Desktop ↗ is that frame on your machine — what you control.
Runtime
Where the process lives: spare PC, VPS, container… We prefer a dedicated machine, not the laptop that holds your whole life. Different idea from “brain” or “app design.”
2 · The agent loop (not the LLM alone)
The loop is not “inside the LLM alone.” Operators decide who does Think vs Act vs Observe.
Three beats. Think (model plans) → Act (app runs a tool or answers) → Observe (result goes back into the chat for the next Think).
That cycle is how an agent system works. It is not a hidden loop living only inside the LLM. Chat-in-a-browser without real host tools is mostly Think → reply.
Think
The model plans: what next, which tool, when to stop. You usually see this as the next reply or a tool request — not a separate “loop chip” inside the model.
Act
Something happens outside pure text: write a file, run a command, call a service — or just answer. Approvals and host safety apply here.
Observe
The tool result or error is pasted back into the chat so the next Think is grounded. No observe → higher chance of invention.
Planning
Choosing steps, then re-planning after each Observe. You help with a clear goal, constraints, and “done when.” (Fine print; the three steps above are enough for pass one.)
| Who | Beat | What happens |
|---|---|---|
| Think · LLM | Plans the next move | Maybe asks for a tool, or drafts a final answer. Think lives in the model’s reply. |
| Act · Harness | Actually runs the tool — or sends the final answer | Harness (+ tools on the machine). Approvals may stop a risky act here. |
| Observe · Harness → LLM | Puts the tool result (or error) back into the conversation | That observation feeds the next Think. Errors count as observations too. |
- I can walk Think → Act → Observe once out loud
- I assign Think to the LLM and Act/Observe packaging to the harness
Who actually runs a file-write tool call?
Pick one — the answer is revealed straight away.
A tool comes back with “permission denied.” What is that?
Pick one — the answer is revealed straight away.
3 · Models, cost, and keys
How you pay for the brain, and where secrets live. One cloud rule: conversation content can leave your machine.
Token
Billing unit for model input/output — roughly part of a word. Free tiers still have limits.
Cloud model
Brain runs at a provider instead of on your machine. Convenient; prompts and replies leave the host. You pick a provider during install (lesson 03).
Local model
Weights run on hardware you control. Different cost (GPU/time). Optional later — not day one.
API key
Secret that proves “this is me” to a provider. If it leaks, someone can spend in your name.
`.env`
Local file for secrets, kept out of git. Programs read keys from there.
4 · What it remembers, and what it forgets
Close the chat and today’s conversation is gone. Anything the agent should still know next week has to be written to a file. That one difference — context vs memory — is what beginners get wrong most, and it explains half the “why did it forget?” moments ahead.
Context
What is in the current chat window for the model — session “RAM.” Close or compress the thread and it fades.
Memory
Facts you (or the agent) write to disk so they can load again next week — e.g. MEMORY.md. Different from “it was in the chat yesterday.”
SOUL
Plain idea: a short identity file — name, tone, hard limits (“never delete without asking”). Lives with the Hermes profile on the host. You will set this in lesson 04; for now just know the word means “who this agent is supposed to be.”
Hallucination
When evidence is missing, the model still sounds sure. Files and tool results reduce that risk — they don’t delete it.
5 · Tools, skills, plugins, and MCP
Two words carry most of it: tool = something the app can do (write a file, list a folder). Skill = a howto package that teaches the agent how to use tools for a job. Everything else can wait.
| Word | What it means | Meet later when… |
|---|---|---|
| Tool | Callable action — the Act step | You open Tools in Desktop (lesson 06) |
| Skill | Howto / procedure file (SKILL.md) | You trim or add skills (lesson 09) |
| Plugin | Extra UI inside Hermes Desktop | You enable Desktop extras |
| MCP | Plug for an outside service (docs, repos…) | You need a live external system — not day one |
Tool
Something Hermes can run: a name, some inputs, a result or error. Hands of the agent, listed in the Hermes tools docs ↗. Output feeds Observe.
Tool call
The model asks for a tool with structured inputs; Hermes runs it (sometimes after you approve); the result comes back as a tool message.
Skill
A reusable howto (often SKILL.md). Helps Think pick good steps. It does not replace tools — it teaches when and how to use them.
Plugin
Optional Desktop add-on (extra UI or product feature). Not required to finish Part I.
MCP
A standard way to plug external services. Powerful and another trust surface. You can finish early lessons without MCP.
6 · Reach outside the Desktop window
Two words for work that happens when you are not staring at the app. Full how-to is lessons 05 and 11.
Gateway
Bridge so the harness can answer from a messaging app (Telegram and others). Only allowlisted people may talk. Setup is lesson 05.
Cron
A job on a schedule (e.g. weekday morning summary). Needs a host that is awake. Lesson 11.
Chat product vs harness agent
Modern browser chat (ChatGPT and friends) can already use some tools. The useful contrast is not “they never touch tools” — it is who owns the loop, the files, and the host.
| Browser chat (e.g. ChatGPT) | Agent on your harness |
|---|---|
| Tools are their product features, on their servers | Tools run under your harness on your runtime (files, shell, …) |
| History lives in their account — you export if they let you | Facts and receipts can live as files you open offline |
| Limits and policies are vendor defaults | Identity, approvals, allowlists are yours to set (SOUL, security) |
| Great for quick answers and hosted workflows | Built for persistence, multi-step work, and local control |