CS I · Fri Oct 23 · 12.5 · Do Now

The Parts List

  • Terminology and concepts to look out for: interface · system prompt · component
  • Relevance to me: You have learned each part one at a time. Today you put all the parts in one list. Next week you see how programs package AI.You have met each part one at a time, like strangers at a bus stop. Today you put all the parts in one list, so you can see the whole machine at once.
  • Board Question: A student types a question into a web page and an answer appears. How many separate parts did that take? Write a number and name the parts.

Open the discussion form on the right and answer Section 1 from your first reading.

Discussion form

Sign out of Google when you finish on a shared computer, so the next student can sign in as themselves. Google then shows a "Redirect notice" page. Click the muggsofcompsci.net/cs1 link on it to come back.

I Do questions
  1. notebook cue: interface

    Which parts of the chain can the user see and touch?

    Check

    Only the interface: the page in the browser, with its typing box, its button and the area where the answer appears. The servers and the model do their work out of sight, and the system prompt usually does too. See The Interface, paragraph 1.

  2. notebook cue: system prompt

    Two tools use the same model and behave differently. What did their builders write differently?

    Check

    The system prompt, the set of instructions each builder writes ahead of time and sends to the model with every request. See The System Prompt, paragraph 2.

  3. notebook cue: component

    "The AI gave me the answer." Break "the AI" into at least three components.

    Check

    Any three of the interface, the request, the server, the system prompt, the model (parameters and runtime), the memory and GPU, and the response. The passage names at least four: the interface, the server, the system prompt and the model. See Components and the Specification, paragraph 1, and Figure 1.

Announcements

The Parts of an AI Tool

This section follows one question from a web page to an answer and names each part that the question passes through.

Following One Question

An AI tool that a person reaches through a web page is built from several parts that pass work along in order. The example is the Name That Element page of MuggsAI. On that page, a student describes something on a screen, such as a box that pops up over a game, and the tool replies with the name of that element.

First, the student types the description into a box on the page and presses a button. The browser then sends a request to the class site's server. A request is a message that names a server and the resource it asks for, and it can carry data such as the text from a form. Next, the class site's server adds its own instructions to the student's text and sends a second request to Mistral's server, which runs the model. The model has two parts: a large file of numbers called parameters and a smaller program called a runtime. To run, the parameters are loaded into memory, usually the memory on a GPU, and the runtime uses them to predict the answer one token at a time. Finally, the answer travels back as a response, from Mistral's server to the class site's server and then to the browser, which shows it on the page. Figure 1 shows the parts of this chain in order, with the two servers drawn as one box.

The Interface

The interface is the part of a tool that a person sees and touches, which for a web tool is the page in the browser. On the Name That Element page, the interface includes the typing box, the button and the area where the answer appears. MDN describes a user interface as anything that helps a person use a machine, and it lists a web page and an input form as examples. For example, a student who changes the color of the button has changed the interface. The server is part of the tool and not part of the interface. A student never sees the class site's server or Mistral's server, even though both do work on every question. Several MuggsAI pages send their requests to the same server and the same model, and each page still has its own interface.

The System Prompt

A system prompt is a set of instructions that the builder of a tool writes ahead of time and sends to the model with every request. Mistral's documentation describes the system message as an optional message that sets the behavior and context of the assistant. It also says that the system prompt is typically managed by the developer of the tool. In MuggsAI, the server places a system message in front of the student's text each time it sends that text to the model. The Name That Element system prompt tells the model to give names from the class Elements Catalog and not to write code.

What the user types is a prompt, not the system prompt. The student's text travels in a separate message, and that message has the role "user" in the request. The user usually never sees the system prompt, although some tools show it. MuggsOfPrompts, for example, shows its system prompt on the page as read-only text. Because the system prompt shapes how the model responds, two tools that use the same model can behave differently.

Components and the Specification

A component is one part of a system that has one job and can be named and replaced. The interface is a component, because its job is to collect the question and show the answer. The server is a component, because its job is to receive the request, add the system prompt and pass the work along. The model is a component whose job is to predict the answer, and the memory and GPU are the hardware it needs to do that. "The AI" is not one component. It is made of at least four: the interface, the server, the system prompt and the model.

Each component can be changed without rebuilding the others. For example, a builder can rewrite the system prompt and leave the interface and the server unchanged. A specification for a tool describes each component: what it is, what it receives and what it sends on.

Summary

A question typed into a web tool passes through an interface, a request, a server, a system prompt, a model running in memory on a GPU, and a response. Each of these is a component with one job. A specification for a tool names each component and describes its job.

Sources: MDN Web Docs, Client-server overview (2026); MDN Web Docs, UI (2025); Mistral AI, Chat completions and Prompting (n.d.); Hugging Face, Optimizing LLMs for Speed and Memory (n.d.); ggml-org, llama.cpp (n.d.); MuggsAI and MuggsOfPrompts request paths, class site source code (2026).

The Parts of an AI Tool, Itemized

This entry follows one question from a web page to an answer and names every part the question passes through on the way, of which there are more than you would think.

Following One Question

An AI tool that a person reaches through a web page is built from several parts that pass work along in order, like a bucket brigade that never gets tired. The example is the Name That Element page of MuggsAI. On that page, a student describes something on a screen, such as a box that pops up over a game, and the tool replies with the name of that element.

First, the student types the description into a box on the page and presses a button. The browser then sends a request to the class site's server. A request is a message that names a server and the resource it asks for, and it can carry data such as the text from a form. Next, the class site's server adds its own instructions to the student's text and sends a second request to Mistral's server, which runs the model. The model has two parts: a large file of numbers called parameters and a smaller program called a runtime. To run, the parameters are loaded into memory, usually the memory on a GPU, and the runtime uses them to predict the answer one token at a time. Finally, the answer travels back as a response, from Mistral's server to the class site's server and then to the browser, which shows it on the page as if nothing much had happened. Figure 1 shows the parts of this chain in order, with the two servers drawn as one box to save everyone some ink.

The Interface

The interface is the part of a tool that a person sees and touches, which for a web tool is the page in the browser. It is the only part most people ever meet. On the Name That Element page, the interface includes the typing box, the button and the area where the answer appears. MDN describes a user interface as anything that helps a person use a machine, and it lists a web page and an input form as examples. For example, a student who changes the color of the button has changed the interface, and nothing else. The server is part of the tool and not part of the interface. A student never sees the class site's server or Mistral's server, even though both do work on every question, quietly, like stagehands. Several MuggsAI pages send their requests to the same server and the same model, and each page still has its own interface.

The System Prompt

A system prompt is a set of instructions that the builder of a tool writes ahead of time and sends to the model with every request. Think of it as a note pinned to the model's shirt before it goes out. Mistral's documentation describes the system message as an optional message that sets the behavior and context of the assistant. It also says that the system prompt is typically managed by the developer of the tool. In MuggsAI, the server places a system message in front of the student's text each time it sends that text to the model. The Name That Element system prompt tells the model to give names from the class Elements Catalog and not to write code.

What the user types is a prompt, not the system prompt. The student's text travels in a separate message, and that message has the role "user" in the request. The user usually never sees the system prompt, although some tools show it. MuggsOfPrompts, for example, shows its system prompt on the page as read-only text, which is unusually honest of it. Because the system prompt shapes how the model responds, two tools that use the same model can behave like two different creatures.

Components and the Specification

A component is one part of a system that has one job and can be named and replaced. The interface is a component, because its job is to collect the question and show the answer. The server is a component, because its job is to receive the request, add the system prompt and pass the work along. The model is a component whose job is to predict the answer, and the memory and GPU are the hardware it needs to do that. "The AI" is not one component, however much it would like to be. It is made of at least four: the interface, the server, the system prompt and the model.

Each component can be changed without rebuilding the others, which is a great comfort to anyone who has to fix one. For example, a builder can rewrite the system prompt and leave the interface and the server alone. A specification for a tool describes each component: what it is, what it receives and what it sends on.

Summary

A question typed into a web tool passes through an interface, a request, a server, a system prompt, a model running in memory on a GPU, and a response. Each of these is a component with one job. A specification for a tool names each component and describes its job, so that nobody has to guess.

Sources: MDN Web Docs, Client-server overview (2026); MDN Web Docs, UI (2025); Mistral AI, Chat completions and Prompting (n.d.); Hugging Face, Optimizing LLMs for Speed and Memory (n.d.); ggml-org, llama.cpp (n.d.); MuggsAI and MuggsOfPrompts request paths, class site source code (2026).

Discussion form

Sign out of Google when you finish on a shared computer, so the next student can sign in as themselves. Google then shows a "Redirect notice" page. Click the muggsofcompsci.net/cs1 link on it to come back.

I Do questions
  1. notebook cue: interface

    Which parts of the chain can the user see and touch?

    Check

    Only the interface: the page in the browser, with its typing box, its button and the area where the answer appears. The servers and the model do their work out of sight, and the system prompt usually does too. See The Interface, paragraph 1.

  2. notebook cue: system prompt

    Two tools use the same model and behave differently. What did their builders write differently?

    Check

    The system prompt, the set of instructions each builder writes ahead of time and sends to the model with every request. See The System Prompt, paragraph 2.

  3. notebook cue: component

    "The AI gave me the answer." Break "the AI" into at least three components.

    Check

    Any three of the interface, the request, the server, the system prompt, the model (parameters and runtime), the memory and GPU, and the response. The passage names at least four: the interface, the server, the system prompt and the model. See Components and the Specification, paragraph 1, and Figure 1.

Figure 1. The seven parts between a question typed on a web page and the answer that appears, numbered in the order the work passes through them.Figure 1. The seven parts between a question typed on a web page and the answer that appears, numbered in the order the work passes through them, whether or not anyone notices.

The big picture so far (newest on top)

Big picture 3 of 5. Generation and retrieval. In Google's AI Mode, Lens reads the image, Search fetches pages from the open web (retrieval), and Gemini writes the answer from its squeezed chunk (generation), with links back to the pages.
Big picture 2 of 5. The song ladder. On each rung the gaps get bigger and less is really known, but the model sings every rung in the same confident voice. On rung 4 a word gets "picked anyway," which people call a hallucination.
Big picture 1 of 5 (from 12.2). Training squeezes one chunk of the internet into a much smaller parameters file and loses details; probability fills the gaps when the model is used.
Discussion form

Sign out of Google when you finish on a shared computer, so the next student can sign in as themselves. Google then shows a "Redirect notice" page. Click the muggsofcompsci.net/cs1 link on it to come back.

I Do questions
  1. notebook cue: interface

    Which parts of the chain can the user see and touch?

    Check

    Only the interface: the page in the browser, with its typing box, its button and the area where the answer appears. The servers and the model do their work out of sight, and the system prompt usually does too. See The Interface, paragraph 1.

  2. notebook cue: system prompt

    Two tools use the same model and behave differently. What did their builders write differently?

    Check

    The system prompt, the set of instructions each builder writes ahead of time and sends to the model with every request. See The System Prompt, paragraph 2.

  3. notebook cue: component

    "The AI gave me the answer." Break "the AI" into at least three components.

    Check

    Any three of the interface, the request, the server, the system prompt, the model (parameters and runtime), the memory and GPU, and the response. The passage names at least four: the interface, the server, the system prompt and the model. See Components and the Specification, paragraph 1, and Figure 1.

The Parts of an AI Tool

This section follows one question from a web page to an answer and names each part that the question passes through.

Following One Question

An AI tool that a person reaches through a web page is built from several parts that pass work along in order. The example is the Name That Element page of MuggsAI. On that page, a student describes something on a screen, such as a box that pops up over a game, and the tool replies with the name of that element.

First, the student types the description into a box on the page and presses a button. The browser then sends a request to the class site's server. A request is a message that names a server and the resource it asks for, and it can carry data such as the text from a form. Next, the class site's server adds its own instructions to the student's text and sends a second request to Mistral's server, which runs the model. The model has two parts: a large file of numbers called parameters and a smaller program called a runtime. To run, the parameters are loaded into memory, usually the memory on a GPU, and the runtime uses them to predict the answer one token at a time. Finally, the answer travels back as a response, from Mistral's server to the class site's server and then to the browser, which shows it on the page. Figure 1 shows the parts of this chain in order, with the two servers drawn as one box.

The Interface

The interface is the part of a tool that a person sees and touches, which for a web tool is the page in the browser. On the Name That Element page, the interface includes the typing box, the button and the area where the answer appears. MDN describes a user interface as anything that helps a person use a machine, and it lists a web page and an input form as examples. For example, a student who changes the color of the button has changed the interface. The server is part of the tool and not part of the interface. A student never sees the class site's server or Mistral's server, even though both do work on every question. Several MuggsAI pages send their requests to the same server and the same model, and each page still has its own interface.

The System Prompt

A system prompt is a set of instructions that the builder of a tool writes ahead of time and sends to the model with every request. Mistral's documentation describes the system message as an optional message that sets the behavior and context of the assistant. It also says that the system prompt is typically managed by the developer of the tool. In MuggsAI, the server places a system message in front of the student's text each time it sends that text to the model. The Name That Element system prompt tells the model to give names from the class Elements Catalog and not to write code.

What the user types is a prompt, not the system prompt. The student's text travels in a separate message, and that message has the role "user" in the request. The user usually never sees the system prompt, although some tools show it. MuggsOfPrompts, for example, shows its system prompt on the page as read-only text. Because the system prompt shapes how the model responds, two tools that use the same model can behave differently.

Components and the Specification

A component is one part of a system that has one job and can be named and replaced. The interface is a component, because its job is to collect the question and show the answer. The server is a component, because its job is to receive the request, add the system prompt and pass the work along. The model is a component whose job is to predict the answer, and the memory and GPU are the hardware it needs to do that. "The AI" is not one component. It is made of at least four: the interface, the server, the system prompt and the model.

Each component can be changed without rebuilding the others. For example, a builder can rewrite the system prompt and leave the interface and the server unchanged. A specification for a tool describes each component: what it is, what it receives and what it sends on.

Summary

A question typed into a web tool passes through an interface, a request, a server, a system prompt, a model running in memory on a GPU, and a response. Each of these is a component with one job. A specification for a tool names each component and describes its job.

Sources: MDN Web Docs, Client-server overview (2026); MDN Web Docs, UI (2025); Mistral AI, Chat completions and Prompting (n.d.); Hugging Face, Optimizing LLMs for Speed and Memory (n.d.); ggml-org, llama.cpp (n.d.); MuggsAI and MuggsOfPrompts request paths, class site source code (2026).

The Parts of an AI Tool, Itemized

This entry follows one question from a web page to an answer and names every part the question passes through on the way, of which there are more than you would think.

Following One Question

An AI tool that a person reaches through a web page is built from several parts that pass work along in order, like a bucket brigade that never gets tired. The example is the Name That Element page of MuggsAI. On that page, a student describes something on a screen, such as a box that pops up over a game, and the tool replies with the name of that element.

First, the student types the description into a box on the page and presses a button. The browser then sends a request to the class site's server. A request is a message that names a server and the resource it asks for, and it can carry data such as the text from a form. Next, the class site's server adds its own instructions to the student's text and sends a second request to Mistral's server, which runs the model. The model has two parts: a large file of numbers called parameters and a smaller program called a runtime. To run, the parameters are loaded into memory, usually the memory on a GPU, and the runtime uses them to predict the answer one token at a time. Finally, the answer travels back as a response, from Mistral's server to the class site's server and then to the browser, which shows it on the page as if nothing much had happened. Figure 1 shows the parts of this chain in order, with the two servers drawn as one box to save everyone some ink.

The Interface

The interface is the part of a tool that a person sees and touches, which for a web tool is the page in the browser. It is the only part most people ever meet. On the Name That Element page, the interface includes the typing box, the button and the area where the answer appears. MDN describes a user interface as anything that helps a person use a machine, and it lists a web page and an input form as examples. For example, a student who changes the color of the button has changed the interface, and nothing else. The server is part of the tool and not part of the interface. A student never sees the class site's server or Mistral's server, even though both do work on every question, quietly, like stagehands. Several MuggsAI pages send their requests to the same server and the same model, and each page still has its own interface.

The System Prompt

A system prompt is a set of instructions that the builder of a tool writes ahead of time and sends to the model with every request. Think of it as a note pinned to the model's shirt before it goes out. Mistral's documentation describes the system message as an optional message that sets the behavior and context of the assistant. It also says that the system prompt is typically managed by the developer of the tool. In MuggsAI, the server places a system message in front of the student's text each time it sends that text to the model. The Name That Element system prompt tells the model to give names from the class Elements Catalog and not to write code.

What the user types is a prompt, not the system prompt. The student's text travels in a separate message, and that message has the role "user" in the request. The user usually never sees the system prompt, although some tools show it. MuggsOfPrompts, for example, shows its system prompt on the page as read-only text, which is unusually honest of it. Because the system prompt shapes how the model responds, two tools that use the same model can behave like two different creatures.

Components and the Specification

A component is one part of a system that has one job and can be named and replaced. The interface is a component, because its job is to collect the question and show the answer. The server is a component, because its job is to receive the request, add the system prompt and pass the work along. The model is a component whose job is to predict the answer, and the memory and GPU are the hardware it needs to do that. "The AI" is not one component, however much it would like to be. It is made of at least four: the interface, the server, the system prompt and the model.

Each component can be changed without rebuilding the others, which is a great comfort to anyone who has to fix one. For example, a builder can rewrite the system prompt and leave the interface and the server alone. A specification for a tool describes each component: what it is, what it receives and what it sends on.

Summary

A question typed into a web tool passes through an interface, a request, a server, a system prompt, a model running in memory on a GPU, and a response. Each of these is a component with one job. A specification for a tool names each component and describes its job, so that nobody has to guess.

Sources: MDN Web Docs, Client-server overview (2026); MDN Web Docs, UI (2025); Mistral AI, Chat completions and Prompting (n.d.); Hugging Face, Optimizing LLMs for Speed and Memory (n.d.); ggml-org, llama.cpp (n.d.); MuggsAI and MuggsOfPrompts request paths, class site source code (2026).

Table Talk
A student types a question into a web page and an answer appears. How many separate parts did that take? Write a number and name the parts.

Each table agrees on one number and one list of parts. Different tables may get different numbers. The count depends on how finely the parts are divided.

Chromebooks stay closed while your table talks. Sections 1 and 2 of the discussion form are already done. After you talk, finish Section 3 right here under My View. Submit before the exit ticket.

Sign out of Google when you finish on a shared computer, so the next student can sign in as themselves. Google then shows a "Redirect notice" page. Click the muggsofcompsci.net/cs1 link on it to come back.

This form has three sections. Section 1: answer today's Board Question. Section 2: after the reading. Section 3 opens later in class. Today's Board Question: A student types a question into a web page and an answer appears. How many separate parts did that take? Write a number and name the parts.

CR 1. Board Question: A student types a question into a web page and an answer appears. How many separate parts did that take? Write a number and name the parts. Give your answer and one reason.

Write your answer in your lab notebook, labeled CR 1.

MC 1. Think about your answer to the board question. A student types a question into a web page and an answer appears. How many separate parts did that take? Write a number and name the parts. Which position is closest to yours now?

  • Two: the web page and the AI.
  • Four or five: the page, the request, the server and the model.
  • Seven or more, once the system prompt, the hardware and the response are counted.

MC 2. (Statement 1) The system prompt is the question the user types.

  • Agree
  • Disagree

MC 3. (Statement 2) The interface is the part of a tool that the user sees and touches.

  • Agree
  • Disagree

MC 4. (Statement 3) Two tools that use the same model can behave differently.

  • Agree
  • Disagree

CR 2. (A different view) Write the view at your table that was most different from yours. If everyone agreed, write the strongest argument against your table's answer.

Write your answer in your lab notebook, labeled CR 2.

CR 3. Think about the Board Question again: A student types a question into a web page and an answer appears. How many separate parts did that take? Write a number and name the parts. Do you have the same opinion as when you first answered the board question? If it is the same, what from the reading or table talk reaffirmed your opinion? If it is different, what from the reading or table talk changed your opinion?

Write your answer in your lab notebook, labeled CR 3.