# How AI agents are built

- Link: https://arqiv.si/ai/how-agents-are-built/
- Published: 2026-10-13T07:54:59-04:00
- Author: Steven Ryan

[Skip to content](https://arqiv.si/ai/how-agents-are-built/#main-content)

[arqiv](https://arqiv.si/)

[For educators](https://arqiv.si/teachers/)

Teach

 * [Start here](https://arqiv.si/teachers/)
 * [Lessons & printable kits](https://arqiv.si/teachers/resources/)
 * [Classroom labs](https://arqiv.si/teachers/labs/)
 * [Free 20-minute lesson](https://arqiv.si/teachers/free-ai-lesson/)

Plan

 * [Curriculum guide](https://arqiv.si/teachers/curriculum/)
 * [AI Learning Center](https://arqiv.si/teachers/ai-literacy/)
 * [Future of work unit](https://arqiv.si/future-of-work/)
 * [What the research says](https://arqiv.si/teachers/what-works/)
 * [AI education worldwide](https://arqiv.si/teachers/around-the-world/)

Understand

 * [Think First method](https://arqiv.si/teachers/think-first/)
 * [Our approach](https://arqiv.si/research/#our-method)
 * [AI vocabulary](https://arqiv.si/teachers/ai-vocabulary/)

By role

 * [Counselors](https://arqiv.si/counselors/)
 * [School leaders & PD](https://arqiv.si/schools/)
 * [Speaking & workshops](https://arqiv.si/speaking/)
 * [Products](https://arqiv.si/products/)

[Learn AI](https://arqiv.si/ai/topics/)

Start

 * [All AI topics](https://arqiv.si/ai/topics/)
 * [The AI journey, from zero](https://arqiv.si/ai/)
 * [Using AI well](https://arqiv.si/ai/talking-to-ai/)
 * [AI builds](https://arqiv.si/ai-builds/)

AI in the world

 * [Space](https://arqiv.si/space/)
 * [Weather](https://arqiv.si/weather/)
 * [Health](https://arqiv.si/health/)
 * [Engineering](https://arqiv.si/engineering/)
 * [Farming](https://arqiv.si/farming/)
 * [Quantum](https://arqiv.si/quantum/)

What it means

 * [Future of work](https://arqiv.si/future-of-work/)
 * [Your AI path](https://arqiv.si/ai/your-path/)
 * [Research, explained](https://arqiv.si/research/)

[Games & labs](https://arqiv.si/games/)[Research](https://arqiv.si/research/)[Blog](https://arqiv.si/blog/)
[About](https://arqiv.si/about/)

[Search or ask](https://arqiv.si/ai/topics/)[Newsletter](https://arqiv.si/newsletter/)
[ARQIV.FM ↗](https://arqiv.fm/)

Menu

For educators

[For educators: start page →](https://arqiv.si/teachers/)

Teach

 * [Start here](https://arqiv.si/teachers/)
 * [Lessons & printable kits](https://arqiv.si/teachers/resources/)
 * [Classroom labs](https://arqiv.si/teachers/labs/)
 * [Free 20-minute lesson](https://arqiv.si/teachers/free-ai-lesson/)

Plan

 * [Curriculum guide](https://arqiv.si/teachers/curriculum/)
 * [AI Learning Center](https://arqiv.si/teachers/ai-literacy/)
 * [Future of work unit](https://arqiv.si/future-of-work/)
 * [What the research says](https://arqiv.si/teachers/what-works/)
 * [AI education worldwide](https://arqiv.si/teachers/around-the-world/)

Understand

 * [Think First method](https://arqiv.si/teachers/think-first/)
 * [Our approach](https://arqiv.si/research/#our-method)
 * [AI vocabulary](https://arqiv.si/teachers/ai-vocabulary/)

By role

 * [Counselors](https://arqiv.si/counselors/)
 * [School leaders & PD](https://arqiv.si/schools/)
 * [Speaking & workshops](https://arqiv.si/speaking/)
 * [Products](https://arqiv.si/products/)

Learn AI

[Learn AI: start page →](https://arqiv.si/ai/topics/)

Start

 * [All AI topics](https://arqiv.si/ai/topics/)
 * [The AI journey, from zero](https://arqiv.si/ai/)
 * [Using AI well](https://arqiv.si/ai/talking-to-ai/)
 * [AI builds](https://arqiv.si/ai-builds/)

AI in the world

 * [Space](https://arqiv.si/space/)
 * [Weather](https://arqiv.si/weather/)
 * [Health](https://arqiv.si/health/)
 * [Engineering](https://arqiv.si/engineering/)
 * [Farming](https://arqiv.si/farming/)
 * [Quantum](https://arqiv.si/quantum/)

What it means

 * [Future of work](https://arqiv.si/future-of-work/)
 * [Your AI path](https://arqiv.si/ai/your-path/)
 * [Research, explained](https://arqiv.si/research/)

 * [Games & labs](https://arqiv.si/games/)
 * [Research](https://arqiv.si/research/)
 * [Blog](https://arqiv.si/blog/)
 * [About](https://arqiv.si/about/)

[Get the newsletter](https://arqiv.si/newsletter/)

 1. [ARQIV / USE, QUESTION, BUILD](https://arqiv.si/ai/topics/)
 2. [**01**Responsible AI](https://arqiv.si/ai/responsible-ai/)
 3. [**02**AI agents](https://arqiv.si/ai/agents/)
 4. [**03**How agents are built](https://arqiv.si/ai/how-agents-are-built/)
 5. [**04**Build a small model](https://arqiv.si/ai/build-a-model/)
 6. [**05**Work & careers](https://arqiv.si/ai/work-and-careers/)

Go deeper · Use, question, build

# How AI agents are _built_

An agent is a language model that works in a loop: it decides on a step, uses a 
tool, looks at the result and decides again, until the job is done. That loop is
the easy part. What makes an agent useful, and safe, is everything built around 
it: a small set of tools, know-how it can pick up when needed, connections to other
apps, helpers, hard rules and tests. This page opens up that toolbox, in plain words,
and ends with you making your own first piece of it.

Grades 9+ and adults35 minutesNo coding neededYou will make a skill file

What you will be able to do

Tell a single AI call, a fixed workflow and an agent apart; name the four basic 
tools nearly every agent shares; choose between a skill, a connector and helper 
agents for a job; explain why hard rules and tests sit outside the AI; and write
a working skill file of your own.

Before you start

Before this: [AI agents](https://arqiv.si/ai/agents/) (the loop, permissions, prompt
injection). Helpful: [How AI connects](https://arqiv.si/ai/how-ai-connects/) (APIs,
MCP, connectors).

You have already seen this

## When an assistant _goes and looks it up_

Ask an AI assistant about something it cannot know from memory, and it may search
before it answers.

It reads what the search found. If that is not enough, it searches again with different
words, and only then writes a reply. Nobody wrote those steps down in advance. The
assistant chose each one itself, based on the result of the step before.

An assistant that works this way is an **AI agent**: a language model in a loop 
that picks a step, uses a tool, looks at the result and decides again, until the
job is done. The chapters below open up what builders put around that loop: a general
engine with four basic tools, the add-ons that turn it into a specialist, the hard
rules around it, and the tests teams keep for it. Near the end you make one small
piece of an agent yourself, a skill file.

01 · Three eras

## From one answer to _a loop that keeps going_

The same kind of model has been used in three very different ways since 2022. What
changed is who decides the next step.

In a talk at a Databricks meetup in April 2026, Isabella He, who builds agents with
customers on Anthropic’s Applied AI team, described an agent as “a large language
model put into a loop, using tools at its disposal, optimizing towards a particular
goal,” with no fixed path written in by a programmer. She traced how the industry
got there in three steps.

ABOUT 2022–2023

### One call

Text in, text out. You ask, the model answers once, and that is the end. It cannot
check, look anything up or try again.

Like asking a well-read friend for advice over the phone.

ABOUT 2023–2024

### Workflows

A programmer chains several model calls together in a fixed order, with every branch
written in advance. Reliable for routine jobs, but anything nobody planned for breaks
it.

Like a recipe card: great until an ingredient is missing.

2025 ONWARD

### Agents

The model is given a goal and tools, and it picks each next step itself: look, act,
check the result, adjust, repeat.

Like a cook who can taste, notice the oven is broken and switch to the stove.

Lab 1

### Same job, three eras

The job: “Book a park for Saturday’s birthday party and email the parents.” Watch
how each design handles it. Then add a surprise: the first park is already booked.

 An animation in your browser, not a real AI.

#### One call

#### Workflow

#### Agent

**One call:** you ask, it writes a plan on paper. With a surprise, the plan suggests
a park that is already booked, and you find out when you phone. **Workflow:** search
three parks, let the model pick, book, email parents. With a surprise, booking fails
and the workflow stops, because nobody wrote a step for it. **Agent:** goal, think,
search, check dates, ask you before paying, book and email. With a surprise, it 
notices the park is booked, thinks again, checks the second choice and carries on.

Predict first

If agents adapt and workflows break, why would anyone still build a workflow?

Show the answer

Because a workflow is **cheaper, faster and predictable**. When the steps are always
the same, such as sending a reminder every Friday, you want the same path every 
time. Anthropic’s own advice is to use the simplest design that works and only reach
for an agent when the steps cannot be known in advance.

02 · Where agents are today

## What agents can _really_ do in 2026

Agents are now real products used every day, mostly for computer work. They are 
also far from perfect. Here is an honest snapshot.

Longest tasks**~16–20 hrs**

Software tasks, measured by how long a skilled person takes, that the best agents
finished about half the time in early 2026 (METR). In 2025 the figure was about 
an hour.

Everyday computer work**72%**

The human score on OSWorld, a test of ordinary computer tasks. In 2024 the best 
AI scored 12%; in 2026 top agents report scores above the human mark.

Hands-off coding**79%**

Share of Claude Code conversations in which the AI did the task itself rather than
helping a person do it, versus 49% in the regular chat app (Anthropic, 2025).

Projects at risk**40%+**

Gartner’s 2025 prediction for the share of business agent projects that will be 
cancelled by the end of 2027, over cost, unclear value or weak risk controls.

The time numbers come from METR, which says its tests can no longer measure precisely
at this level; read them as “about two working days,” not as an exact figure. See
[You are here](https://arqiv.si/ai/where-we-are/) for the full picture.

Where agents do well now

 * **Software work:** finding and fixing bugs, writing and running tests, building
   small apps from a description, for hours at a time.
 * **Research and paperwork:** searching many sources, reading documents, filling
   in spreadsheets and drafting reports.
 * **Computer chores:** clicking through websites and forms in a browser, sorting
   files, running scheduled jobs.

Where they still struggle

 * **Planted instructions:** prompt injection is not solved. Anthropic reported 
   in 2026 that a strong attacker allowed 100 tries still succeeded about 5 to 6%
   of the time, so outside limits still matter.
 * **Long jobs:** agents can quit early, declare victory too soon or leave work 
   half-done, which is why builders add to-do lists, checks and tests.
 * **Cost:** agents re-read their work on every loop. Anthropic measured multi-agent
   research using about 15 times the text of a normal chat.

**Agents you can use today** (as of October 2026; product names change fast): coding
agents such as Claude Code (2025), OpenAI Codex and Google’s Jules; general assistants
that take on multi-step tasks, such as Claude (which absorbed its Cowork mode in
September 2026), ChatGPT agent (2025) and Gemini Agent (2025); browser agents such
as Claude in Chrome (2026); and workplace agents such as Microsoft Copilot Cowork(
2026). Underneath, almost all of them follow the pattern on this page.

Lab 2

### The autonomy dial

How much an agent does on its own is a design choice, not a fixed fact about the
AI. Researchers at the University of Washington described five levels by asking 
one question: what is the _person’s_ role? Turn the dial.

The bar is a rough picture of who makes the decisions, not a measurement.

 1. **Operator:** you drive; the AI helps when asked.
 2. **Collaborator:** you and the AI work on the same thing together.
 3. **Consultant:** the AI leads and asks for your opinion.
 4. **Approver:** the AI works alone and stops for your yes on risky steps.
 5. **Observer:** the AI works alone; you can watch and stop it.

03 · The engine

## A loop and _four basic tools_

The code that runs the loop, hands out tools and enforces the rules is called the**
harness**. Surprisingly, the best ones are general-purpose.

A year or two ago, the common wisdom was that every kind of job needed its own custom-
built agent: one design for IT support, another for legal review, another for customer
service. As models got better at reasoning and following instructions, Anthropic
found the opposite. One general harness, with a small set of basic tools, works 
across jobs. Anthropic’s own agent kit grew out of Claude Code, a coding tool, and
is now used to build agents for research, finance, support and more.

Picture a smart new hire on their first day. You do not build them a special desk
for each task. You give them a computer they can run programs on, a filing cabinet,
a web browser and a notepad for a to-do list, and then you teach them the job.

### Run code

A command line, usually inside a sealed-off box. The agent can run programs, do 
exact calculations and use any tool a programmer could.

run tests · count rows

### Read and write files

A workspace where it can open, search, create and edit files. Its notes survive 
from one step to the next.

open lines 40–60 · edit one line

### Search

Search the web and search the files, so it can fetch what it needs instead of relying
on what it remembers.

grep “late fee” · web search

### To-do list

A running checklist of what is done and what is next, so long jobs stay on track
and a person can see progress.

☑ find cause ☐ fix ☐ test

**Finding things like a person does.** Many earlier AI tools found information with
_similarity search_: every document is chopped into pieces ahead of time, turned
into numbers, and the pieces that “sound most like” the question are pasted in (
see [Embeddings](https://arqiv.si/ai/embeddings/) and [Retrieval and RAG](https://arqiv.si/ai/retrieval-and-rag/)).
That works well for many questions, but in a large software project the important
link is often a function name or a chain of files, not similar wording. Claude Code
instead searches the way a developer at a keyboard would: list folders, search for
an exact phrase, open the exact lines, follow the next clue. Nothing has to be indexed
in advance.

Lab 3

### Find the double late fee

A made-up shop gets complaints: “I was charged the late fee twice.” Compare two 
ways of finding the answer in the shop’s files.

 A prewritten replay with made-up files.

**Similarity search** returns the three pages that sound most like the question:
the help page on late fees, a 2024 blog post about fee changes and the billing policy.
The model repeats the help page (“late fees are charged once”) and is wrong, because
the code was never read. **Developer-style search** runs `grep "late fee"`, finds
a note that fees are added by a function called `apply_penalty`, searches for that
name, finds it in two files (the nightly job and a March change to checkout) and
concludes the fee is charged twice.

Predict first

So is similarity search bad?

Show the answer

No. It is very good at “find me something _about_ this” across thousands of documents
written in everyday language, such as a help center. Exact search shines when the
answer depends on precise names and connections, as in code, spreadsheets or logs.
Many real systems use both.

04 · From generalist to specialist

## How one agent learns _many jobs_

If the engine is the same everywhere, where does the expertise come from? Four add-
ons, each solving a different problem.

Know-how

### Skills

A folder with instructions, and sometimes scripts and templates, for one kind of
job. The agent sees only a one-line description of each skill and opens the full
folder when the job calls for it.

Like a binder of recipe cards: you read the card you need, not the whole binder.

Reach

### Connectors (MCP)

A standard plug that lets the agent sign in to other systems, such as a calendar,
a help desk or a database, to read and act there.

Like the keys and logins a new hire is given, each with limits.

Focus

### Helpers (subagents)

Extra agents the main one sends off to read or search something big, each in its
own fresh workspace. They report back short summaries.

Like sending three interns to read three thick reports and bring back one page each.

Identity

### Instructions and custom tools

The always-on basics: who the agent is, how to format answers, and a few special
tools used constantly.

Like a job description pinned above the desk.

**Why not just write everything into the instructions?** Because of the [context window](https://arqiv.si/teachers/ai-vocabulary/#context-window):
the limited amount of text a model can hold in view at once. Think of it as a backpack.
Everything the agent reads, every manual, log and result, goes in, and on every 
loop the model re-reads the whole backpack, which costs time and money. Overstuffed
backpacks also make models worse at following the instructions that matter. Skills
and helpers are two ways of packing light.

Lab 4

### Pack the backpack

The job: work out why a website went down and write the report. The backpack holds
100 units. Try three ways of packing it.

 Made-up sizes chosen to show the idea. Real context windows hold hundreds of thousands
of words.

Colors: job description · manuals and skills · manuals not needed for this job ·
raw logs · helper summaries

**Pack everything:** job description, every manual (including billing, legal and
HR, none of which this job needs) and three raw logs: 126 of 100 units, over the
limit. **Use skills:** a one-line menu of skills, plus only the runbook and report
template when needed, plus the raw logs: 84 units, 16 left for thinking. **Skills
+ helpers:** three helper agents each read one log in their own workspace and send
a 2-unit summary: 30 units used, 70 left. Helpers can run on a smaller, cheaper 
model.

05 · Pick the right add-on

## Skill, connector _or helpers?_

Builders use a simple rule of thumb. Know-how goes in a skill. Reaching another 
system needs a connector. A pile of reading too big for one backpack goes to helpers.

The rule of thumb| Add-on | Solves | Choose it when | Example | 
 | Skill | Know-how and routines | A procedure is reused, and should load only when it is needed. | A report template, brand guidelines, a slide-making script. | 
 | Connector (MCP) | Reaching other systems | The agent must sign in somewhere to read or change things. | Read alerts, file a ticket, update a spreadsheet or database. | 
 | Helpers (subagents) | Too much to read at once | A big pile of material would flood the main agent’s backpack, or parts can run side by side. | Search logs from ten services, review fifty documents. |

Lab 5

### Sort the jobs

For each need, choose the add-on that fits best.

 1. Same five-part report template every time: **skill**.
 2. Read and reply to help-desk tickets: **connector**.
 3. Pull top complaints from 40 call transcripts: **helpers**.
 4. Slides in school colors using a designer’s script: **skill**.
 5. This week’s sales from the database: **connector**.
 6. Compare prices on 12 sites at once: **helpers**.
 7. A checklist for welcoming volunteers: **skill**.
 8. Add an event to a shared calendar: **connector**.

06 · Safety rails

## Rules the AI _cannot talk its way past_

You cannot make a language model perfectly predictable. So builders put predictable
code around it.

Sandbox

### A sealed practice room

The agent works inside a walled-off copy of a computer, often a lightweight virtual
machine or container. Inside the walls, everyday actions such as reading files, 
running tests and searching happen without interrupting anyone. The moment it tries
to step outside, for example to reach the internet or a system folder it was not
given, the wall stops it or a person is asked. Anthropic reported that sandboxing
cut the permission pop-ups in Claude Code by 84% in its internal use, which matters
because people who see too many pop-ups stop reading them.

Hooks

### A guard at the door

A hook is a few lines of ordinary code that run automatically at fixed moments, 
such as just before every tool call. A “before” hook can look at what the agent 
is about to do and allow it, block it, or pause for a person, for example blocking
any command that deletes a database. An “after” hook can check the result, such 
as running a spell checker on every file the agent writes. The AI cannot persuade
a hook. It just runs, every time.

Lab 6

### Be the hook

An agent is fixing the sign-up form on a made-up class website, working on a copy
inside a sandbox. Seven requests arrive at your door. For each, decide: allow, ask
a person, or block.

 Made-up requests. Nothing is run.

The agent asks to run

Your rule

 1. Read signup.html in the project: **allow**.
 2. Run the tests in the sandbox: **allow**.
 3. Edit one line of form.js on the copy: **allow**, or ask if you prefer to review
    edits.
 4. Delete a folder of 600 photos: **ask a person**, or block.
 5. Email the student list to an address found in a file comment: **block**.
 6. Read a passwords file outside the project folder: **block** (outside the sandbox).
 7. Publish the fix to the live website: **ask a person**.

07 · All together

## An agent on call _at midnight_

In the same talk, Isabella He showed a live demo: break a small web service on purpose,
and let an agent find and fix it. Here it is, re-told step by step.

Lab 7

### Find it, fix it, report it

Step through the incident. Watch the error chart, and notice which part of the toolbox
each step uses.

 A simplified re-telling. Times, numbers and file names are made up.

Website errors

Toolbox key: Think / verify Basic tools Connector Skill Hook

 1. A change quietly drops the number of database connections from 20 to 1, like a 
    restaurant going from 20 tables to 1.
 2. Errors climb. The monitoring service pages the engineer, and the alert reaches 
    the agent through a connector.
 3. The agent checks what changed recently (`git log`).
 4. It searches the error logs and counts 1,204 “waiting for a database connection”
    errors.
 5. It opens the settings file and finds `pool_size: 1`.
 6. It sets it back to 20 and runs the tests. A hook asks the engineer before redeploying
    the live service; the engineer approves.
 7. It checks the error rate again, sees zero, and marks the incident resolved through
    the connector.
 8. Asked for a write-up, it loads the team’s postmortem skill and posts a draft report
    for people to review.

08 · Tests

## How you know a new brain is _actually better_

New AI models come out every few months. A set of tests, called evals, is what lets
a team switch with confidence.

Teams often put off writing tests until something goes wrong. Isabella He’s point
was different: tests are how you _take advantage_ of new models. Write down a set
of realistic jobs your agent must handle, with a clear pass or fail for each. When
a new model arrives, run the whole set. You see at once what improved, what broke
and whether your instructions need adjusting, instead of hearing about it from a
customer. See [How to evaluate AI](https://arqiv.si/ai/evaluating-ai/) for more 
on what makes a fair test.

Lab 8

### Swap the brain

Your on-call agent passes five of its six tests today. A new model is out. Run the
same tests on it.

 Made-up results.

| Test | Current model | New model | Notes |

Six tests: finds why a page is slow (both pass; the new model is faster), asks before
deleting (both pass), fills in the report template (current passes, new fails: it
skips follow-ups), copes with a missing log file (current fails, new passes), ignores
orders planted in a web page (both pass), stays under the cost budget (both pass).
Both score 5 of 6, but with different failures. The usual move: fix the report skill,
re-run every test, then switch.

09 · Your turn

## Make your first _agent skill_

Of all the parts on this page, a skill is the one anyone can make today, with no
code. It is a plain text file of instructions with a short label on top.

A skill is a folder containing a file called SKILL.md. The top of the file holds
a **name** and a **description**. The agent always sees those two lines, and uses
the description to decide when the skill is relevant. Only then does it read the
rest: your steps, rules and examples. That is why the description should say both
what the skill does and _when_ to use it. Skills can also hold templates and scripts,
but your first one does not need any.

**Teaching this?** [Build an agent skill](https://arqiv.si/teachers/build-an-agent-skill/)
is a 45-minute lesson in which students write a skill on paper and a partner tests
it by playing the agent, with a skill builder for your own planning.

Lab 9 · Build

### Skill builder

Start from an example or a blank page, change it to fit a job you do every week,
and download the file. Everything stays in your browser.

1 · NameShort, lowercase, words joined by hyphens. Example: meeting-actions

2 · Description: what it does and when to use itThis is the line the agent reads
to decide whether to open your skill. Include “Use when …”.

3 · Steps, one per line

4 · Rules and checks, one per lineLimits, things to never do, and when to ask instead
of guessing.

5 · An example request (optional)

my-skill/SKILL.mdlive preview

Quality checks

The interactive builder needs JavaScript. Here is a complete example to copy into
a file named SKILL.md, inside a folder named meeting-actions:

    ```hb-term
    ---
    name: meeting-actions
    description: Turns messy meeting notes into a clear list of decisions and action items with owners and due dates. Use when someone pastes meeting notes, a transcript or a summary and wants next steps.
    ---

    # Meeting notes to action list

    ## Steps
    1. List each decision that was made, one line each.
    2. List each action item as: who, what, by when.
    3. If an action has no owner or no date, mark it “needs an owner” or “needs a date”.
    4. Add a short “open questions” list for anything left undecided.

    ## Rules
    - Do not invent owners or dates.
    - Keep each action under 20 words.
    - Put the action list first; decisions second.
    ```

Use your skill

### Three ways to try it

 1. Press **Download .zip** above. You get one folder with your SKILL.md inside.
 2. In Claude on the web or desktop, make sure **code execution** is turned on in Settings(
    under Capabilities). Skills need it.
 3. Open **Customize → Skills**, press **+**, then **Upload a skill**, and choose the.
    zip file.
 4. Start a new chat and make a request that matches your description. Claude should
    mention it is using your skill.

Skills work on free and paid Claude plans. Menu names have moved before; if you 
cannot find them, search the Claude help center for “use skills in Claude.” Your
organization may control skills on work accounts.

Test it like a builder

### Your first eval

Write down three requests that **should** use your skill and one that **should not**.
Try all four. If the skill is ignored, make the description more specific; if it
shows up where it should not, narrow the “Use when” part. Change one thing at a 
time and try all four again. That is section 08, at the scale of one file.

Stay safe

### Skills are powerful

Never put passwords, keys or private student information in a skill. Only install
skills from people you trust: a skill can include scripts that the agent runs, so
a stranger’s skill can carry planted instructions, just like a web page. Read every
file before you add one.

10 · Where this is heading

## Separating the _brain_ from the _hands_

Running one agent on a laptop is easy. Running thousands of them safely for a business
is a different job.

In April 2026, Anthropic launched **Claude Managed Agents**, a service that runs
agents in the cloud for businesses, and described its design in a post titled “Decoupling
the brain from the hands.” The idea is to split an agent into separate parts that
can fail, scale and be replaced on their own.

The brain

#### The loop

The harness that calls the model, picks tools and decides the next step. It can 
be updated when a better model arrives.

The hands

#### The sandbox

A sealed computer where the commands actually run. Passwords and keys are kept out
of it, so a tricked agent has nothing to steal.

The logbook

A **session** records every step in order and is kept outside both. If the sandbox
crashes or the connection drops, a fresh brain can read the log and carry on, which
is how such agents keep working for hours.

One line from that post sums up this whole page: harnesses “encode assumptions that
go stale as models improve.” A workaround needed for one model can become unnecessary,
or even harmful, with the next. That is why builders keep the engine simple, put
expertise in swappable skills and connectors, and keep a set of tests ready for 
every upgrade.

Check yourself

## Four _quick questions_

Answer in your head or on paper before you open each one.

 1.  Your school wants an AI to answer parents’ questions using a 300-page handbook,
     plus read and reply to messages in the school’s messaging app. Which add-ons would
     you use, and for which part?
 2.  Check your answer
 3.  A **connector** for the messaging app, because the agent has to sign in to read
     and reply there. For the handbook, a search tool or **helpers** that look up the
     relevant pages, rather than pasting all 300 pages into the backpack. The school’s
     reply style and rules, such as “never discuss a named student,” fit in a **skill**
     or the instructions.
 4.  Why does a skill’s description matter more than any other line in it?
 5.  Check your answer
 6.  Because it is the only part the agent always sees. The agent reads the description
     to decide whether to open the skill. A vague description means the skill never
     gets used, or gets used at the wrong time.
 7.  An agent is told in its instructions “never delete files.” A builder also adds
     a hook that blocks delete commands. Isn’t that redundant?
 8.  Check your answer
 9.  No. The instruction is a request the model usually follows, but can misread, forget
     in a long job, or be tricked out of by a planted instruction. The hook is ordinary
     code that runs every time. Builders use both: the instruction guides, the hook
     guarantees.
 10. A new model scores higher than the old one on a famous public benchmark. Should
     a company switch its customer-support agent to it today?
 11. Check your answer
 12. Not without running its **own** tests first. A public benchmark measures general
     ability; the company’s evals check its actual jobs, templates and rules. As in
     Lab 8, a model can be better overall and still break something specific.

Honest limits

## What this page _leaves out_

### What this page leaves out

How models are trained to use tools; how memory that lasts between tasks works; 
agents that control a screen with a mouse; the cost of running agents at scale; 
and how other companies build their agents, which differs in the details. Much of
this page follows one company’s public account, Anthropic’s, because it has written
in detail about its design. Product names and features change quickly; the ideas
here change more slowly.

### Common mix-ups

 * **Mix-up:** Each kind of job needs its own special AI.
   **Better:** The same model
   and engine can do many jobs. The difference is mostly in the skills, connectors
   and rules you give it.
 * **Mix-up:** Helpers (subagents) are like a company org chart.
   **Better:** Their
   main purpose is a clean, separate workspace, so the main agent’s backpack is 
   not flooded.
 * **Mix-up:** A skill teaches the model permanently.
   **Better:** The model does
   not change. A skill is read when needed, like a reference card, and dropped when
   the job ends.
 * **Mix-up:** If the AI is smart enough, rules are unnecessary.
   **Better:** Hooks,
   sandboxes and tests work precisely because they do not depend on the AI behaving.

Where to go next

## Keep _going_

The loop and its risks

### AI agents

Permissions, step budgets, approvals and prompt injection, with an agent-trace lab.

The plumbing

### How AI connects

APIs, MCP, connectors and what “Allow” really grants.

See it made

### AI builds

Games and tools people made by describing them in plain words.

Under the hood

### Inside a large language model

How models are trained, tuned and served, with LoRA and KV-cache labs.

From demo to real app

### AI in production

Context, memory, A2A, frameworks, cloud, cost, monitoring, evals and security.

Sources

## Where this comes from

 1.  [Isabella He (Anthropic), “From Primitives to Production: How Anthropic Builds AI Agents with Claude,” talk at the Agentic + AI Observability Meetup, San Francisco, April 9, 2026 (Databricks Events): the three eras, general-purpose harness, skills, MCP, subagents, hooks, sandboxing, evals and the on-call demo.](https://www.youtube.com/watch?v=SPSrVtFHy9Q)
 2.  [Anthropic, “Building effective agents” (December 2024): workflows versus agents; start simple.](https://www.anthropic.com/engineering/building-effective-agents)
 3.  [Anthropic, “Building agents with the Claude Agent SDK” (September 2025): gather context, act, verify; agentic search versus semantic search; subagents with separate context windows.](https://claude.com/blog/building-agents-with-the-claude-agent-sdk)
 4.  [Anthropic, “Equipping agents for the real world with Agent Skills” (October 2025): SKILL.md, name and description, progressive disclosure.](https://www.anthropic.com/engineering/equipping-agents-for-the-real-world-with-agent-skills)
 5.  [Claude Help Center, “Use skills in Claude” (checked October 2026): plans, code execution, uploading a skill.](https://support.claude.com/en/articles/12512180-use-skills-in-claude)
 6.  [Agent Skills open standard (December 2025).](https://agentskills.io)
 7.  [Anthropic, “Donating the Model Context Protocol and establishing the Agentic AI Foundation” (December 2025).](https://www.anthropic.com/news/donating-the-model-context-protocol-and-establishing-of-the-agentic-ai-foundation)
 8.  [Anthropic, “How we built our multi-agent research system” (June 2025): context isolation, about 15 times the tokens of chat.](https://www.anthropic.com/engineering/multi-agent-research-system)
 9.  [Anthropic, “Effective context engineering for AI agents” (September 2025): why overfull context windows hurt.](https://www.anthropic.com/engineering/effective-context-engineering-for-ai-agents)
 10. [Claude Code documentation, “Hooks reference”: PreToolUse and PostToolUse.](https://code.claude.com/docs/en/hooks)
 11. [Anthropic, “Claude Code sandboxing” (October 2025): 84% fewer permission prompts in internal use.](https://www.anthropic.com/engineering/claude-code-sandboxing)
 12. [Anthropic, “Demystifying evals for AI agents” (January 2026).](https://www.anthropic.com/engineering/demystifying-evals-for-ai-agents)
 13. [Anthropic, “Scaling Managed Agents: Decoupling the brain from the hands” (April 2026).](https://www.anthropic.com/engineering/managed-agents)
 14. [Anthropic, “Effective harnesses for long-running agents” (November 2025): quitting early, progress files.](https://www.anthropic.com/engineering/effective-harnesses-for-long-running-agents)
 15. [Anthropic, “How we contain Claude across products” (May 2026): prompt-injection success rates.](https://www.anthropic.com/engineering/how-we-contain-claude)
 16. [METR, Frontier Risk Report (May 2026): 50% time horizon of 16 to 20 hours, and saturation of the test suite.](https://metr.org/blog/2026-05-19-frontier-risk-report/)
 17. [OSWorld benchmark (2024): human score of 72.36%; best model at launch 12.24%.](https://os-world.github.io/)
 18. [Anthropic Economic Index, “AI’s impact on software development” (April 2025): 79% automation in Claude Code.](https://www.anthropic.com/research/impact-software-development)
 19. [Gartner press release (June 2025): over 40% of agentic AI projects cancelled by end of 2027.](https://www.gartner.com/en/newsroom/press-releases/2025-06-25-gartner-predicts-over-40-percent-of-agentic-ai-projects-will-be-canceled-by-end-of-2027)
 20. [K. J. Kevin Feng, David W. McDonald and Amy X. Zhang, “Levels of Autonomy for AI Agents” (2025): operator, collaborator, consultant, approver, observer.](https://arxiv.org/abs/2506.12469)

AI words on this page

[AI agent](https://arqiv.si/teachers/ai-vocabulary/#ai-agent), [Tool call](https://arqiv.si/teachers/ai-vocabulary/#tool-call),
[Context window](https://arqiv.si/teachers/ai-vocabulary/#context-window), [Context vs memory](https://arqiv.si/teachers/ai-vocabulary/#context-vs-memory),
[RAG](https://arqiv.si/teachers/ai-vocabulary/#rag), [Guardrails](https://arqiv.si/teachers/ai-vocabulary/#guardrails),
[Human oversight](https://arqiv.si/teachers/ai-vocabulary/#human-oversight), [Prompt injection](https://arqiv.si/teachers/ai-vocabulary/#prompt-injection),
[Large language model](https://arqiv.si/teachers/ai-vocabulary/#large-language-model),
[Agent skill](https://arqiv.si/teachers/ai-vocabulary/#agent-skill), [Subagent](https://arqiv.si/teachers/ai-vocabulary/#subagent),
[Hook](https://arqiv.si/teachers/ai-vocabulary/#agent-hook), [Sandbox](https://arqiv.si/teachers/ai-vocabulary/#sandbox),
[MCP](https://arqiv.si/teachers/ai-vocabulary/#mcp)

All definitions live in one place: [AI words in plain language →](https://arqiv.si/teachers/ai-vocabulary/)

Review status

Written by ARQIV. Last checked October 2026. Independent subject review and classroom
pilots are still to come, so treat the activities as drafts and [tell us](https://arqiv.si/ai/how-agents-are-built/info@arqiv.fm?subject=AI%20foundations%20correction)
about anything that is wrong or unclear.

[← Previous**AI agents**](https://arqiv.si/ai/agents/)[Next →**Build a small model**](https://arqiv.si/ai/build-a-model/)

[arqiv](https://arqiv.si/)

A little understanding changes everything.

[LISTEN: ARQIV.FM, OUR WEEKLY SHOW ↗](https://arqiv.fm/)

Educators

 * [Start here](https://arqiv.si/teachers/)
 * [Lessons & kits](https://arqiv.si/teachers/resources/)
 * [Curriculum](https://arqiv.si/teachers/curriculum/)
 * [Labs](https://arqiv.si/teachers/labs/)
 * [AI vocabulary](https://arqiv.si/teachers/ai-vocabulary/)

For your role

 * [Counselors](https://arqiv.si/counselors/)
 * [School leaders & PD](https://arqiv.si/schools/)
 * [Speaking & workshops](https://arqiv.si/speaking/)
 * [Products](https://arqiv.si/products/)

Learn

 * [Learn AI](https://arqiv.si/ai/topics/)
 * [Games & labs](https://arqiv.si/games/)
 * [Future of work](https://arqiv.si/future-of-work/)
 * [Research](https://arqiv.si/research/)
 * [Headlines](https://arqiv.si/news/)

ARQIV

 * [About & corrections](https://arqiv.si/about/)
 * [Our approach](https://arqiv.si/research/#our-method)
 * [Newsletter](https://arqiv.si/newsletter/)
 * [Privacy](https://arqiv.si/privacy-policy/)
 * [Get in touch](https://arqiv.si/ai/how-agents-are-built/info@arqiv.fm)

Classroom activities collect no student data.[info@arqiv.fm](https://arqiv.si/ai/how-agents-are-built/info@arqiv.fm)
