Complete for freeAdvancedBrowser simulator included

Course 24

Agentic Coding, MCP, and Tool-Using AI

Design and supervise coding-agent workflows with repository exploration, plans, diffs, tests, tool schemas, MCP, APIs, permissions, approvals, and defenses against prompt injection and untrusted output. The course combines structured lessons, guided browser concept simulations, and learner-created project files made with freely installable or open tools described in the course instructions. This guided page does not execute code, train models, run databases, create repositories, access hardware, or provide hosted infrastructure.

Free completion promise: The always-free pathway combines agent-workflow concept simulations with learner-created task, tool-schema, permission, diff-review, and evaluation files. The C4T page does not provide a repository, model, tools, or test runner; paid model access is optional.

Before you begin

Requirements & setup for Agentic Coding, MCP, and Tool-Using AI

Start with the complete free pathway below. Hardware, subscriptions, paid APIs, and cloud credits are never required.

Start here · free path

Your complete $0 setup

The always-free pathway combines agent-workflow concept simulations with learner-created task, tool-schema, permission, diff-review, and evaluation files. The C4T page does not provide a repository, model, tools, or test runner; paid model access is optional.

$0 required

Setup checklist

0 of 9 complete

This checklist is a temporary setup aid and resets when the page reloads. Saved course progress begins in the setup lessons below.

  1. Use the browser-based tools and simulations throughout this course. Paid software, APIs, cloud credits, GPUs, and physical equipment are optional.

    About 2 min

  2. Open the concept simulator and read its scenario, assumptions, and limitations.

    About 5 minOpen C4T Deterministic Agent Sandbox Concept Simulator (opens in a new tab)

  3. Make a prediction, adjust the available controls, and compare the result with the explanation.

    About 5 min

  4. Record what changed and why; repeat with at least one different input.

    About 5 min

  5. For applied work, follow the course instructions to create and keep your own project files with a freely installable or open tool appropriate to the subject.

    About 5 min

  6. Open C4T Deterministic Agent Sandbox Concept Simulator.

    About 5 minOpen C4T Deterministic Agent Sandbox Concept Simulator guided alternative (opens in a new tab)

  7. Choose the browser-based guided pathway.

    About 5 min

  8. Complete this check: Submit the learner-created file or documented design evidence requested by the assignment; the C4T page does not verify local execution.

    About 5 min

  9. C4T Deterministic Agent Sandbox Concept Simulator: Complete one prediction-and-explanation cycle and record the evidence you would carry into a learner-created project file. Optional local language model: Submit the learner-created file or documented design evidence requested by the assignment; the C4T page does not verify local execution.

    About 5 min

Software

2 items

C4T Deterministic Agent Sandbox Concept Simulator

A free browser concept simulator with adjustable values, a prediction prompt, deterministic feedback, and a short explanatory trace. This guided page does not execute code, train models, run databases, create repositories, access hardware, or provide hosted infrastructure.

Course need
C4T Deterministic Agent Sandbox Concept Simulator
Free

A free browser concept simulator with adjustable values, a prediction prompt, deterministic feedback, and a short explanatory trace. This guided page does not execute code, train models, run databases, create repositories, access hardware, or provide hosted infrastructure. Use keyboard controls and the text trace or written alternative when a visual or pointer interaction is not suitable.

  1. Open the concept simulator and read its scenario, assumptions, and limitations.
  2. Make a prediction, adjust the available controls, and compare the result with the explanation.
  3. Record what changed and why; repeat with at least one different input.
  4. For applied work, follow the course instructions to create and keep your own project files with a freely installable or open tool appropriate to the subject.
Open C4T Deterministic Agent Sandbox Concept Simulator (opens in a new tab)

No-hardware path

Deterministic Agent Sandbox Concept Simulator

Explore course concepts through adjustable values, prediction, deterministic feedback, and an explanatory trace. No hardware is required.

Optional paid alternatives

You do not need these options to complete the course.

Paid hosted model API

Optional provider comparison using the learner's own approved key; never required or stored by the course.

Optional only—never required for course completion.

Hosted coding-agent subscription

Optional interface comparison after completing the provider-independent sandbox workflow.

Optional only—never required for course completion.

Optional local language model

Optional learner-managed software for extending project files outside the guided concept simulator. It is not supplied, installed, connected, or run by this site.

Optional
C4T Deterministic Agent Sandbox Concept Simulator guided alternative
Free

Use the built-in guided concept lab; native installation is an optional extension. The simulator, supplied traces, and written tables cover the assessed concepts without handling physical parts.

  1. Open C4T Deterministic Agent Sandbox Concept Simulator.
  2. Choose the browser-based guided pathway.
  3. Complete this check: Submit the learner-created file or documented design evidence requested by the assignment; the C4T page does not verify local execution.
Open C4T Deterministic Agent Sandbox Concept Simulator guided alternative (opens in a new tab)

No-hardware path

Deterministic Agent Sandbox Concept Simulator

Explore course concepts through adjustable values, prediction, deterministic feedback, and an explanatory trace. No hardware is required.

Hardware

Nothing required

No physical hardware is needed for this course.

Accounts

Nothing required

No external account is needed for this course.

What you will be able to do

Learning outcomes

  • Distinguish assistant and autonomous behavior and write bounded engineering tasks.
  • Inspect repositories, critique plans and diffs, and require test evidence.
  • Design validated tools and understand MCP client-server boundaries.
  • Enforce permissions, approvals, and defenses against untrusted instructions and outputs.

Included downloads

Free starter assets

Original · synthetic · licensed

These small files contain no personal data, credentials, or secrets. Dataset fixtures are CC0 and starter code is MIT licensed.

Starter pack guide & licensesSee what each original synthetic dataset, fixture, and starter file contains.Bounded agent evaluation taskA fictional repository task with deterministic checks and no credentials.Recorded safe agent traceA simulated multi-agent trace that blocks an unsafe action.

Build real work

Assignments & capstone

Free tools accepted

Tool schema and approval design

Specify narrow coding-agent tools, permission boundaries, validation, approval points, and audit evidence.

The always-free pathway combines agent-workflow concept simulations with learner-created task, tool-schema, permission, diff-review, and evaluation files. The C4T page does not provide a repository, model, tools, or test runner; paid model access is optional. Submit a project file, text trace, screenshots with descriptions, or equivalent simulator evidence.

Adversarial diff-review exercise

Inspect a repository, critique a plan and diff, diagnose checks, and resist injected instructions in content and tool output.

The always-free pathway combines agent-workflow concept simulations with learner-created task, tool-schema, permission, diff-review, and evaluation files. The C4T page does not provide a repository, model, tools, or test runner; paid model access is optional. Submit a project file, text trace, screenshots with descriptions, or equivalent simulator evidence.

Final assessment

Safe sandboxed coding agent

Build or configure an agent that inspects a sandbox repository, plans, makes scoped edits, runs checks, reviews its diff, respects permissions, requires sensitive-action approval, handles untrusted content, and produces an auditable report. Deliverables: Bounded task and repository exploration, Scoped plan, edit, and diff evidence, Tests, lint, and type-check results, Permission and approval enforcement, and Injection handling and auditable final report.

Prerequisites & pacing

Skills assumed

  • Git collaboration, backend APIs, testing, and command-line development

Recommended prior courses

These are advisory, not locks. If you already have the skills listed above, enroll directly.

Choose your pace

  • self paced: 10 weeks at 5 hours per week
  • weekly: 10 weeks at 5 hours per week

Part of this learning path

  • 🛠️ Agentic Systems · step 4 of 5

    Build tool-using AI agents that are auditable, permission-bounded, and evaluated against adversaries.

Course created by Zafir Shamsi.