Agentic Software Development: Two-Week Online Course

A two-week online course on developing software with coding agents such as Claude Code, taught on Smarter, a code base shaped for agents, with six 30-minute recorded lectures and a 90-minute live session each week. Week 1 covers how agents work and how to delegate and review, and week 2 covers instructions, safety and responsibility. See Course Formats and Grading for the format, the grading scale and the course policies, and Agentic Software Development with Claude Code for an overview of the subject.

At a Glance

Students

Software developers who write Python or JavaScript.

Deployment

Each student runs Smarter from source, with a fork on GitHub and a coding agent installed, before Live session 1.

Workload

3 hours of instruction and 4 to 6 hours of assignments each week.

Cost

A coding agent subscription or API usage for each student, plus small model charges from Smarter’s tests.

Learning Objectives

By the end of the course, students can:

  1. Explain how coding agents work, and what makes a code base agent-friendly.

  2. Delegate broad, bounded tasks with clear acceptance criteria.

  3. Review agent-written code and tests critically, and verify them independently.

  4. Write instructions and skills that improve an agent’s results, and measure the effect.

  5. Work safely with agents, and take responsibility for what they produce.

Technical Prerequisites

  • Required: Python or JavaScript, well enough to review a pull request.

  • Required: Git and GitHub, including code review.

  • Required: the command line, and Docker basics.

  • Required before Live session 1: Smarter installed from source, and a coding agent working in the repository.

  • Required: basic generative AI concepts: prompts, context windows and tool calls.

  • Helpful: automated testing, and Markdown.

Schedule

Week

Item

Content

1

Lecture 1 (30 min)

What a coding agent is. A model in a loop with tools, context and permissions.

1

Lecture 2 (30 min)

How you ask. Outcomes, evidence, acceptance criteria and the pattern-first workflow. Agentic Development.

1

Lecture 3 (30 min)

Reviewing agent code. Weakened tests, swallowed errors, invented APIs, and verifying independently.

1

Live session 1 (90 min)

The instructor delegates a task live and reviews the result with the class. Pairs then delegate one of their own. Start Assignment 1.

2

Lecture 4 (30 min)

Instructions and skills. CLAUDE.md, Agent Skills, and how Smarter’s skills grew.

2

Lecture 5 (30 min)

Safety. Permissions, sandboxes, live credentials, secrets and prompt injection through files.

2

Lecture 6 (30 min)

Responsibility. Authorship, attribution, licenses, and the changing developer role.

2

Live session 2 (90 min)

Capstone presentations (about 5 minutes each, with 2 minutes of questions).

Assignment 1 is due at the end of week 1, Assignment 2 in the middle of week 2, and Assignment 3 and the capstone at the start of Live session 2.

Graded Assignments

Assignment 1: Delegation and Review

Students delegate a broad, bounded change to the agent, and review the resulting pull request as a colleague’s.

Turn in: the request, the pull request against their fork, and a review of at least five comments with test and hook results.

Criterion

Pts

Exemplary

Developing

Request

4

Outcome and acceptance criteria.

Steps or vague.

Review

8

Substantive.

“Looks good”.

Verification

5

Run by the student.

Agent’s word.

Honesty

3

Problems reported.

Omitted.

Assignment 2: The Bug Hunt

The instructor provides three agent-written pull requests, each with a planted problem (a weakened assertion, a swallowed exception, an invented function). Students find and explain each problem, and write the test that would have caught it.

Turn in: a short report for each pull request, and the tests.

Criterion

Pts

Exemplary

Developing

Problems found

8

All three.

One.

Explanation

6

Why it is wrong and what it would cause.

Named only.

Tests

6

Fail on the planted problem, pass when fixed.

Missing or ineffective.

Assignment 3: With and Without Skills

Students compare the agent’s work on the same task with and without the skills.

Turn in: both diffs and a one-page comparison.

Criterion

Pts

Exemplary

Developing

Fair comparison

5

Same task and model, fresh context.

Uncontrolled.

Criteria

6

Correctness, patterns, tests and time.

One.

Analysis

6

Linked to skill content.

Describes only.

Conclusion

3

Honest.

Assumed.

Capstone Projects

Students choose one, and present it in Live session 2.

Capstone A: A Feature Built with an Agent

Learning objective. Deliver a real feature with a coding agent while remaining its accountable author.

Students build a feature in their fork with an agent, keep a session log, and must be able to explain every line.

What students turn in:

  • A pull request with code, tests and docs, passing tests and hooks.

  • The request, acceptance criteria and session log.

  • A one-page reflection, and a five-minute presentation with live questions on the diff.

How it is graded (100 points):

Criterion

Pts

Exemplary

Developing

Working feature

20

Correct, tested, documented.

Partly working.

Specification

15

Clear criteria.

Vague.

Review and intervention

20

Problems caught and corrected.

Accepted everything.

Understanding

30

Explains any line when asked.

Cannot explain key parts.

Reflection

15

Specific and honest.

Generic.

Capstone B: A Skill That Works

Learning objective. Improve an agent’s results by writing instructions, and prove the improvement.

Students write a skill for a recurring mistake, and run three tasks with and without it.

What students turn in:

  • The skill, following skills/README.md.

  • Tasks, results and scores.

  • A two-page report, and a five-minute presentation.

How it is graded (100 points):

Criterion

Pts

Exemplary

Developing

Problem

15

Real and recurring.

Hypothetical.

Skill quality

25

Concise, specific, clear trigger.

Long and generic.

Experiment

25

Controlled, three tasks.

Uncontrolled.

Results

20

Honest.

Cherry-picked.

Report and presentation

15

Explains why.

Results only.

Further Study

  • Documentation: the Claude Code documentation, including its pages on memory (CLAUDE.md), skills, hooks and subagents, and the open Agent Skills format.

  • Essays: Anthropic’s Building effective agents, and its engineering blog’s posts on agentic coding best practices and context engineering.

  • Research: METR’s study Measuring the Impact of Early-2025 AI on Experienced Open-Source Developer Productivity (2025), a randomized trial whose results surprised its authors, and a good starting point for a discussion of how to measure productivity honestly.

  • YouTube: Andrej Karpathy’s talk Software Is Changing (Again) (Y Combinator AI Startup School, 2025), and the talks on coding agents on the AI Engineer channel.

  • Podcasts: Latent Space, and The Pragmatic Engineer podcast and newsletter by Gergely Orosz, which reports on how engineering teams actually use AI.

  • Writing: Simon Willison’s weblog, which documents his own use of coding agents in detail, and the essays on blog.smarter.sh about building Smarter with agents.