AASE AASEEECS 498 · Fall 2026

EECS 498-016 · Fall 2026 · University of Michigan

Applied Agentic Software Engineering

AASE · say it "A two S E"

One object, a coding agent, taken three ways across fifteen weeks. Use one to build one. Open real ones, Claude Code, Codex and Aider, and see how they work inside. Then build on them.

Read the syllabus FAQ
4 creditsTechnical elective
Tue + ThuLecture · 3:00 – 4:30
Mon or TueLab · 2-hour section
No examsProjects, labs, demos

01 The premise

The job is changing. The curriculum should too.

Software engineers increasingly direct systems that write code, instead of typing every line themselves. This course treats that work as an engineering discipline and teaches it like one: with theory, deliberate practice, instrumentation, and grading that rewards understanding over output.

You will spend the whole semester inside real tools. First you learn to drive a coding agent deliberately, and to diagnose failures using the Big Three: context, model, prompt. Then you open real harnesses and read how they work: how they load skills, guard against failure, reach the shell and the browser, hand work to subagents, keep a long conversation affordable, and remember what you told them. You extend your own copy of Aider toward an agent, and you build on Codex through its app-server.

Lectures run live demos. Labs are hands-on working sessions. Every project ships code that runs, and a design you can defend.

"The engineers we want to graduate can explain why an agent failed and fix the system around it."

02 Three phases

Drive one. Take real ones apart. Build on them.

Administrative · 10% Apply · 18% Analyze · 22.5% Create · 49.5%
01

Weeks 1–3, build into 6

Apply

Use Aider to specify and build a pair-programmer. Sixteen guided lessons come first. Then you design the architecture, write specs and diagrams, and implement all seven features plus YAML configuration from documentation and development tooling. Both design and working behavior are graded, including your tests.

  • 6 lectures (L01 to L06)
  • Tools: Aider, permitted models, compatible endpoints
  • Pair-programmer due Tue Oct 6
02

Weeks 4–7

Analyze

Open real coding agents and see what they rest on. Lectures take Claude Code, Codex and Aider apart one feature at a time: the API and the loop, skills, guardrails, the shell, MCP, the browser, subagents. Your project extends your own private copy of Aider toward an agent, and each part is designed with Elephant and Goldfish before it is built.

  • 8 lectures (L07 to L14)
  • Tools: Codex, your own copy of Aider
  • Project dates announced in class
03

Weeks 8–15

Create

The tour of harness features keeps going: compaction and prompt caching, memory, knowledge bases, and many models behind one harness. Then you build on an existing harness instead of writing your own loop. What you build in weeks 10 to 15 is announced in class.

  • 14 lectures (L15 to L28)
  • Individual, like every project here
  • Final format announced in class

Weights are locked. The three phases divide the 90% that is not administrative in the ratio 20 / 25 / 55, which is where 18 / 22.5 / 49.5 comes from. There are no exams. Full detail on the syllabus.

03 Outcomes

By December, you will be able to

  1. /01Drive a coding agent deliberately, and explain every line you hand in.
  2. /02Diagnose AI coding failures with the Big Three framework: context, model, prompt.
  3. /03Explain how a production coding agent works inside: the loop, tools, skills, approvals, context and caching, memory, and the model behind it.
  4. /04Change a large codebase you did not write, with a design that survives a fresh-context review, then build it with a coding agent.
  5. /05Treat the model as configuration, not a vendor, and serve your own.

04 The stack

Real tools, current versions

Everything runs on a normal laptop, and the course costs nothing beyond it. No textbook, no API bill, no subscription. In Apply you serve a small model yourself with Ollama, and if your laptop cannot carry it, CAEN does. From Lab03 you work with Codex on model credit the course provides.

aider ollama · qwen3.5 codex · gpt-6-luna python · pytest git + github prairielearn

05 Staff

Instructors

Marcus Darden

Marcus Darden

Instructor mmdarden@umich.edu
Rafe Symonds

Rafe Symonds

GSI rsymonds@umich.edu
Zilin Wang

Zilin Wang

GSI zilinwan@umich.edu

Rushil Kagithala

IA ksrushil@umich.edu

One address reaches all four: eecs-aase-staff@umich.edu

Office hours

Times and rooms live on the course calendar. Add it to yours so changes show up automatically.

View office hours Add to Google Calendar iCal feed (Apple, Outlook)

Fall 2026 is under way

The course began Aug 31, 2026. Enrolled students: the syllabus and schedule are the source of truth for dates and policy, and Ed is where we reach you.

Read the syllabus