Skip to content
Agentic Software Engineering: Build, Verify, Evaluate
Public files
Initializing search
Home
Course
Start here
Weeks
Earlier materials
Practice and project
Policies
Reference
Agentic Software Engineering: Build, Verify, Evaluate
Home
Course
Course
How this course works
Syllabus
Schedule
Help with setup and learning
Start here
Start here
Set up for the course
From a plausible answer to checked work
Fallback checklist
Weeks
Weeks
Week 1: The internals of coding agents
Week 1: The internals of coding agents
Week 1 overview
Week 1 guide
Week 1 notes
Week 1 slides
Week 1 activities
Week 1 readings
Week 1 self-check
Week 1 self-check answers
Week 2: Advanced context engineering
Week 2: Advanced context engineering
Week 2 overview
Week 2 guide
Week 2 notes
Week 2 slides
Week 2 activities
Week 2 readings
Week 2 self-check
Week 2 self-check answers
Dissect a recorded agent session
Compare two production prompts
Week 3: Agent skills and the CLI
Week 3: Agent skills and the CLI
Week 3 overview
Week 3 guide
Week 3 notes
Week 3 slides
Week 3 activities
Week 3 readings
Week 3 self-check
Week 3 self-check answers
Week 4: Customizing your agent and repository
Week 4: Customizing your agent and repository
Week 4 overview
Week 4 guide
Week 4 notes
Week 4 slides
Week 4 activities
Week 4 readings
Week 4 self-check
Week 4 self-check answers
Week 5: Agent-ready codebases
Week 5: Agent-ready codebases
Week 5 overview
Week 5 guide
Week 5 notes
Week 5 slides
Week 5 activities
Week 5 readings
Week 5 self-check
Week 5 self-check answers
Week 6: Agentic code review
Week 6: Agentic code review
Week 6 overview
Week 6 guide
Week 6 notes
Week 6 slides
Week 6 activities
Week 6 readings
Week 6 self-check
Week 6 self-check answers
Week 7: Tests that notice a fault
Week 7: Tests that notice a fault
Week 7 overview
Week 7 guide
Week 7 notes
Week 7 slides
Week 7 activities
Week 7 readings
Week 7 self-check
Week 7 self-check answers
Week 8: Security
Week 8: Security
Week 8 overview
Week 8 guide
Week 8 notes
Week 8 slides
Week 8 activities
Week 8 readings
Week 8 self-check
Week 8 self-check answers
Public fixture
Week 9: Background agents
Week 9: Background agents
Week 9 overview
Week 9 guide
Week 9 notes
Week 9 slides
Week 9 activities
Week 9 readings
Week 9 self-check
Week 9 self-check answers
Week 10: Evaluating agents
Week 10: Evaluating agents
Week 10 overview
Week 10 guide
Week 10 notes
Week 10 slides
Week 10 activities
Week 10 readings
Week 10 self-check
Week 10 self-check answers
Public fixture
Week 11: Building an AI-native team
Week 11: Building an AI-native team
Week 11 overview
Week 11 guide
Week 11 notes
Week 11 slides
Week 11 activities
Week 11 readings
Week 11 self-check
Week 11 self-check answers
Team operation and incident practice fixtures
Week 12: The software factory and what comes next
Week 12: The software factory and what comes next
Week 12 overview
Week 12 guide
Week 12 notes
Week 12 slides
Week 12 activities
Week 12 readings
Week 12 self-check
Week 12 self-check answers
Public audit-verification fixture
Week 13: Assessment week
Week 13: Assessment week
Week 13 overview
Earlier materials
Earlier materials
Earlier course pages
Earlier course pages
Assessment and appeals
Assessment rubric
Capstone milestone rubric
Open-source contributions rubric
Project scoring and appeals
Check your starting point
Check the approved model route
GitHub assignment submission and public feedback
course_llm: generate once, then verify
Dashboard status demonstration
Earlier project materials
Earlier project materials
Read Trajectories Safely: Generate, Then Verify
Trajectory Anomaly Patterns: Generate, Detect, Explain, Verify
Clues Are Not Conclusions
Practice and project
Practice and project
Assignments A1–A6
Term project
A1
A1
A1: Read a coding-agent session
A2
A2
A2: Build a small MCP tool server
A3
A3
A3: Turn a manual workflow into a skill
A4
A4
A4: Make a messy repository agent-ready
A5
A5
A5: Score agent readiness from observations
A6
A6
A6: Audit an evaluation instance and scorer
Contributions
Contributions
Open-source contributions
Policies
Policies
Scoring rubrics
Reference
Reference
Course glossary
Lecture decks, week by week
Factsheets
Factsheets
SWE-bench: inputs and verification boundaries for one subset
Codex CLI: published base instructions and the update_plan tool schema at a pinned commit
Qwen Code: the system-prompt builder and the edit and todo_write tool schemas at a pinned tag
Templates
Templates
Decision log
AI-use note
Incident postmortem
Course project pull request template
Term project alpha and task backlog
Term project final checklist
Term project proposal
Term project technical specification
Reflection
Feature specification
Work record
Public files
demo.py
loop.py
verify_loop.py
Back to top