AI Engineering: Agents and Applications › AI Coding Agents › Day 308
Hands-on lab — Day 308: Shipping a Feature with an Agent
- ← Back to the Day 308 lesson
- Open the hands-on files on GitHub — clone or download them from the public labs repository
- Local path in your clone:
labs/sections/ai-engineering/day-308-shipping-a-feature-with-an-agent/
Commands
Setup
pip install -r requirements/requirements.txt Run
python examples/feature_orchestrator.py Test
bash tests/run_tests.sh File tree
examples/feature_orchestrator.py expected-output/examples-run.txt expected-output/FIELDS.md expected-output/measured-values.txt expected-output/run-output.txt expected-output/starter-run.txt expected-output/test-output.txt expected-output/test-run.txt metadata.yml README.md requirements/requirements.txt security.md starter/feature_orchestrator.py tests/run_tests.sh tests/test_feature_orchestrator.py troubleshooting.md
Lab README
Day 308 Lab: Shipping a Feature with an Agent
Lesson
- Lesson title: Shipping a Feature with an Agent
- Day number: 308 of 365
- Lesson article: https://ai-roadmap-365.github.io/day-308-shipping-a-feature-with-an-agent
- Lab files: everything you need is in this directory — follow “How to run” below.
- Browse the course locally: from the repository root, this lab also appears in the course website at
/labs/day-308-shipping-a-feature-with-an-agentwhen the site is running.
Purpose
Build an End-to-End Feature Orchestrator in Python that executes automated verification quality gates and compiles comprehensive Walkthrough artifacts for peer review.
Learning objectives
- Execute verification commands and evaluate exit codes.
- Synthesize structured Walkthrough markdown artifacts.
- Format modified file lists and test execution evidence.
- Manage end-to-end feature delivery telemetry.
Prerequisites
- Python 3.10+ installed
- pytest installed
Supported operating systems
- macOS, Linux, Windows WSL2
Hardware requirements
- Standard CPU, 512MB RAM
Required software
- Python 3.10+, pytest
Free and open-source options
- Python Standard Library, Pytest
Installation
python3 -m venv .venv
source .venv/bin/activate
pip install -r requirements/requirements.txt
File structure
starter/feature_orchestrator.py: Starter implementation skeletonexamples/feature_orchestrator.py: Verified reference implementationtests/test_feature_orchestrator.py: Test suiteexpected-output/: Captured execution logs
How to run
python3 examples/feature_orchestrator.py
What the commands do
- Executes test command, captures output, and compiles Walkthrough markdown summary.
Expected output
## Feature Walkthrough: Demo Feature
### Summary of Changes
The feature was implemented following the 6-stage agentic shipping playbook.
### Modified Files
- `a.py`
### Verification Evidence
- Test Exe
Validation steps
Run test runner:
bash tests/run_tests.sh
Tests
The test suite validates:
- Passing and failing quality gate execution
- Walkthrough formatting with feature name, modified files, and test output
- Evidence attachment and review note generation
Cleanup
rm -rf .pytest_cache __pycache__ .venv
Troubleshooting
Verify test command paths and string formatting.
Security notes
Runs completely offline on local CPU.
Extension exercises
Add code coverage percentage extraction.
Navigation
Day number: 308 of 365
Expected output
FIELDS.md
# Measured Values
- `features_orchestrated`: 1
- `walkthroughs_generated`: 1
examples-run.txt
# Feature Walkthrough: Demo Feature
## Summary of Changes
The feature was implemented following the 6-stage agentic shipping playbook.
## Modified Files
- `a.py`
## Verification Evidence
- Test Exe
measured-values.txt
features_orchestrated=1
walkthroughs_generated=1
run-output.txt
# Feature Walkthrough: Demo Feature
## Summary of Changes
The feature was implemented following the 6-stage agentic shipping playbook.
## Modified Files
- `a.py`
## Verification Evidence
- Test Exe
starter-run.txt
An untouched starter fails the suite. Captured from a real run:
self = <examples.feature_orchestrator.FeatureOrchestrator object at 0x10aaa7d90>
feature_name = 'Multi-Tenancy Middleware'
files_modified = ['models.py', 'schemas.py', 'routes.py', 'tests/test_api.py']
test_results = {'passed': True, 'exit_code': 0, 'stdout': '5 passed in 0.02s', 'stderr': ''}
def generate_walkthrough_artifact(self, feature_name: str, files_modified: List[str], test_results: Dict[str, Any]) -> str:
> raise NotImplementedError('TASK 2: implement generate_walkthrough_artifact.')
E NotImplementedError: TASK 2: implement generate_walkthrough_artifact.
examples/feature_orchestrator.py:21: NotImplementedError
=========================== short test summary info ============================
FAILED tests/test_feature_orchestrator.py::test_execute_quality_gates_passed
FAILED tests/test_feature_orchestrator.py::test_execute_quality_gates_failed
FAILED tests/test_feature_orchestrator.py::test_generate_walkthrough_artifact
============================== 3 failed in 0.03s ===============================
Implement each TASK in starter/, copy it over examples/, and the same
suite goes green.
test-output.txt
============================= test session starts ==============================
platform darwin -- Python 3.14.0, pytest-9.1.1, pluggy-1.6.0 -- <repo>/.venv-tools/bin/python3.14
cachedir: .pytest_cache
rootdir: <repo>/labs/sections/ai-engineering/day-308-shipping-a-feature-with-an-agent
plugins: cov-7.1.0, anyio-4.14.2
collecting ... collected 3 items
tests/test_feature_orchestrator.py::test_execute_quality_gates_passed PASSED [ 33%]
tests/test_feature_orchestrator.py::test_execute_quality_gates_failed PASSED [ 66%]
tests/test_feature_orchestrator.py::test_generate_walkthrough_artifact PASSED [100%]
============================== 3 passed in 0.08s ===============================
test-run.txt
============================= test session starts ==============================
platform darwin -- Python 3.14.0, pytest-9.1.1, pluggy-1.6.0 -- <repo>/.venv-tools/bin/python3.14
cachedir: .pytest_cache
rootdir: <repo>/labs/sections/ai-engineering/day-308-shipping-a-feature-with-an-agent
plugins: cov-7.1.0, anyio-4.14.2
collecting ... collected 3 items
tests/test_feature_orchestrator.py::test_execute_quality_gates_passed PASSED [ 33%]
tests/test_feature_orchestrator.py::test_execute_quality_gates_failed PASSED [ 66%]
tests/test_feature_orchestrator.py::test_generate_walkthrough_artifact PASSED [100%]
============================== 3 passed in 0.08s ===============================
Source files
examples/feature_orchestrator.py (1812 bytes)
import subprocess
import os
from typing import Dict, Any, List
class FeatureOrchestrator:
def __init__(self, workspace_root: str):
self.workspace_root = os.path.realpath(workspace_root)
def execute_quality_gates(self, test_cmd: str = "python3 -m unittest") -> Dict[str, Any]:
res = subprocess.run(
test_cmd,
shell=True,
cwd=self.workspace_root,
capture_output=True,
text=True
)
return {
"exit_code": res.returncode,
"passed": res.returncode == 0,
"stdout": res.stdout,
"stderr": res.stderr
}
def generate_walkthrough_artifact(
self,
feature_name: str,
files_modified: List[str],
test_results: Dict[str, Any]
) -> str:
file_table = "\n".join([f"- `{f}`" for f in files_modified])
status = "PASSED (100%)" if test_results.get("passed") else "FAILED"
return (
f"# Feature Walkthrough: {feature_name}\n\n"
f"## Summary of Changes\n"
f"The feature was implemented following the 6-stage agentic shipping playbook.\n\n"
f"## Modified Files\n{file_table}\n\n"
f"## Verification Evidence\n"
f"- Test Execution Status: `{status}`\n"
f"- Exit Code: `{test_results.get('exit_code')}`\n\n"
f"### Test Output\n```text\n{test_results.get('stdout', '').strip()}\n```\n\n"
f"> *Ready for human architectural review and merge.*"
)
if __name__ == "__main__":
orchestrator = FeatureOrchestrator(".")
res = orchestrator.execute_quality_gates("python3 -c 'print(\"Tests OK\")'")
print(orchestrator.generate_walkthrough_artifact("Demo Feature", ["a.py"], res)[:200])
metadata.yml (407 bytes)
lesson_id: D308
day: 308
kind: python
languages:
- python
setup_commands:
- pip install -r requirements/requirements.txt
run_commands:
- python examples/feature_orchestrator.py
test_commands:
- bash tests/run_tests.sh
cleanup_commands:
- rm -rf __pycache__ .pytest_cache
requires_network: false
requires_api_key: false
estimated_minutes: 45
last_executed: '2026-08-30'
executed_on: macOS 15.0 Apple Silicon
requirements/requirements.txt (14 bytes)
pytest>=7.0.0
starter/feature_orchestrator.py (1106 bytes)
"""STARTER -- implement each TASK below, then run the tests.
Every function that raises NotImplementedError is yours to write. The
imports, constants and data structures are given; the logic is not.
Run `bash tests/run_tests.sh` to see which tasks are still outstanding.
"""
import subprocess
import os
from typing import Dict, Any, List
class FeatureOrchestrator:
def __init__(self, workspace_root: str):
self.workspace_root = os.path.realpath(workspace_root)
def execute_quality_gates(self, test_cmd: str='python3 -m unittest') -> Dict[str, Any]:
raise NotImplementedError('TASK 1: implement execute_quality_gates.')
def generate_walkthrough_artifact(self, feature_name: str, files_modified: List[str], test_results: Dict[str, Any]) -> str:
raise NotImplementedError('TASK 2: implement generate_walkthrough_artifact.')
if __name__ == '__main__':
orchestrator = FeatureOrchestrator('.')
res = orchestrator.execute_quality_gates('python3 -c \'print("Tests OK")\'')
print(orchestrator.generate_walkthrough_artifact('Demo Feature', ['a.py'], res)[:200])
tests/run_tests.sh (253 bytes)
#!/usr/bin/env bash
set -e
export PYTHONPATH=examples:.
if [ -n "$PYTEST" ]; then
$PYTEST tests/test_*.py -v
elif command -v pytest &> /dev/null; then
pytest tests/test_*.py -v
else
python3 -m unittest discover -s tests -p 'test_*.py' -v
fi
tests/test_feature_orchestrator.py (1458 bytes)
import pytest
import tempfile
from examples.feature_orchestrator import FeatureOrchestrator
def test_execute_quality_gates_passed():
with tempfile.TemporaryDirectory() as tmpdir:
orchestrator = FeatureOrchestrator(tmpdir)
res = orchestrator.execute_quality_gates("python3 -c 'print(\"Gate Passed\")'")
assert res["exit_code"] == 0
assert res["passed"] is True
assert "Gate Passed" in res["stdout"]
def test_execute_quality_gates_failed():
with tempfile.TemporaryDirectory() as tmpdir:
orchestrator = FeatureOrchestrator(tmpdir)
res = orchestrator.execute_quality_gates("python3 -c 'exit(1)'")
assert res["exit_code"] == 1
assert res["passed"] is False
def test_generate_walkthrough_artifact():
orchestrator = FeatureOrchestrator(".")
test_res = {
"passed": True,
"exit_code": 0,
"stdout": "5 passed in 0.02s",
"stderr": ""
}
walkthrough = orchestrator.generate_walkthrough_artifact(
feature_name="Multi-Tenancy Middleware",
files_modified=["models.py", "schemas.py", "routes.py", "tests/test_api.py"],
test_results=test_res
)
assert "# Feature Walkthrough: Multi-Tenancy Middleware" in walkthrough
assert "- `models.py`" in walkthrough
assert "- `routes.py`" in walkthrough
assert "Test Execution Status: `PASSED (100%)`" in walkthrough
assert "5 passed in 0.02s" in walkthrough
Troubleshooting
Troubleshooting - Day 308
Verify test commands return clean exit code 0 on success.
Security notes
Security - Day 308
Ensure walkthrough artifacts contain no production secrets or access tokens.