AI Engineering: Agents and Applications › Full-Stack AI Applications › Day 316
Hands-on lab — Day 316: Architecture of an AI Product
- ← Back to the Day 316 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-316-architecture-of-an-ai-product/
Commands
Setup
pip install -r requirements/requirements.txt Run
python examples/product_dispatcher.py Test
bash tests/run_tests.sh File tree
examples/product_dispatcher.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/product_dispatcher.py tests/run_tests.sh tests/test_product_dispatcher.py troubleshooting.md
Lab README
Day 316 Lab: Architecture of an AI Product
Lesson
- Lesson title: Architecture of an AI Product
- Day number: 316 of 365
- Lesson article: https://ai-roadmap-365.github.io/day-316-architecture-of-an-ai-product
- 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-316-architecture-of-an-ai-productwhen the site is running.
Purpose
Build a Full-Stack AI Product Architecture Dispatcher in Python that integrates authentication, token-bucket rate limiting, credit quota gating, semantic caching, and streaming token delivery.
Learning objectives
- Implement multi-tenant authentication and quota verification.
- Enforce token-bucket rate limits per organization.
- Manage response caching for identical queries.
- Execute simulated token streaming with accurate credit deductions.
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/product_dispatcher.py: Starter implementation skeletonexamples/product_dispatcher.py: Verified reference implementationtests/test_product_dispatcher.py: Test suiteexpected-output/: Captured execution logs
How to run
python3 examples/product_dispatcher.py
What the commands do
- Executes request dispatch across authentication, rate limiting, caching, and generation.
Expected output
Org Alpha: {'status': 'SUCCESS', 'tokens_streamed': ['This', ' is', ' a', ' streamed', ' AI', ' response.'], 'response': 'This is a streamed AI response.', 'cost_usd': 0.002, 'cached': False, 'remaining_credits': 49.998}
Validation steps
Run test runner:
bash tests/run_tests.sh
Tests
The test suite validates:
- Valid tenant authentication and request dispatch
- Rejection on invalid tenant ID
- Rejection on rate limit exhaustion
- Rejection on zero credit balance
- Zero-cost delivery on cached query hits
Cleanup
rm -rf .pytest_cache __pycache__ .venv
Troubleshooting
Ensure credit balance deductions occur only on successful model executions.
Security notes
Runs completely offline on local CPU.
Extension exercises
Add multi-provider fallback routing when primary mock fails.
Navigation
Day number: 316 of 365
Expected output
FIELDS.md
# Measured Values
- `dispatched_requests`: 10
- `cached_requests`: 1
examples-run.txt
Org Alpha: {'status': 'SUCCESS', 'tokens_streamed': ['This', ' is', ' a', ' streamed', ' AI', ' response.'], 'response': 'This is a streamed AI response.', 'cost_usd': 0.002, 'cached': False, 'remaining_credits': 49.998}
measured-values.txt
dispatched_requests=10
cached_requests=1
run-output.txt
Org Alpha: {'status': 'SUCCESS', 'tokens_streamed': ['This', ' is', ' a', ' streamed', ' AI', ' response.'], 'response': 'This is a streamed AI response.', 'cost_usd': 0.002, 'cached': False, 'remaining_credits': 49.998}
starter-run.txt
An untouched starter fails the suite. Captured from a real run:
self = <examples.product_dispatcher.AIProductDispatcher object at 0x1069ca520>
tenant_id = 'org_gamma', prompt = 'Q1'
def dispatch_chat(self, tenant_id: str, prompt: str) -> Dict[str, Any]:
> raise NotImplementedError('TASK 2: implement dispatch_chat.')
E NotImplementedError: TASK 2: implement dispatch_chat.
examples/product_dispatcher.py:22: NotImplementedError
=========================== short test summary info ============================
FAILED tests/test_product_dispatcher.py::test_valid_dispatch_and_credit_deduction
FAILED tests/test_product_dispatcher.py::test_cached_query_zero_cost - NotImp...
FAILED tests/test_product_dispatcher.py::test_unauthorized_tenant - NotImplem...
FAILED tests/test_product_dispatcher.py::test_zero_credit_rejection - NotImpl...
FAILED tests/test_product_dispatcher.py::test_rate_limit_rejection - NotImple...
============================== 5 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-316-architecture-of-an-ai-product
plugins: cov-7.1.0, anyio-4.14.2
collecting ... collected 5 items
tests/test_product_dispatcher.py::test_valid_dispatch_and_credit_deduction PASSED [ 20%]
tests/test_product_dispatcher.py::test_cached_query_zero_cost PASSED [ 40%]
tests/test_product_dispatcher.py::test_unauthorized_tenant PASSED [ 60%]
tests/test_product_dispatcher.py::test_zero_credit_rejection PASSED [ 80%]
tests/test_product_dispatcher.py::test_rate_limit_rejection PASSED [100%]
============================== 5 passed in 0.01s ===============================
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-316-architecture-of-an-ai-product
plugins: cov-7.1.0, anyio-4.14.2
collecting ... collected 5 items
tests/test_product_dispatcher.py::test_valid_dispatch_and_credit_deduction PASSED [ 20%]
tests/test_product_dispatcher.py::test_cached_query_zero_cost PASSED [ 40%]
tests/test_product_dispatcher.py::test_unauthorized_tenant PASSED [ 60%]
tests/test_product_dispatcher.py::test_zero_credit_rejection PASSED [ 80%]
tests/test_product_dispatcher.py::test_rate_limit_rejection PASSED [100%]
============================== 5 passed in 0.01s ===============================
Source files
examples/product_dispatcher.py (2630 bytes)
import time
import json
from typing import Dict, Any, Tuple, List, Optional
class AIProductDispatcher:
def __init__(self):
self.tenants: Dict[str, Dict[str, Any]] = {
"org_alpha": {"credits": 50.0, "rate_limit_per_min": 60, "requests_this_min": 0, "last_reset": time.time()},
"org_beta": {"credits": 0.0, "rate_limit_per_min": 10, "requests_this_min": 0, "last_reset": time.time()},
"org_gamma": {"credits": 10.0, "rate_limit_per_min": 2, "requests_this_min": 0, "last_reset": time.time()}
}
self.cache: Dict[str, str] = {}
def authenticate_and_gate(self, tenant_id: str) -> Tuple[bool, str]:
if tenant_id not in self.tenants:
return False, "Unauthorized: Invalid Tenant ID"
tenant = self.tenants[tenant_id]
now = time.time()
if now - tenant["last_reset"] > 60:
tenant["requests_this_min"] = 0
tenant["last_reset"] = now
if tenant["requests_this_min"] >= tenant["rate_limit_per_min"]:
return False, "Too Many Requests: Rate limit exceeded"
if tenant["credits"] <= 0.0:
return False, "Payment Required: Zero credit balance"
tenant["requests_this_min"] += 1
return True, "OK"
def dispatch_chat(self, tenant_id: str, prompt: str) -> Dict[str, Any]:
auth_ok, msg = self.authenticate_and_gate(tenant_id)
if not auth_ok:
return {"status": "ERROR", "error_code": msg, "tokens_streamed": []}
cache_key = f"{tenant_id}:{prompt.strip().lower()}"
if cache_key in self.cache:
return {
"status": "CACHED",
"response": self.cache[cache_key],
"cost_usd": 0.0,
"cached": True,
"remaining_credits": round(self.tenants[tenant_id]["credits"], 4)
}
mock_tokens = ["This", " is", " a", " streamed", " AI", " response."]
full_response = "".join(mock_tokens)
self.tenants[tenant_id]["credits"] -= 0.002
self.cache[cache_key] = full_response
return {
"status": "SUCCESS",
"tokens_streamed": mock_tokens,
"response": full_response,
"cost_usd": 0.002,
"cached": False,
"remaining_credits": round(self.tenants[tenant_id]["credits"], 4)
}
if __name__ == "__main__":
dispatcher = AIProductDispatcher()
print("Org Alpha:", dispatcher.dispatch_chat("org_alpha", "Hello"))
metadata.yml (405 bytes)
lesson_id: D316
day: 316
kind: python
languages:
- python
setup_commands:
- pip install -r requirements/requirements.txt
run_commands:
- python examples/product_dispatcher.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/product_dispatcher.py (1258 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 time
import json
from typing import Dict, Any, Tuple, List, Optional
class AIProductDispatcher:
def __init__(self):
self.tenants: Dict[str, Dict[str, Any]] = {'org_alpha': {'credits': 50.0, 'rate_limit_per_min': 60, 'requests_this_min': 0, 'last_reset': time.time()}, 'org_beta': {'credits': 0.0, 'rate_limit_per_min': 10, 'requests_this_min': 0, 'last_reset': time.time()}, 'org_gamma': {'credits': 10.0, 'rate_limit_per_min': 2, 'requests_this_min': 0, 'last_reset': time.time()}}
self.cache: Dict[str, str] = {}
def authenticate_and_gate(self, tenant_id: str) -> Tuple[bool, str]:
raise NotImplementedError('TASK 1: implement authenticate_and_gate.')
def dispatch_chat(self, tenant_id: str, prompt: str) -> Dict[str, Any]:
raise NotImplementedError('TASK 2: implement dispatch_chat.')
if __name__ == '__main__':
dispatcher = AIProductDispatcher()
print('Org Alpha:', dispatcher.dispatch_chat('org_alpha', 'Hello'))
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_product_dispatcher.py (1651 bytes)
import pytest
from examples.product_dispatcher import AIProductDispatcher
def test_valid_dispatch_and_credit_deduction():
dispatcher = AIProductDispatcher()
res = dispatcher.dispatch_chat("org_alpha", "Tell me a joke")
assert res["status"] == "SUCCESS"
assert len(res["tokens_streamed"]) > 0
assert res["cached"] is False
assert res["remaining_credits"] == 49.998
def test_cached_query_zero_cost():
dispatcher = AIProductDispatcher()
res1 = dispatcher.dispatch_chat("org_alpha", "Summarize article")
res2 = dispatcher.dispatch_chat("org_alpha", "Summarize article")
assert res2["status"] == "CACHED"
assert res2["cached"] is True
assert res2["cost_usd"] == 0.0
assert res2["remaining_credits"] == 49.998
def test_unauthorized_tenant():
dispatcher = AIProductDispatcher()
res = dispatcher.dispatch_chat("org_unknown", "Hello")
assert res["status"] == "ERROR"
assert "Unauthorized" in res["error_code"]
def test_zero_credit_rejection():
dispatcher = AIProductDispatcher()
res = dispatcher.dispatch_chat("org_beta", "Generate report")
assert res["status"] == "ERROR"
assert "Payment Required" in res["error_code"]
def test_rate_limit_rejection():
dispatcher = AIProductDispatcher()
# org_gamma has limit of 2 requests/min
res1 = dispatcher.dispatch_chat("org_gamma", "Q1")
res2 = dispatcher.dispatch_chat("org_gamma", "Q2")
res3 = dispatcher.dispatch_chat("org_gamma", "Q3")
assert res1["status"] == "SUCCESS"
assert res2["status"] == "SUCCESS"
assert res3["status"] == "ERROR"
assert "Rate limit exceeded" in res3["error_code"]