MODULE 04 / 08

The Revenue Engine: Self-Optimizing Ad-Creative Agent

Build an autonomous LangGraph system that generates, audits, and self-corrects ad creatives against synthetic CTR rewards—closed-loop Generator→Critic→Prompt Refiner, Bayesian A/B simulation, Redis cache, and FastAPI serving tied to revenue metrics.

Multi-agent LangGraph orchestration: closed-loop Generator ↔ Critic with persistent state, synthetic CTR rewards, and Bayesian A/B launch selection.

LangGraphFastAPIRedisGPT-4o/Llama-3PostgreSQL

YOU'LL BUILD

A Self-Learning Digital Marketing Suite

Production goals

G01Connect Generative AI directly to business revenue metrics (ROI).
G02Implement a self-correcting data flywheel for automated creative iteration.
G03Achieve inference-time scaling via multi-agent adversarial debate.

You'll master techniques:

T01Multi-Agent Orchestration with LangGraph
T02Closed-loop feedback for continuous model improvement
T03Inference-time Scaling (System-2 Thinking)
T04Synthetic Reward Signals for CTR Simulation
T05Bayesian A/B Testing Simulator for prompt refinement

The Revenue Engine: Self-Optimizing Ad-Creative Agent

The Project Kit

The Closed-Loop Agent Graph

A modular Python codebase structured for revenue-facing creative optimization:

LangGraph Orchestration: Stateful Generator → Critic → Prompt Refiner loop with should_continue gates for inference-time System-2 iteration.
Synthetic CTR Rewards: Critic agent scores creatives against historical angle priors + business heuristics before media spend.
Bayesian A/B Simulator: Beta-binomial Thompson sampling to pick a launch winner from iterated candidates.
Prompt Lineage: Versioned prompt updates that encode critic feedback for continuous improvement.

The Full-Stack Serving Layer

An entire system to optimize campaigns and serve cached winners:

FastAPI Microservice: / /health /metadata /simulate POST /optimize with CORS and App Runner-ready Docker Compose.
Interactive Playground: Campaign brief → Generator/Critic loop UI with synthetic reward, workflow trace, and Bayesian A/B winner.
Redis Response Cache: TTL write-back for repeated campaign briefs (ElastiCache / local).
Postgres-Ready Lineage: Patterns for creative history, prompt versions, and campaign performance events.
Deploy Scripts: AWS App Runner helpers without rebuilding the image for every brief.

1curl -X POST http://127.0.0.1:8000/optimize -H "Content-Type: application/json" -d '{"product":"AI ad creative optimizer","audience":"B2B growth teams","offer":"Book a free CTR audit","iterations":3}'

Portfolio-Ready Documentation

README.md + TUTORIAL.md / TUTORIAL_FULL.md: System architecture + closed-loop pipeline diagrams and production goals designed for GitHub showcase.
Smoke Tests: Compile + route checks that assert a winning creative is returned.

1docker-compose up --build

Tutorial Summary

Tutorial: Building a Self-Optimizing Ad Creative API What We'll Build - The System Architecture Production Goals What You'll Master Essential Source Hooks Campaign Brief Generator Agent Critic Agent Prompt Refinement Bayesian A/B Simulation FastAPI Service Run the System Smoke Test

Tutorial: Building a Self-Optimizing Ad Creative API

What We'll Build - The System Architecture

In this project, we'll implement a self-correcting ad creative agent that generates campaign variants, audits them with a synthetic CTR reward signal, refines the prompt, and returns the best creative before media spend is committed.

You'll build a self-learning digital marketing suite using LangGraph, FastAPI, Redis, GPT-4o/Llama-3, and PostgreSQL production patterns.

The workflow begins when a marketer submits a campaign brief. The generator agent creates a candidate ad, the critic agent scores it against historical CTR patterns, and the prompt refiner updates the next generation instruction. After several iterations, a Bayesian A/B simulator estimates which creative should launch first.

Kernel Labs | Kuriko IWAI | kuriko-iwai.com

Figure A. System architecture — clients and growth tooling enter via gateway/LB; FastAPI serves /optimize and /simulate; LangGraph agents (Generator, Critic, Prompt Refiner, Bayesian A/B) talk to Redis, PostgreSQL, historical CTR priors, and optional LLM providers.

Kernel Labs | Kuriko IWAI | kuriko-iwai.com

Figure B. Closed-loop pipeline — campaign brief → FastAPI → generate/critique/refine loop → Bayesian A/B → winning creative.

Production Goals

Connect Generative AI directly to business revenue metrics (ROI).
Implement a self-correcting data flywheel for automated creative iteration.
Achieve inference-time scaling via multi-agent adversarial debate.

What You'll Master

Multi-Agent Orchestration with LangGraph
Closed-loop feedback for continuous model improvement
Inference-time Scaling (System-2 Thinking)
Synthetic Reward Signals for CTR Simulation
Bayesian A/B Testing Simulator for prompt refinement

Essential Source Hooks

1LangGraph orchestration: build_langgraph_workflow in src/workflow.py
2Generator/Critic/Refiner: src/agents.py
3Prompt construction: src/prompts.py
4Synthetic reward: synthetic_reward_signal in src/agents.py
5Bayesian A/B test: bayesian_ab_test in src/agents.py
6

The core loop is intentionally small:

1while True:
2    state = generator_agent(state)
3    state = critic_agent(state)
4    if not should_continue(state):
5        break
6    state = prompt_refiner_agent(state)
7

Shipping AI Systems?

I help teams design and deploy scalable ML / RAG / LLM pipelines and MLOps infrastructure.

Or explore:

Dive deeper 👉 Research Archive
Learn by building 👉 AI Engineering Masterclass
Try it live 👉 Playground

Campaign Brief

The API accepts a structured brief:

1{
2  "product": "AI ad creative optimizer",
3  "audience": "B2B growth teams",
4  "offer": "Book a free CTR audit",
5  "channel": "social",
6  "iterations": 3
7}
8

The core engine converts the request into a CampaignBrief, which carries the product, audience, offer, objective, voice, constraints, and historical performance data.

Generator Agent

The generator chooses an ad angle from historical winners, then creates a candidate headline, body, and call to action. In a production build, this node is where GPT-4o, Llama-3, or another model would generate richer variants.

1candidate = CreativeCandidate(
2    headline=f"{headline_seed}: {brief.product}",
3    body=f"{body_seed} {brief.offer} for {brief.audience}.",
4    call_to_action="Optimize my ads",
5    angle=angle,
6    prompt_version=prompt_version,
7)
8

Critic Agent

The critic produces a synthetic reward signal. It combines historical CTR for the selected angle with simple business heuristics such as offer strength, ROI language, clarity, and constraint penalties.

1reward = predicted_ctr * 1000
2

This gives the system a measurable optimization target before real campaign data arrives.

If the reward is below the configured target, the refiner updates the prompt with the critic's feedback. This creates an inference-time feedback loop: generate, audit, debate the angle, adjust, and generate again.

1Generator -> Critic -> Prompt Refiner -> Generator
2

Shipping AI Systems?

I help teams design and deploy scalable ML / RAG / LLM pipelines and MLOps infrastructure.

Or explore:

Dive deeper 👉 Research Archive
Learn by building 👉 AI Engineering Masterclass
Try it live 👉 Playground

Bayesian A/B Simulation

After candidate generation finishes, the system simulates an A/B test with a beta-binomial Thompson sample. The output includes observed clicks, impressions, posterior CTR samples, and a winning angle.

FastAPI Service

The serving layer exposes five endpoints:

1GET  /
2GET  /health
3GET  /metadata
4GET  /simulate
5POST /optimize
6

Repeated optimization requests can be cached in Redis for one hour.

Run the System

Install dependencies:

1uv sync
2

Start the API:

1uv run python app.py
2

Or start with Docker:

1docker-compose up --build
2

Run a simulation:

1curl "http://127.0.0.1:8000/simulate"
2

Smoke Test

Run:

1uv run bash scripts/test.sh
2

This compiles the Python files, verifies API routes, and checks that the optimization loop returns a winning creative.

Get the entire package with bash scripts 👇

The Project Kit

The Closed-Loop Agent Graph

A modular Python codebase structured for revenue-facing creative optimization:

LangGraph Orchestration: Stateful Generator → Critic → Prompt Refiner loop with should_continue gates for inference-time System-2 iteration.
Synthetic CTR Rewards: Critic agent scores creatives against historical angle priors + business heuristics before media spend.
Bayesian A/B Simulator: Beta-binomial Thompson sampling to pick a launch winner from iterated candidates.
Prompt Lineage: Versioned prompt updates that encode critic feedback for continuous improvement.

The Full-Stack Serving Layer

An entire system to optimize campaigns and serve cached winners:

FastAPI Microservice: / /health /metadata /simulate POST /optimize with CORS and App Runner-ready Docker Compose.
Interactive Playground: Campaign brief → Generator/Critic loop UI with synthetic reward, workflow trace, and Bayesian A/B winner.
Redis Response Cache: TTL write-back for repeated campaign briefs (ElastiCache / local).
Postgres-Ready Lineage: Patterns for creative history, prompt versions, and campaign performance events.
Deploy Scripts: AWS App Runner helpers without rebuilding the image for every brief.

1curl -X POST http://127.0.0.1:8000/optimize -H "Content-Type: application/json" -d '{"product":"AI ad creative optimizer","audience":"B2B growth teams","offer":"Book a free CTR audit","iterations":3}'

Portfolio-Ready Documentation

README.md + TUTORIAL.md / TUTORIAL_FULL.md: System architecture + closed-loop pipeline diagrams and production goals designed for GitHub showcase.
Smoke Tests: Compile + route checks that assert a winning creative is returned.

1docker-compose up --build

The Revenue Engine: Self-Optimizing Ad-Creative Agent

Production goals

You'll master techniques:

The Project Kit

The Closed-Loop Agent Graph

The Full-Stack Serving Layer

Portfolio-Ready Documentation

Tutorial Summary

Table of Contents

Tutorial: Building a Self-Optimizing Ad Creative API

What We'll Build - The System Architecture

Production Goals

What You'll Master

Essential Source Hooks

Shipping AI Systems?

Campaign Brief

Generator Agent

Critic Agent

Prompt Refinement

Shipping AI Systems?

Bayesian A/B Simulation

FastAPI Service

Run the System

Smoke Test

Get the entire package with bash scripts 👇

The Project Kit

The Closed-Loop Agent Graph

The Full-Stack Serving Layer

Portfolio-Ready Documentation

Get the entire package with bash scripts 👇

Table of Contents

Tutorial: Building a Self-Optimizing Ad Creative API

What We'll Build - The System Architecture

Production Goals

What You'll Master

Essential Source Hooks

Shipping AI Systems?

Campaign Brief

Generator Agent

Critic Agent

Prompt Refinement

Shipping AI Systems?

Bayesian A/B Simulation

FastAPI Service

Run the System

Smoke Test