PHHM Journal • Production AI Series

Engineering essays on production AI

A fifteen-part series on building multi-agent AI systems that survive production — from architecture and APIs through guardrails, observability, cost engineering, and the war stories in between. Best read in order.

Part 1 • Start here

Building a Multi-Agent AI Orchestration Layer in Python

Lessons from six collaborating agents — how PHHM reduced workflow time by 85% and errors by 73% with specialist agents, central orchestration, and shared workflow state.

Read the article →
Focus
Architecture
Read time
20 min
Series
PHHM Journal
Theme
Production AI
Part 2Production APIs14 min

Building Production AI APIs with FastAPI

Why AI APIs are orchestration, not CRUD — a single workflow endpoint, Pydantic validation at the boundary, and keeping FastAPI thin while the orchestrator does the thinking.

Read more →
Part 3Configuration8 min

Configuration-Driven AI: Why YAML Beats Hardcoded Prompts in Production

How PHHM adds new agents, models, prompts, and workflows without rewriting application code — configuration changes behavior, not code structure.

Read more →
Part 4State14 min

State Management for Multi-Agent AI

Workflow state is not shared memory. Every execution owns structured context that survives retries and agent handoffs, so the platform behaves like one system.

Read more →
Part 5Prompt Versioning15 min

Prompt Versioning at Scale

Prompts are deployable software assets — semantic versions, workflow mapping, regression tests, and rollbacks that make prompt changes boring instead of risky.

Read more →
Part 6Guardrails10 min

Guardrails for Multi-Agent AI Systems

Treat every AI response as untrusted input. Schema validation protects the software, business rules protect the meaning, and recovery paths keep failures contained.

Read more →
Part 7Observability14 min

Observability for Multi-Agent AI Systems

You can't debug what you can't see — correlation IDs, structured logs, distributed traces, workflow metrics, and audit trails that make AI systems explain themselves.

Read more →
Part 8Evaluation12 min

Evaluation and Regression Testing for AI Workflows

Stop testing prompts in isolation. Golden datasets, behavioral assertions, and CI/CD evaluation gates that prove the workflow still works before every deploy.

Read more →
Part 9Security10 min

Securing Multi-Agent AI Systems

Prompt injection isn't the root problem — trust boundaries are. Why the model sits outside the trusted core and never decides what the platform does.

Read more →
Part 10Frameworks10 min

Why We Didn't Use LangChain in Production (And What We Built Instead)

Evaluating LangChain, CrewAI, and AutoGen taught us an important lesson — use frameworks for capabilities, but own the architecture that differentiates your platform.

Read more →
Part 11Refactoring11 min

From Monolith to Multi-Agent: The Refactoring We Should Have Done Earlier

Simplicity has a hidden expiration date. How PHHM outgrew its single-agent design and rebuilt into six specialists without breaking production.

Read more →
Part 12Post-Mortem14 min

The Production Incident That Changed How We Deploy AI Prompts

No alert fired. Nothing crashed. A post-mortem on the single sentence that quietly degraded our Care Agent — and how the telemetry found it.

Read more →
Part 13Testing10 min

Testing AI Systems Without Calling a Single LLM

Thousands of regression tests in CI/CD with a zero-pound API bill — mockable interfaces, dependency injection, golden responses, and deterministic workflows.

Read more →
Part 14Cost • Measure13 min

Cost Engineering for Production AI — Part 1: Measure

You can't optimize costs you don't measure. Cost per workflow, token accounting, and why context — not model pricing — is usually the biggest expense.

Read more →
Part 15Cost • Optimize10 min

The Cost of Production AI — Part 2: Optimize

The cheapest AI call is the one you never make — prompt compression, intelligent routing, caching, and parallel execution that made PHHM economically sustainable.

Read more →