Why this playbook

One model is often enough. When mistakes are costly, a measured second pass can be worth it.

This is a hands-on playbook for orchestrating several AI agents — a builder that drafts, a separately prompted reviewer whose performance you measure, task-specific routing, and source-aware research checks. Written for solo founders and indie developers who already work with an agent like Claude Code, Codex CLI or Cursor and want a coordinated setup without a machine-learning background or unnecessary complexity. A second model is an option, not a universal requirement.

What is inside

Ten chapters, dated and sourced

01Why more than one agent

The principle, a maturity ladder, and an honest account of when one model is enough.

02The 2026 model landscape

Claude, GPT, Gemini and Grok as flagship / balanced / cheap-fast tiers, with dated, provider-accurate prices.

03Open & self-hosted models

Llama, Qwen, DeepSeek, Mistral, gpt-oss: a decision tree for when local is genuinely worth it.

04Orchestration patterns

Reviewer, planner-executor, router, ensemble, debate, pipeline, orchestrator-worker — what each is for, and what it costs.

05The reviewer pattern, hands-on

Builder + independent read-only reviewer, step by step, including conflict resolution.

06Tooling & orchestration stack

Claude Code subagents, Codex CLI, LangGraph, CrewAI, AutoGen, Google ADK, PydanticAI and more — without over-engineering.

07Deep research in your workflow

How agentic research works, which tools fit, and how to verify it before you build on it.

08Cost & quality

A cost model, an interactive calculator, and evaluation-led recipes per task type.

09Safety, security & governance

Prompt injection between agents, least privilege, and human-in-the-loop gates.

10Start now

Five copy-paste prompts — and a defensive security-check prompt you run first.

Also included

A working kit, not just prose

Interactive cost calculator

Estimate what your multi-agent setup actually costs — offline, in your browser.

Model-selection matrix (XLSX)

Compare tiers and pick per task, not per fashion.

Setup checklist (XLSX)

The orchestration rollout, step by step.

Full prompt pack (.md)

Planning, setup, review, deep research — plus the security-check prompt.

Everything works offline. No tracking, no external dependencies. The print edition is a 66-page tagged PDF.

Before you buy

An honest promise

What this guide will not tell you

A separate review pass can reduce missed errors when the exact builder-reviewer pairing performs well on representative evaluations; it can also miss defects or add false positives. This guide gives you a method and a dated snapshot, not a guarantee.

Verify current model names, capabilities and prices on the provider’s official page before relying on them. All figures are current as of July 2026 and traceable to the providers’ own documentation.

Fit check

Who it’s for

Built for you if…

you already work with an AI agent (Claude Code, Codex CLI, Cursor…)
you want a second model to catch what the first one misses
you decide with evaluations and cost figures, not vibes
you are a solo founder or indie developer — no ML background needed

Skip it if…

you are looking for “10x your output overnight” promises
you have never used an AI coding or writing agent
you need enterprise MLOps or fine-tuning guidance

Part of a practical series

ENThe AI-First Operating Playbook

The business-wide operating system this deep dive plugs into. €39

DEDas KI-First-Betriebs-Playbook

Die deutsche Ausgabe des AI-First-Playbooks. €39

StoreAll guides →

Kleingewerbe guides (DE + EN), AI-first operations, and this playbook — the full store.

Links open in a new tab.

Get the playbook

Orchestrating AI Agents

Reviewer patterns · routing · research verification · cost control. Dated 2026 figures. No hype.

I want this — €39

Instant download via Gumroad · PDF + offline HTML bundle + 2 XLSX workbooks + prompt pack · Single-user licence