Dargel Solutions

Products / Orchestrating AI Agents

Playbook · Published under Adrian Verdan · English

Orchestrating AI Agents

Learn when one model is enough and when an additional agent earns its place. A practical, dated playbook for designing and evaluating multi-agent workflows — with reviewer patterns, routing methods, research verification, cost controls and copy-paste prompts.

12.90 € excl. VAT

VAT depends on your country; the final price is shown at Gumroad checkout before purchase. Merchant of Record: Gumroad.

Buy on Gumroad

Immediate download after purchase.

Created with AI assistance and editorially revised. Editorial responsibility: Adrian Verdan (Dargel Solutions). Transparency notice and details inside the product.

The motif

Many agent voices — one human approval.

Four agent lanes — plan, build, review, research — converge on a single human approval gate. That is the whole method, and it is the score motif the book is designed around.

PLAN BUILD REVIEW RESEARCH HUMAN approves

From the book’s design language: notes are agent turns, outlined notes are review passes, and every strand ends at the amber human-approval ring.

What's inside

Ten chapters, from model choice to workflow.

  1. Why more than one agent. The principle, a maturity ladder, and an honest account of when one model is enough.
  2. The 2026 model landscape. Claude Fable 5.1, GPT-6 Astra, Gemini 3.8 Flash and Grok 4.6: dated model references, access limits and migration checks. No default winner.
  3. Open & self-hosted models. Llama, Qwen, DeepSeek, Mistral, gpt-oss: a decision tree for when local is genuinely worth it (hint: usually privacy, not cost).
  4. Orchestration patterns. Reviewer, planner-executor, router, ensemble, debate, pipeline, orchestrator-worker: what each is for, and what it costs.
  5. The reviewer pattern, hands-on. Reproduce a builder plus an independent read-only reviewer (Claude Code + Codex-style) step by step, including conflict resolution.
  6. Tooling & orchestration stack. Framework choices, pending tool calls, cancellation and recovery. Use a small evaluation set to decide how much orchestration the task needs.
  7. Deep research in your workflow. How agentic research works, which tools fit, and how to verify it before you build on it.
  8. Cost & quality. A cost model, an interactive calculator, and evaluation-led recipes per task type.
  9. Safety, security & governance. Prompt injection between agents, least privilege, and human-in-the-loop gates.
  10. Start now. Six prompt templates for five workflows: security triage, planning, setup, review and two-stage research.

Real excerpts

This is what the product looks like inside.

Orchestrating AI Agents Chapter 1

When orchestration does not pay off

Start by testing whether orchestration adds value. Three situations where adding agents can cost more than they add:

  • The task has many interdependencies. When subtasks continually need shared information, handoffs can cost more than they add. Test your task against a single-agent baseline rather than treating coding as categorically unsuitable.
  • Handoffs lose context. In practice, agents “suffered from lost context at each handoff and spent more tokens coordinating than executing” (Anthropic, “When to use multi-agent systems,” January 2026). More agents means more places where information can be dropped or distorted.
  • The task is not well-defined enough to decompose. A fuzzy problem does not become sharper by splitting it across two models. Fix the problem statement first.
Excerpt from the playbook, chapter 1 — shown with full context in the product.
Orchestrating AI Agents Chapter 8 — Live demo

Multi-agent cost calculator

Pre-filled with the playbook’s documented defaults. Change any value to model your own workload; prices are USD per million tokens (MTok).

$0.29
Multi-agent cost / task
$9.00
Extra cost / month (reviewer)
45.0 %
Reviewer uplift vs. single

Single-agent cost per task = (inTok × builder-in + outTok × builder-out) / 1,000,000. Reviewer cost per task = passes × ((inTok + outTok) × reviewer-in + 0.5 × outTok × reviewer-out) / 1,000,000 — the reviewer reads the output plus the context and writes about half the output as a findings report. Multi-agent = single + reviewer; monthly totals multiply by tasks per month. Token inputs are raw counts; prices are USD per million tokens.

The calculator uses editable example rates, not a live model-price feed. Enter the current rates for your chosen builder and reviewer before budgeting; include cache, tool and retry costs separately. Model-specific long-context thresholds and service modes require separate pricing; the calculator is a flat-rate estimate.

Excerpt from the playbook, chapter 8 — the full version shows all seven metrics, the formulas and the levers that matter more than model choice.

Before you buy

An honest promise.

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. The September 2026 update dates its model references and separates access, API compatibility and example costs. Provider limits and prices can change.

What this looks like in practice, with sources: what the pipeline rejected →

What broke along the way, and what changed because of it, is written up with dates and logs: the essays →

For whom — and for whom not

Is this playbook right for you?

A good fit if you

  • already work with an AI agent (Claude Code, Codex CLI, Cursor …)
  • want a second model to catch what the first one misses
  • decide with evaluations and cost figures, not vibes

Not a fit if you

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

Everything included

What you download.

Frequently asked

Quick answers.

What exactly is included?

Ten chapters as an offline HTML bundle plus a tagged PDF, an interactive multi-agent cost calculator, a model-selection matrix (XLSX), an orchestration setup checklist (XLSX), and the full prompt pack as a plain-text file. Everything works offline.

Do I need a machine-learning background?

No. The playbook is 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.

Does adding a second model guarantee better results?

No. 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. The guide gives you a method and a dated snapshot, not a guarantee — and it is honest about when one model is enough.

12.90 € excl. VAT

VAT depends on your country; the final price is shown at Gumroad checkout before purchase. Merchant of Record: Gumroad.

Buy on Gumroad

Part of the AI-First series

The AI-First Operating Playbook is the business-wide operating system this deep dive plugs into: automation blueprint, function-level playbooks, governance and ROI. Orchestrating AI Agents is the hands-on multi-agent companion behind its chapter 5.

The AI-First Operating Playbook →

Also available in German: Deutsche Ausgabe „KI-Agenten orchestrieren“ →