/ˈeɪdʒənt ˌhɜːr.dər/ (noun) — a practitioner who orchestrates fleets of AI coding agents; one who makes sense of parallel, asynchronous agent work without losing the plot.
Running one Claude Code session is using AI.
Running fifteen at once, on purpose, without losing control, is a practice.
We call that practice Agent Herding. This is where to learn it.
Read the free Course → See the Bootcamp → Join the cert waitlist →
6-week prep program · coaching-led cohort · outcome-guaranteed · cert exam bundled · launch cohort 2026. Same curriculum readable free as the self-paced Course.
For the last 40 years, software engineering assumed one human, at one terminal, writing code. We built our tools, our workflows, our mental models around that shape.
AI coding agents broke that shape. A single developer running 10+ Claude Code sessions in parallel is not just a faster developer. They're doing a qualitatively different job. The bottleneck moved from "how fast can I write code" to "how well can I brief, supervise, and coordinate autonomous workers."
No one taught us how to do that. There's no book. No conference talk. No training program.
Until now.
Agent Herding is the practice of:
It looks, honestly, a lot like managing a small team of junior engineers — except the juniors cost pennies, never sleep, and produce code faster than you can read it.
Getting to 2–3 parallel sessions is usually self-taught — common sense and a weekend. The wall most people hit is the jump from 3 to 4–12, where the coordination overhead changes shape entirely. That's the step this practice is about.
Agent Herding has three natural stages. Each one sets up the next.
1–3 parallel sessions. The baseline. CLAUDE.md, skills, context management, briefing a single agent well. This is common sense plus a bit of craft — most developers can learn it alone. Curriculum is here for reference, but you probably already have this.
For: reference, or if you've never run a Claude Code session before.
3–8 parallel sessions. Where the practice actually begins. Decomposing work into independent streams, briefing a cohort at once, git workflows that don't collapse under merge conflicts, catching agents that are quietly off-course. This is the jump most people plateau at.
For: senior engineers, leads, and solo founders who have tried to scale beyond 3 sessions and hit a wall.
10+ parallel sessions. Exam-grade. Agents spawning agents, forked sessions for alternative approaches, cross-repo coordination, and staying the coordinator instead of becoming the bottleneck. This is what the certification exam actually tests.
For: the practitioners at the frontier — and anyone preparing for the certification exam.
Cert curriculum is free. Read it as the self-paced AgentHerder Course — no gate, no drip wall. The paid thing is the exam.
The exam is ~3 hours, live, observed by a Principal AgentHerder — someone who already runs 10+ parallel sessions daily. You operate 10+ parallel sessions against a test repo we provide, delivering specified outcomes inside the window. Practice-tested, not knowledge-tested.
What gets graded:
Pass = Certified AgentHerder. Listable on LinkedIn, and issued by the person who wrote the curriculum. It's a new credential, so what it's worth today comes from what the exam actually puts you through rather than from name recognition. Not-yet = Apprentice — includes one free re-take within 6 months.
Join the waitlist to get:
No spam. One email per milestone. Unsubscribe with one click.
Want a structured path to get cert-ready? The AgentHerder Bootcamp is the productized 6-week prep program — coaching-led, cert exam bundled, outcome-guaranteed. See the curriculum →
You can't herd 15 sessions from a keyboard and a pile of terminal windows. You need a tool that lets Claude open its own tabs, know which tabs are running what, and coordinate across them.
We built one. It's open source, MIT, npm install -g @generativereality/cctabs.
cctabs ≠ AgentHerder. The tool is the lever. The practice is what you're learning to do with it.
If you got here looking for the tool rather than the practice, start with what AgentHerder and cctabs actually are, then how to run Claude Code sessions in parallel and where tmux fits.
Built by Fredrik Wollsén — Agentic Software/Growth Engineer at Augmented Mind, previously Mozilla. Twenty-two years as a professional software engineer; the last decade making AI genuinely useful, personally and professionally.
Currently Principal Tech Lead & AI-Native Transformation Coach at F-Secure. Former Claude Code Coach at DNV Cyber. The 4-engineer team he leads has been operating AI-native since September 2025, and in June 2026 merged 844 pull requests out of 892 opened against shipping product. Runs 8–20 parallel Claude Code work streams daily across product work and independent products (Remember This, My Transcriber).
Everything you'll learn in this program is something the curriculum author does every day, with a real fleet, against a shipping product. Not theorised. Not from a deck.
On stage at: GOSIM AI Vision Forum Paris 2026, Panel 1 — Agentic AI Systems & Human-AI Symbiosis (May 4, 2026).