Mariete Academy
Mariete Builder
specialistBuilder

Mariete Builder Specialist

Foundation taught you to brief, review, and schedule a single Builder run. Specialist is what you reach for when one agent is no longer the right unit of work. Multi-agent decomposition, SDK-built sub-agents with their own tool boundaries, human-in-the-loop approval gates, versioned rollouts with regression detection, and an incident practice that survives a production failure. This course assumes Foundation; it skips the basics and gets directly to the engineering decisions that separate a hobby workspace from a system you can defend in front of a CTO, an auditor, and a regulator.

5 modules20 questions~110 minPass at 75%Free
Outcomes

What you'll be able to do.

  • Multi-agent decomposition
  • Custom SDK agents
  • Approval gates and human-in-the-loop
  • Production governance
  • Failure modes and incident response
Curriculum

5 modules. ~110 minutes total.

  1. 01
    Multi-agent decomposition
    ~22 min

    A single Builder run is the right unit of work for a job that fits in one head. Once a job needs two heads — a researcher and a writer, a tr…

  2. 02
    Custom SDK agents
    ~22 min

    The 50+ pre-built recipes cover most jobs. The Builder SDK is for the jobs they don't. This module is about when to drop into the SDK, how t…

  3. 03
    Approval gates and human-in-the-loop
    ~22 min

    Some agent decisions must not happen without a human. Sending external email to a regulator. Posting to the company's official social accoun…

  4. 04
    Production governance
    ~22 min

    A Builder workspace with three schedules and one operator is easy to govern. A workspace with sixty schedules across eight teams, three mode…

  5. 05
    Failure modes and incident response
    ~22 min

    Production multi-agent systems fail. Not "might fail" — will fail. The team that builds Builder pipelines as if failure is impossible has no…

Get a feel for the skills check

One sample question. Click to reveal the answer.

Multiple choice

A teammate proposes splitting a 5-step lead-qualification job into 5 separate agents because "more agents are more flexible." What is the most accurate response, given the decomposition criteria?

  1. Approve — granular agents are always more reviewable than monolithic ones
  2. Reject the split unless at least two of the five decomposition criteria are met (distinct phases, isolation, different approvers, different cadences, divergent token budgets)
  3. Approve only if the team also creates a "skeptic agent" to review each step
  4. Reject — multi-agent flows are only appropriate for SDK-built agents, never for forks

20 questions like this. Builder Specialist pass-mark is 75%.

Your pathway

Where this fits.

Continue with Builder

Ready?

Free. No exam fee. Two retakes per cycle.

Mariete Builder Specialist · Mariete Academy