bRRAInSkills stacks · Practitioner
v2.0

AI Team Development

Run shared bRRAIn memory for a team of people and AI assistants: structure, access, curation, attribution and hand-offs.

Level
Practitioner
Learning time
18 hours
Price
$499
Credential
Valid 3 years
Enroll on learn.brrain.io See the syllabus
What's new in v2.0

What changed in this edition.

  • Memory layers replace v1's 'five zones', mapped to real vault structures: org and project canonical, session records, personal workspaces (Z2) and the access layer.
  • Access for humans and agents taught on the real console: custom roles whose checklist replaces tier defaults, per-project Read/Add/Update/Delete grants, and purpose-issued agent credentials proven with a refused write.
  • Hand-offs are MCP-first: start_brain_session, record_assistant_turn, record_decision with a human owner, and hand-off turns whose Depends on / Produced lines feed Nexus Memory Lineage. The git open/closure ritual is now the secondary variant.
  • The Consolidator and Conflict Zone are taught as the product components they are: priorities, three-way merge, role-hierarchy auto-resolution and the 24-hour default escalation, with humans curating canonical.
  • New team surfaces: console Projects with AI charter drafting, Nexus Plan epics and sprints, Nexus Memory and Meetings, and multi-client teams across Claude Desktop, VS Code, ChatGPT and Nexus.
  • Labs and the capstone are AI role-plays scored against published rubrics; the exam is a per-candidate form with four AI-conducted performance tasks.
Outcomes

What you will be able to do.

  • You will be able to design a team memory layout across memory layers, projects and charters for a mixed human-agent team.
  • You will be able to configure least-privilege access for people and AI agents with custom roles, per-project permissions and proven boundaries.
  • You will be able to run consolidation and curation of canonical memory and resolve collisions and conflicts without losing history.
  • You will be able to attribute every decision to an accountable human across AI clients and hand off work between any combination of people and agents.
  • You will be able to encode team standards so every assistant inherits them, and enforce the mechanical ones with recorded overrides.
  • You will be able to run multi-actor work and blameless retros on Nexus Plan, Memory and Meetings.
  • You will be able to onboard a new engineer or AI contributor into team memory in about 30 minutes.

Who it's for

  • Tech leads and engineering managers running mixed human and AI teams
  • Staff engineers responsible for shared memory and standards
  • Project curators and maintainers coordinating contributors with AI assistance
  • Founders moving from solo AI use to team AI use

Not covered here

  • The personal session loop (see #13 AI Coding with bRRAIn; this course assumes it)
  • Release-train design (see #15 AI SDLC & Release Train)
  • System architecture (see #16 AI Augmented Systems Architect)
  • People management; this is engineering practice
Syllabus

8 modules, 64 lessons.

About 18 hours of learning. Open a module to see every lesson.

  1. Team memory structure 8 lessons · 2 h 15 min

    Why team memory differs from solo memory; the five memory layers mapped onto real vault structures; console Projects with AI-drafted 12-section charters; personal workspaces (Z2) and per-session records; designing a complete team memory layout. Lab 1 designs Northwind's layout with its engineering manager.

    1. Module 1 pretest Diagnostic pretest · 5 min
    2. Why solo memory and team memory are different Reading · 15 min
    3. Memory layers: mapping team memory onto the vault Reading · 15 min
    4. Projects and AI-drafted charters Worked example · 15 min
    5. Personal workspaces and session records Reading · 15 min
    6. Designing a team memory layout end to end Worked example · 15 min
    7. Lab 1: Design Northwind's team memory layout AI role-play lab · 45 min
    8. Retrieval: 8 questions across the module Retrieval check · 10 min
  2. Access for humans and agents 8 lessons · 2 h 15 min

    The seven canonical roles mapped to a team; custom roles whose checklist replaces tier defaults; per-project Read/Add/Update/Delete permissions; agent credentials, least privilege and refused-write proofs; an access review after a near miss. Lab 2 configures access with the security lead.

    1. Module 2 pretest Diagnostic pretest · 5 min
    2. The seven roles and team memory Reading · 15 min
    3. Custom roles that replace tier defaults Reading · 15 min
    4. Per-project permissions for team access Worked example · 15 min
    5. Agent access: credentials, least privilege, proof Reading · 15 min
    6. Scenario: reviewing a team's access after a near miss Scenario · 15 min
    7. Lab 2: Configure team access with the security lead AI role-play lab · 45 min
    8. Retrieval: 8 questions across the module Retrieval check · 10 min
  3. Consolidation and curation 9 lessons · 2 h 30 min

    The Consolidator pipeline at team scale and its read-only inspection commands; session records versus canonical; the curation protocol and its four dispositions; the Conflict Zone, role-hierarchy auto-resolution and escalation; consolidation and curation cadence; a worked weekly curation pass. Lab 3 curates a week of session records with the project curator.

    1. Module 3 pretest Diagnostic pretest · 5 min
    2. The Consolidator at team scale Reading · 15 min
    3. Session records vs canonical: the fundamental split Reading · 15 min
    4. The curation protocol: what survives, what doesn't Reading · 15 min
    5. Conflicts and the Conflict Zone Reading · 15 min
    6. Consolidation and curation cadence Reading · 15 min
    7. A weekly curation pass, worked Worked example · 15 min
    8. Lab 3: Curate a week of team session records AI role-play lab · 45 min
    9. Retrieval: 8 questions across the module Retrieval check · 10 min
  4. Attribution and hand-offs 10 lessons · 2 h 45 min

    Attribution from credentials, record_decision owners and the first-turn convention; commit conventions for AI-touched work; multi-client teams across Claude Desktop, the VS Code extension, the ChatGPT app and Nexus; the MCP-first hand-off ritual with the git variant; AI-to-AI, human-to-AI and AI-to-human hand-offs. Lab 4 runs a six-step hand-off chain.

    1. Module 4 pretest Diagnostic pretest · 5 min
    2. The attribution model: who did what, with which assistant Reading · 15 min
    3. Commit conventions for AI-touched work Reading · 15 min
    4. Multi-client teams: Claude Desktop, VS Code, ChatGPT and Nexus Reading · 15 min
    5. The hand-off ritual: MCP-first Reading · 15 min
    6. AI-to-AI hand-offs: sub-agents and parallel sessions Reading · 15 min
    7. Human-to-AI hand-offs: resume my work Reading · 15 min
    8. AI-to-human hand-offs: review this Reading · 15 min
    9. Lab 4: Run a hand-off chain across two humans and two agents AI role-play lab · 45 min
    10. Retrieval: 8 questions across the module Retrieval check · 10 min
  5. Standards AI inherits 8 lessons · 2 h 15 min

    The four kinds of team standard and what makes one enforceable; encoding standards in canonical so every assistant inherits them through the session protocol and pointer rules; hooks and CI checks with recorded overrides; the 'AI says no' pattern; auditing standards drift. Lab 5 adds standards and enforcement for Northwind.

    1. Module 5 pretest Diagnostic pretest · 5 min
    2. The standards anatomy: style, review, decision quality, documentation Reading · 15 min
    3. Encoding standards so every assistant inherits them Reading · 15 min
    4. Pre-commit hooks and CI checks for AI-touched work Reading · 15 min
    5. The 'AI says no' pattern Reading · 15 min
    6. Auditing standards drift across a team, worked Worked example · 15 min
    7. Lab 5: Add team standards and enforcement for Northwind AI role-play lab · 45 min
    8. Retrieval: 8 questions across the module Retrieval check · 10 min
  6. Multi-actor operations 9 lessons · 2 h 30 min

    The shape of a multi-actor session; team surfaces in Nexus Plan, Memory and Meetings; detecting the five collisions; lock-free coordination with append-only records and attribution-based merge; reviewing versus writing modes enforced by access; blameless retros that separate AI and human causes. Lab 6 runs a live session with injected collisions.

    1. Module 6 pretest Diagnostic pretest · 5 min
    2. The multi-actor session shape Reading · 15 min
    3. Team surfaces: Nexus Plan, Memory and Meetings Reading · 15 min
    4. Detecting collisions in real time Reading · 15 min
    5. Lock-free coordination: append-only records and attribution-based merge Reading · 15 min
    6. AI is reviewing vs AI is writing Reading · 15 min
    7. Blameless retros that separate AI and human causes Reading · 15 min
    8. Lab 6: Run a live multi-actor session with injected collisions AI role-play lab · 45 min
    9. Retrieval: 8 questions across the module Retrieval check · 10 min
  7. Onboarding and coaching 7 lessons · 2 h

    The 30-minute onboarding ritual for people; onboarding AI contributors with owner, credential, pointer instructions and a boundary proof; the coaching arc from personal loop to team fluency; common new-contributor failures. Lab 7 onboards a new engineer in 30 minutes.

    1. Module 7 pretest Diagnostic pretest · 5 min
    2. The 30-minute onboarding ritual Reading · 15 min
    3. Onboarding an AI contributor Reading · 15 min
    4. The coaching arc from solo to team fluency Reading · 15 min
    5. Common new-contributor failures and how to spot them Reading · 15 min
    6. Lab 7: Onboard a new engineer in 30 minutes AI role-play lab · 45 min
    7. Retrieval: 8 questions across the module Retrieval check · 10 min
  8. Capstone and exam readiness 5 lessons · 1 h 30 min

    The capstone brief, rubric and hard fails; exam structure, blueprint and pacing; the capstone role-play: stand up and run team memory for Harborline Logistics' Rate-Engine project and handle an incident.

    1. Module 8 pretest Diagnostic pretest · 5 min
    2. The capstone brief: what is given and what is required Reading · 15 min
    3. Exam readiness: blueprint, item types and timing Reading · 15 min
    4. Retrieval: 6 questions across the module Retrieval check · 10 min
    5. Capstone: Stand up and run team memory for a mixed human-agent team AI role-play lab · 45 min
Labs and capstone

Practice against someone who pushes back.

Labs run in your browser as AI role-plays. An AI plays the person on the other side of the scenario — with their own goals and objections — and your work is scored against the published rubric. There is nothing to install.

  • Lab 1 · Team memory structure

    AI role-play with Northwind's engineering manager: design the team memory layout for a mixed human-agent project

  • Lab 2 · Access for humans and agents

    AI role-play with the security lead: configure roles, per-project grants and agent credentials for the team

  • Lab 3 · Consolidation and curation

    AI role-play with the project curator: curate a week of team session records

  • Lab 4 · Attribution and hand-offs

    AI role-play with a senior engineer arriving cold: run a six-step hand-off chain across two humans and two agents

  • Lab 5 · Standards AI inherits

    AI role-play with a skeptical senior engineer: add team standards and enforcement that every assistant inherits

  • Lab 6 · Multi-actor operations

    AI role-play with the engineering manager: run a live multi-actor session with five injected collisions

  • Lab 7 · Onboarding and coaching

    AI role-play with a new engineer: run the 30-minute onboarding ritual

  • Lab 8 · Capstone and exam readiness

    AI role-play with a VP Engineering and a curator: stand up team memory for a new project and handle an incident

Capstone

Stand up and run team memory for a mixed human-agent team

AI role-play scored against the published rubric

Pass mark: 72%

Scored on

  • Memory layout and project structure15%
  • Access design for humans and agents20%
  • Attribution and hand-off protocol20%
  • Curation, consolidation and conflict handling20%
  • Standards encoding and enforcement15%
  • Onboarding and incident communication10%
Exam and credential

One exam. A credential anyone can verify.

The exam

Items per form
59
Time allowed
120 min
Pass mark
72%
Performance tasks
4
Attempts included
2
Wait between attempts
7 days
  • Online and timed, taken on learn.brrain.io.
  • Your form is assembled for you from the course's item bank, so no two candidates sit the same paper.
  • Performance tasks are conducted by an AI examiner: you work through a realistic scenario and are scored against a published rubric.

The credential

  • A verifiable digital badge in your name.
  • A public verification page at learn.brrain.io/verify, so an employer or client can confirm it.
  • Valid for 3 years.
  • Renewal: At 3 years, by passing the then-current exam; CE modules completed during the cycle keep the credential current
Before and after

Where this course sits.

Stacks well with

Questions

Frequently asked.

Do I need to install anything for the labs?

No. Labs and the capstone run in your browser on learn.brrain.io as AI role-plays: an AI plays the person on the other side of the scenario, and your work is scored against the rubric published with the course.

How is the exam delivered?

Online and timed: 59 items in 120 minutes, on a form assembled for you from the course's item bank. 4 of the items are performance tasks conducted by an AI examiner: you do the work rather than pick an answer. The pass mark is 72%.

What if I don't pass first time?

You have 2 attempts, with a 7-day wait after an unsuccessful attempt. Further exam attempts can be bought for $299 each.

How long is the credential valid?

3 years. You receive a verifiable digital badge with a public verification page at learn.brrain.io/verify, so anyone can confirm it is genuine.

I hold the v1 credential. Is it still valid?

Yes. Credentials earned on v1 remain valid and verifiable at learn.brrain.io/verify. When you renew, you sit the then-current version of the exam.

Can my company enroll a team?

Yes. Firms can buy a certification bundle for $2,999 per firm per year — see the pricing page — or contact us to arrange enrollment for a larger group.

Also in bRRAInSkills stacks

Related courses.

See every bRRAInSkills stacks course · Full catalog

Enroll

AI Team Development

Run shared bRRAIn memory for a team of people and AI assistants: structure, access, curation, attribution and hand-offs.

Enroll on learn.brrain.io Back to all courses