Skip to content
Academy
AI-assisted developmentAdvanced

Course 4.4 · Curriculum 2026.1

Running agents in parallel with worktrees

Run several agents at once without them overwriting each other. Isolation, merge discipline, and knowing when parallelism stops paying.

Estimated effort
3 hr
Lessons
26
Modules
5
Material
3 hr

Estimated effort is the sum of the lesson and lab times in the course outline, for this version of the course.

In development

This course is planned and not on sale. The curriculum below is the plan, and it may change before the course opens.

See the courses on sale

01What you will learn

6 capabilities, stated as things you can do

Each one is what you should be able to do at the end, not what the course covers. If an outcome is not testable, it is not an outcome.

  1. Set up isolated working trees so two agents never touch the same files.
  2. Split work into tasks that genuinely do not overlap.
  3. Merge parallel results without losing work or shipping a silent conflict.
  4. Recognise the point where coordination costs more than the parallelism saves.
  5. Keep org-level side effects from colliding when two agents deploy.
  6. Review parallel output as one change rather than as three unrelated ones.

02Curriculum

5 modules, 26 lessons

Every lesson shows its length and its type, from the course outline.

5 modules · 26 lessons · 3 hr of material

Separate working trees, separate scratch orgs, separate everything an agent can write to.

  1. VideoWhy two agents in one directory corrupt each otherPreview7 min
  2. SCORMLegacy module: Git worktrees, branches and rebasesA packaged module from our earlier authoring toolchain. It tracks and reports exactly like the native lessons around it.26 min
  3. VideoTen named worktrees, one agent per branch5 min
  4. VideoScratch orgs per agent, and the metadata that cannot be duplicated5 min
  5. ReadingWhat isolation does not protect you from4 min
  6. QuizCheck: isolation8 min

SCORM lessons report their own completion, so we treat it as telemetry. The assessment is what awards a certificate.

04Before you start

What you need first

Assumed knowledge and setup

  • Course 4.1, and comfort with Git at the level of branch, commit and merge.
  • A repository with Salesforce metadata under source control.
  • A machine that can run more than one agent session at a time.

Before this course

Courses often taken next

Each is a separate course, bought on its own.

05Who teaches it

Elliot Saha

Co-founder, Chief Technology Officer

Platform architecture, custom Apex and Lightning Web Components, AI systems, and the Academy platform itself.

Full background

06Reviews

No learner reviews yet

This course has not been taken by enough people to publish an honest rating, and we will not print invented quotes on a page that sells verification discipline. Here is what we can evidence instead.

Assessment
Lesson checks onlyThis course carries lesson checks and issues no certificate.
Curriculum version
2026.1You enrol into a version. Content changes do not move you mid-course, and your required-lesson count is snapshotted at enrollment.
Refunds
14 daysAn individual purchase can be refunded within 14 days if you have completed less than 20% of the lessons. Team seats are refundable before they are assigned. From the Academy terms.
Enrol

Start 4.4

This course is in development and not yet open for enrolment. The courses open now are listed in the catalogue.

See courses open now
  • 3 hr estimated effort, labs included
  • A ShareCo certificate is not a Salesforce certification