SoftBricks AI
Home Services Projects About Contact
Academy
All Programs Agentic AI Bootcamp Agentic Coding Bootcamp AI Agent Mastery Bootcamp MLOps Bootcamp LLMOps Bootcamp Student Access
Enroll Now — $399
Cohort 1 · Now Open

Build a Real System Around Your AI Coding Assistant.

Prompting is not a workflow. Systems are.

8 weeks. 48 hours live. Stop fighting the same bugs every session. Walk out with a personal operating system — rules, commands, validation gates, and agent orchestration — that makes every feature you ship faster and more predictable than the last.

🌐 Web Portal 📱 iOS App 📱 Android App

Live sessions Saturdays & Sundays · 8:00 PM – 11:00 PM WAT · Cohort 1 · Now Open

⚠️ Limited Seats · Cohort 1

Cohort 1: Now Open

Saturdays & Sundays · 8:00 PM – 11:00 PM WAT

Join Early → Full Recordings From Day One

Start working on your system the hour you enrol. Arrive at the first live session with code to review.

0
Hours Live
0
Weeks
0
System Builds
$0+
Value Delivered

Why AI Coding Assistants Still Let You Down

The tools got better. Most workflows did not. The gap between casual prompting and shipping real systems is wider than people admit.

🔍

You Throw Away Most of What It Writes

You ask for a fix, skim the output, paste in half, rewrite the rest. Over a week that is hours of code you discard. The assistant never knows why — so it keeps making the same mistakes.

🔃

Every Session Starts From Zero

Your context, preferences, and past corrections evaporate when the chat ends. Tomorrow you are teaching the same rules again. Nothing compounds. Nothing gets sharper.

🔧

One-Off Fixes Instead of Feedback Loops

When code breaks, you patch it manually and move on. The root cause lives in your setup — missing rules, weak validation, no review step — and it will bite again next week. The way out is a system, not another patch.

Two Phases. One Engineer Who Ships.

Start by fixing the core loop. End by running a personal coding organisation with rules, tools, remote agents, and subagents working for you.

PHASE 1 · WEEKS 1–4

Foundations

Fix the loop. Make progress compound.

Master the plan-implement-validate cycle, lock down project rules and context, build a command library you can chain, and run spec-driven features from a written PRD. By Week 4 you will have a reusable personal baseline.

  • Mental model: plan → implement → validate
  • Global and project-local rules
  • Reusable commands and chaining patterns
  • PRD-driven feature delivery
PHASE 2 · WEEKS 5–8

Leverage

Scale yourself into a team of one.

Turn validation into automation. Connect your assistant to the tools it needs. Move work onto remote agents that run without you watching. Coordinate subagents in parallel. Graduate with a capstone system you can reuse on every future project.

  • Automated validation gates and review
  • MCP servers and tool integration
  • Remote and GitHub-based coding agents
  • Subagent orchestration and capstone

8 Weeks. 8 Systems You Keep.

Every week you leave with a working piece of your personal coding system. By the end, these pieces plug together.

WEEK 1
Foundations & The PIV Loop
Build: Personal Baseline Config

Install the right assistant for your workflow, learn the plan-implement-validate loop, and set up a baseline config you will carry into every repo. The idea is simple: planning up front beats retrofitting fixes after.

Claude Code / Cursor / Windsurf Plan-Implement-Validate Workspace setup Config hygiene Baseline templates
WEEK 2
Rules & Project Context
Build: Rulebook for a Real Repo

Give your assistant the rules a new teammate would need — coding style, framework conventions, testing expectations, non-negotiables. Learn when to pin rules globally versus per project, and how to keep them short enough to stay loaded.

Global rules Project rules CLAUDE.md / AGENTS.md Context budgeting Repo onboarding
WEEK 3
Commands & Workflow Chains
Build: Your First Command Library

Convert the prompts you retype into reusable commands. Learn the structure of a robust command, how to chain them into multi-step workflows, and when to branch conditionally based on what the assistant found.

Slash commands Arguments & flags Chaining Branching flows Team-shareable libraries
WEEK 4
Spec-Driven Delivery with PRDs
Build: Feature Shipped From a Written Spec

Write a tight PRD, let the assistant turn it into a plan, then implement and validate in iterations. Learn why a two-page spec is the highest-leverage artefact you can give an AI coding assistant — and how to keep it from drifting.

PRD templates Plan generation Implementation passes Acceptance criteria Drift prevention
WEEK 5
Validation Gates & Code Review
Build: Automated Review Pipeline

Turn human review into an automated pyramid: linters, unit tests, integration checks, and AI-driven code review. Define the exact gates your assistant must pass before it hands work back. Mistakes become feedback the system absorbs.

Validation pyramid Lint & type gates Test expectations AI code review Self-correcting loops
WEEK 6
MCP Servers & Tool Integration
Build: Custom MCP Tool For Your Stack

Connect your assistant to the systems it keeps asking you about: your database, your issue tracker, your deployment platform. Use existing MCP servers and write one of your own for a bespoke internal tool.

Model Context Protocol Off-the-shelf servers Building your own MCP Auth & scopes Tool discipline
WEEK 7
Remote & GitHub-Based Agents
Build: Headless Agent That Ships PRs

Move work off your laptop. Run coding agents in CI, on a VM, or directly against your issue tracker. Let them open draft PRs while you sleep — with validation gates that stop anything half-baked from merging.

GitHub Actions integration Headless runs Issue → PR flows Cloud runners Gate-protected merges
WEEK 8
Subagents, Orchestration & Capstone
Build: Multi-Agent System You Keep

Split work across specialised subagents — one plans, one implements, one reviews — with a supervisor making the hand-offs. Present a capstone system: your complete personal setup running on a real project, shipped with evidence.

Subagent patterns Supervisor orchestration Parallel delegation Capstone review Graduation demo

The Stack You Will Work In

Standard tools engineering teams actually ship with. No toy demos, no throwaway sandboxes.

🤖

AI Coding Assistants

Claude Code, Cursor, Windsurf, Cline, Codex-class IDE tools

🔌

Protocols

Model Context Protocol, tool-use schemas, agent hand-offs

📁

Version Control

Git, GitHub, GitHub Actions, PR review automation

Validation

pytest, Vitest, ESLint, Ruff, type checkers, pre-commit hooks

☁️

Remote Runners

GitHub Actions, cloud VMs, container runners, scheduled jobs

🔀

Orchestration

Subagent patterns, supervisor flows, parallel delegation

📝

Specs & Docs

PRDs, task lists, plan artefacts, acceptance criteria

📄

Rules & Commands

CLAUDE.md, AGENTS.md, slash commands, chained workflows

🛠

Dev Environment

VS Code, dev containers, shell tooling, observability helpers

Everything Included

One price. A system you keep. A community that stays active after the cohort ends.

🎓
48 Hours Live Instruction
$800 value
Two 3-hour live sessions each weekend. Real-time reviews of your rules, commands, and agent flows on actual repos.
📦
Rules & Command Starter Pack
$400 value
A curated starter pack of battle-tested rules, slash commands, and PRD templates. Drop them into your repos on day one.
🚀
Capstone System
$400 value
Your complete setup — baseline config, rules, commands, MCP tools, remote agent, subagent orchestration — running on a real project.
🔧
Custom MCP Tool
$250 value
Build and keep a bespoke MCP server wired into one of your own stacks. The reusable building block for the next ten features.
🔄
Unlimited Cohort Attendance
$300 value
Re-attend every future cohort free. The tools move fast — so you move with them.
💬
Private Cohort Community
$200 value
A private channel of engineers reviewing each other's rules, sharing commands, and debugging agent runs.
📁
Full Source Repository
$200 value
Every weekly build in a public-to-cohort repo. Fork it, adapt it, carry it into your own projects.
🎥
Session Recordings
$150 value
Every live session recorded inside 24 hours. Review any week, any time, for as long as the academy exists.
🏅
Completion Certificate
$200 value
A verified certificate from SoftBricks Academy recognising completion of the Agentic Coding track.
Total Value
$2,200+ value delivered

What Early Cohort Members Say

Notes from engineers previewing the curriculum ahead of the live cohort.

★★★★★

"I thought I was already using Claude Code well. The rules and validation sections showed me I was doing about a third of it. My acceptance rate on generated code jumped noticeably in the first week."

OD
Oumar D.
Senior Backend Engineer
★★★★★

"The PRD → plan → implement flow changed how I brief anything, not just the assistant. I write two pages up front and I argue with myself there instead of in the code."

IH
Imane H.
Staff Engineer, SaaS Company
★★★★★

"The MCP module was the one I was least sure I needed and it is the one I now use every day. Wiring the assistant into our database killed half the copy-paste in my workflow."

KM
Kwame M.
Full-Stack Developer
★★★★★

"Running agents on GitHub Actions felt like science fiction until Week 7. Now I wake up to draft PRs. I review them before coffee and most of them merge."

RP
Rukia P.
Tech Lead, Fintech
★★★★★

"My rules folder used to be a junk drawer. Now it is the artefact that turns my assistant into a teammate who actually knows the codebase."

TC
Tadeo C.
Indie Founder
★★★★★

"Subagents week rewired how I think about parallel work. I stopped hand-walking the assistant through every step and started delegating whole slices of the feature."

JE
Joana E.
Engineering Manager
TA
Instructor

Terence Ateya

AI Engineer & Founder, SoftBricks

Ships production AI systems for clients across Africa and Europe. Architect behind StudyMate AI, a full-stack agentic platform running onboarding, moderation, meeting flows, and support automation in production. Uses the same plan-implement-validate loop, rule stack, and remote agent setup you will build in this bootcamp — every day, on real client work. The curriculum is his working method, not a theory lecture.

15+
Projects Shipped
200+
Engineers Taught
48h
Live per cohort

Is This Right for You?

This bootcamp rewards engineers who already write code and want a better feedback loop. Make sure you see yourself on the left column.

This is for you if...

  • You already ship code and use AI coding assistants casually
  • You want reliable output instead of hit-or-miss prompting
  • You are willing to commit 10–15 hours per week for 8 weeks
  • You prefer a system that compounds over shortcut hacks
  • You work on a real codebase you can practise on between sessions

This is NOT for you if...

  • You have never written code and want an intro programming class
  • You expect the assistant to think for you without guidance
  • You want a passive video library, not a live cohort
  • You cannot commit at least 10 hours per week

One Cohort. Full Access.

One price. No tiers, no upsells. Everything needed to leave with a working system.

Agentic Coding Bootcamp — Cohort 1 — Now Open
$399
One-time · EMI available at checkout
  • 48 hours of live instruction
  • 8 system builds you keep
  • Rules & command starter pack
  • Custom MCP tool for your stack
  • Capstone system with review
  • Unlimited cohort re-attendance
  • Private community access
  • Full source repository
  • All session recordings
  • Completion certificate
Enroll Now — $399 Join Cohort WhatsApp

✓ Secure checkout · EMI available at checkout

🔒 14-day money-back guarantee. No questions asked.

Start this weekend. Arrive already ahead.

Enrol today and get immediate access to the recordings and starter pack. Run through your first plan-implement-validate loop before the live cohort begins.

Enroll Now — $399
Live Instructor-Led ⚠️ Limited Seats · Cohort 1 Certificate of Completion Lifetime Access Start Today

Common Questions

The questions most engineers ask before enrolling.

Which AI coding assistant does the course use?

The live walkthroughs use Claude Code as the primary assistant, with examples in Cursor, Windsurf, and Cline so you can translate the system to whichever tool you prefer. The patterns are assistant-agnostic.

How much coding experience do I need?

At least a year of writing and shipping code in any mainstream language. The bootcamp assumes you can read a diff, run a test suite, and open a PR. It does not teach intro programming.

What is the time commitment?

Plan for 10–15 hours a week — 6 hours live across Saturday and Sunday, plus 4–9 hours of weekly build work. Most of the real learning happens in the build.

Do I need my own project to practise on?

Ideally yes. A real repo you care about makes the rules, commands, and MCP work stick. If you do not have one, a seed project is provided so nobody is blocked on Week 1.

How does this differ from the Agentic AI Bootcamp?

Agentic AI is about building agents that serve your users in production. Agentic Coding is about building a system that serves you while you code. Different audience, different outcome. Many engineers take both.

What if I miss a live session?

Every session is recorded and posted within 24 hours. You also get unlimited re-attendance for future cohorts at no extra cost, so any week you miss, you catch live next time.

Is EMI available?

Yes. EMI is offered at checkout. For any other payment arrangement, reach us at academy@softbricks.ai.

What if the tools change after the cohort?

They will. The curriculum is written around the underlying loop — planning, context, validation, orchestration — not one vendor. Unlimited cohort re-attendance is included so you can re-run the curriculum with the new tools each time.

SoftBricks Academy · Agentic Coding Bootcamp · Cohort 1 · $399
Start Today · Cohort 1 Now Open
Enroll Now — $399