arrow_backback to studio
schoolacademy · applied training

baachee academy

applied AI training for teams — past sessions, knowledge articles, searchable dictionary, and full syllabus.

workspace_premium

training sessions

all completed
cases

case study: techcareer.net

open_in_newbootcamp page

we delivered a hands-on applied AI training bootcamp to developers at techcareer.net — “Agents and Use Cases” — covering agentic tools, automation patterns, MCP integrations, and real-world project builds with working code.

schedule 16 hours totalgroup developerscalendar_month may 2026location_on remote (bootcamp)

sample material

techcareer.netAPPLIED AI SERIES — SESSION 01Agentic AI Assistants (CLI)Claude Code · OpenCode · GitHub Copilot CLIAgentic Workflows · Terminal Steering · Live Project (4 hrs (9,10 May))Vahid FarajijobehdarSr. Applied AI SpecialistAgenda — From Zero to Agentic ProWhat we cover today, in order1 Foundations — CLI, Agentic Loop, Tools2 Get Started — Install, Slash Commands, Config, Permissions3 Power Features — Hooks, Memory, Sub-Agents, CLAUDE.md4 Pro Level — Prompting, Context Engineering, Multi-AgentPart 5 — Live Project (live!)Build a Cargo Tracker app end-to-end▸ Scaffold & deploy with Claude Code▸ Wire a real MCP server (shipment data)© 2026 baachee.ai · techcareer.net1/34

slide from module 01: agentic AI foundations — the agentic loop diagram

article

knowledge articles

menu_book

training syllabus

16 hours · 4 modules
01

Agentic AI Foundations

Agentic loop · CLI tools (Claude Code, Copilot, OpenCode) · Permission modes · HITL patterns · Setting up your first project

4h
02

Context Engineering

CLAUDE.md design · Path-scoped rules · Token budgeting · Prompt structure · /compact and memory management

4h
03

MCP Integrations

MCP protocol spec · Building MCP servers · Tool definitions · .mcp.json wiring · Live data access patterns

4h
04

Advanced: Hooks, Memory & Sub-Agents

Hook events · Custom automation · Memory types · Sub-agent architecture · Custom specialist agents

4h
dictionary

AI dictionary

23 terms
search
Agentic AI
AI that autonomously takes multiple steps to achieve a goal — reads files, writes code, runs commands, verifies results — rather than just answering questions.
Agentic Loop
The cycle an agent repeats: Gather context → Take action → Verify results → Done (or loop back). The human can interrupt at any point.
CLI (Command Line Interface)
A text-based interface where you type commands. AI-powered CLIs let you talk to an agent in natural language directly from your terminal.
Claude Code
Anthropic's agentic CLI tool for full-project coding. Runs in the terminal, understands your codebase, and can read/write/execute autonomously.
Context Engineering
The discipline of giving an AI agent exactly the right information at the right time — no more, no less — to maximize output quality while minimizing token cost.
Context Window
The total amount of text (measured in tokens) an AI model can process at once. Everything — system prompt, conversation history, file contents — competes for this space.
CLAUDE.md
An instruction file loaded at session startup that tells the agent your project conventions, build commands, and architecture rules. Keep under 200 lines.
Fallback Rotation
Automatically switching to secondary API keys when primary quotas are exceeded — ensuring zero failed queries and no wasted retry tokens.
GitHub Copilot CLI
GitHub/Microsoft's terminal-based AI assistant focused on shell commands, git workflows, and PR management.
HITL (Human-in-the-Loop)
A pattern where the human can interrupt, redirect, or stop the agent at any point during its autonomous execution. Press Ctrl+C.
Hooks
Automated actions triggered by agent events (session start, before/after tool use, on stop). Used for formatting, validation, logging, and security guardrails.
MCP (Model Context Protocol)
An open standard that lets you expose your data and services as tools an AI agent can call live — turning it from a text generator into an operational assistant.
OpenCode
Open-source agentic coding CLI that supports any model (local or cloud). Key strength: self-hosting and data sovereignty.
Permission Modes
Controls for how much autonomy the agent has: default (ask everything), acceptEdits (auto-allow edits), auto (AI classifies risk), plan (read-only until you approve).
Prompt Caching
A technique where repeated system instructions are cached so you pay for them once per session rather than once per message — reducing costs significantly.
Schema Compression
Sending only relevant tables, column types, and row counts to the LLM instead of your entire database schema — reducing a 400-table DB to ~2KB of context.
Self-Learning Agent
An agent that improves accuracy over time through a memory layer that accumulates patterns — without model retraining or fine-tuning.
Slash Commands
Shortcuts typed directly in the agent prompt (e.g. /compact, /init, /deploy, /review) that trigger built-in functionality.
Sub-Agent
A specialist agent spawned by the main agent to handle a focused task in its own context window, returning a clean summary without polluting your conversation.
Token
The basic unit of text processing for LLMs. Roughly 4 characters or 3/4 of a word. Every token in your prompt costs money and context space.
Worktree
A separate git branch + directory that lets you run multiple agent sessions simultaneously without merge conflicts.
/compact
Compresses conversation history to free context-window space. Use when switching domains or after long debugging sessions.
/init
Auto-generates a CLAUDE.md instruction file by reading your codebase — project conventions, build commands, architecture notes.

train your team on agentic AI

applied training sessions — agentic workflows, context engineering, MCP, and live project builds.

4-hour modules · remote or on-site · haarlem & beyond

baachee academy · haarlem · applied AI training for small teams