Pebellslearn by building
RoadmapMatrixCatalogSandboxSign in

AI Agents

Outline

34 topics and 63 subtopics mapped. This is the ground the track will cover — the lessons aren't written yet.

  1. 01

    Basic Backend Development

  2. 02

    Git and Terminal Usage

  3. 03

    REST API Knowledge

  4. 04

    Transformer Models and LLMs

    8 subtopics
    • Tokenization
    • Context Windows
    • Token Based Pricing
    • Temperature
    • Frequency Penalty
    • Presence Penalty
    • Top-p
    • Stopping Criteria
  5. 05

    Open Weight Models

  6. 06

    Closed Weight Models

  7. 07

    Streamed vs Unstreamed Responses

  8. 08

    Reasoning vs Standard Models

  9. 09

    Fine-tuning vs Prompt Engineering

  10. 10

    Embeddings and Vector Search

  11. 11

    Understand the Basics of RAG

  12. 12

    Pricing of Common Models

    2 subtopics
    • What are AI Agents?
    • What are Tools?
  13. 13

    Agent Loop

    10 subtopics
    • Perception / User Input
    • Reason and Plan
    • Acting / Tool Invocation
    • Observation & Reflection
    • Personal assistant
    • Code generation
    • Data analysis
    • Web Scraping / Crawling
    • NPC / Game AI
    • Max Length
  14. 14

    What is Prompt Engineering

    6 subtopics
    • Be specific in what you want
    • Provide additional context
    • Use relevant technical terms
    • Use Examples in your Prompt
    • Iterate and Test your Prompts
    • Specify Length, format etc
  15. 15

    Tool Definition

    6 subtopics
    • Web Search
    • Code Execution / REPL
    • Database Queries
    • API Requests
    • Email / Slack / SMS
    • File System Access
  16. 16

    What is Agent Memory?

  17. 17

    Short Term Memory

  18. 18

    Long Term Memory

  19. 19

    Episodic vs Semantic Memory

    4 subtopics
    • RAG and Vector Databases
    • User Profile Storage
    • Summarization / Compression
    • Forgetting / Aging Strategies
  20. 20

    ReAct (Reason + Act)

  21. 21

    Model Context Protocol (MCP)

    3 subtopics
    • MCP Hosts
    • MCP Client
    • MCP Servers
  22. 22

    Creating MCP Servers

    2 subtopics
    • Local Desktop
    • Remote / Cloud
  23. 23

    Chain of Thought (CoT)

  24. 24

    RAG Agent

  25. 25

    Planner Executor

  26. 26

    DAG Agents

  27. 27

    Tree-of-Thought

  28. 28

    Manual (from scratch)

  29. 29

    LLM Native "Function Calling"

    22 subtopics
    • OpenAI Functions Calling
    • Gemini Function Calling
    • OpenAI Assistant API
    • Langchain
    • LlamaIndex
    • Haystack
    • AutoGen
    • CrewAI
    • Smol Depot
    • Anthropic Tool Use
    • Metrics to Track
    • Unit Testing for Individual Tools
    • Integration Testing for Flows
    • Human in the Loop Evaluation
    • LangSmith
    • Ragas
    • DeepEval
    • Structured logging & tracing
    • LangSmith
    • Helicone
    • LangFuse
    • openllmetry
  30. 30

    Prompt Injection / Jailbreaks

  31. 31

    Tool sandboxing / Permissioning

  32. 32

    Data Privacy + PII Redaction

  33. 33

    Bias & Toxicity Guardrails

  34. 34

    Safety + Red Team Testing