🗓️ Agentic AI Workshop Schedule Overview

🗓️ Agentic AI Workshop Schedule Overview#

Day 1: Foundations (LLMs, Prompts, Agent Mindset)#

  • Core Notebooks:
    1_0_dev_quick_start, 1_1_prompt_engineering, 1_2_model_selection, 2_0_agents_overview, 2_1_agent_design_foundations, 1_6_conversational_state

  • Activities:

    • Use-case kickoff & team formation

    • Run basic OpenAI API calls

    • Write and iterate prompts

    • Select a model and justify choice

    • Draft Agent PRD & initial system prompt

    • (Stretch) Try multi-turn memory

  • Optional:
    1_3_prototype_to_production, 3_3_reasoning_models

Day 2: SDK, Building, RAG, Tools & Visualization#

  • Core Notebooks:
    2_2_openai_agents, 2_3_quick_start, 2_4_building_agents, 2_5_running_agents, 2_6_tools, 1_5_function_calling, 1_12_embeddings, 1_13_retrieval, 2_14_visualization, 2_15_agent_output

  • Activities:

    • SDK install & Hello World agent

    • Add tools, function calling

    • Build RAG pipeline (embeddings, retrieval)

    • Visualize agent structure and orchestration

    • Review and analyze agent outputs

  • Optional:
    1_4_structured_outputs, 2_10_context_management, 1_7_streaming, 1_8_file_inputs

Day 3: Production Readiness (Safety, Guardrails, Observability)#

  • Core Notebooks:
    2_9_observability, 1_15_moderation, 3_1_safety, 2_11_guardrails, 3_2_prompt_caching, 3_0_production, 2_12_orchestration, 2_7_mcp, 2_8_handoffs

  • Activities:

    • Add moderation & guardrails

    • Trace & monitor agent runs

    • Test prompt caching, review scaling plans

  • Optional:
    3_5_reproducibility, 2_13_models

Day 4: Eval & Optimization#

  • Core Notebooks:
    1_14_evals, 3_6_evaluation_design, 3_4_accuracy_optimization

  • Activities:

    • Run automated evals & benchmark

    • Tweak prompts/RAG for accuracy

  • Optional:
    All multimodal/extras: 1_9_image_generation, 1_10_text_to_speech, 1_11_speech_to_text, 3_3_reasoning_models

Day 5: Demo, Polish, and Roadmap#

  • Core Notebooks:
    1_3_prototype_to_production, 3_5_reproducibility

  • Activities:

    • Final polish (handoffs, multimodal, UI) — if added by team

    • Review production checklist

    • Team demos & feedback

    • Roadmap planning, case study comparison

  • Optional:
    Case studies (4_legal_qa, etc.) and any Reference/Advanced content as needed

References (for all days):#

All advanced topics, multimodal (image/audio/speech), streaming, context management, model switching, file inputs, best practices, and case studies are available as reference for reading or demos at any point.

Contents