Skip to main content

Order Desk

Blocks start, basics, junior

Expanding existing materials

  • Supplementing current materials
  • Module on real-world agent case studies by industry
  • Module on prompt caching

Senior Block

Resources for studying AI Agents

  • other one-stop shops to study AI Agents
  • Must-read papers
  • Onthological papers
  • Upfront papers

User interface development

  • Rapid UI development
  • Voice bots

Infrastructure and DevOps

  • Production Infrastructure

Advanced prompting

  • Senior-lvl prompting
  • APEs (Autonomous Programming Engines)

RAG advanced level

  • Agentic RAG
  • Hybrid RAG
  • Subtopic node
  • Graph RAG
  • Reranking
  • RAG evaluation
  • Caching

Multi-Agent systems

  • MultiAgents theory
  • Conflict resolution between agents
  • Protocols:
    • MCP (Multi-agent Communication Protocol)
    • ANP (Agent Negotiation Protocol)

Memory theory

  • Memory theory

Testing and evaluation of agents

  • Benchmarks:
    • Popular benchmarks
    • How to create your own
    • Errors in benchmarking
  • Performance monitoring
  • Feedback learning
  • Online evaluation
  • E2E testing
  • ToolChoiceE

Cloud solutions

  • AWS SageMaker AI Agents
  • Google Vertex AI

Extra Block

Business aspects

  • Business insides
  • Business cases

Technology landscape

  • LandScape A2A protocols
  • LandScape AgentOps Infrastructure
    • tracing
    • monitoring
    • logging
    • metrics
    • alerting
    • dashboarding
    • prompt engineering platforms
    • benchmark platforms

Model training

  • fine-tuning models: RL vs PEFT vs P-Tuning
  • fine-tuning models for tool using

Model Deployment

  • Using your own LLM in production: vLLM and friends
  • Using your own LLM in the cloud:
    • serverless solutions vs kubernetes
    • model garden
    • fine-tuning AWS, GCP, Azure, YC, OpenAI

Blocks Not-Agents

  • Improving materials in the light backend development block

Suggest your ideas in the comments!