Garage Education
  • Home
  • Courses
  • Blog
ESC

Searching...

No results found

↑↓ Navigate ↵ Select
Powered by Hugo Blox
  • Courses
    • Agent Harness with Spring AI
      • Start here
        • Front matter
        • Glossary
      • Part 1: Foundations
        • 1. Why a harness?
        • 2. Project setup
        • 3. The model call
        • 4. Tools
      • Part 2: The Loop
        • 5. The agent loop by hand
        • 6. Termination
        • 7. Guardrails
        • 8. Graphs
        • 9. Human-in-the-loop
      • Part 3: Memory and Retrieval
        • 10. Short-term memory
        • 11. Embeddings and hybrid storage
        • 12. Hybrid retrieval
        • 13. Retrieval quality
      • Part 4: Skills and Agents
        • 14. Skills as files
        • 15. Skill selection
        • 16. Sub-agents
        • 17. Agent selection
        • 18. Context isolation
      • Part 5: Observability, Evaluation, and Cost
        • Topics
        • 19. Step logging
        • 20. A small eval set
        • 21. Failure drills
        • 22. Cost optimization
      • Part 6: Durable Execution with Temporal
        • Part 6 overview
        • 23. Run state and messages
        • 24. Temporal basics
      • Part 7: Capstone
        • 25. Assemble the watcher
      • About this course
        • Progress and changelog
    • Apache Spark
      • Course Introduction
      • Python Vs. Scala
      • Introduction
      • About Databricks
      • Spark In The Data Platforms
      • Running Spark
      • Demo: Running Spark on Linux Ubuntu
      • Demo: Running Spark on MacOS
      • Demo: Running Spark on Windows
      • Demo Running Spark On Databricks
      • From Map Reduce To Spark
      • Spark Characteristics
      • Spark Applications
      • Spark Driver
      • Spark Session
      • Spark Cluster Manager
      • Spark Execution Mode
      • Spark Executors
      • Spark Data Partitioning
      • Spark Operations
      • Transformations Narrow Vs Wide
      • Demo: Immutability In Spark
      • Demo: RDD Text Manipulation
      • Demo: GroupByKey Vs. ReduceByKey
      • Demo: Joining RDDs
      • Demo: RDD Operations Part 1
      • Demo: Repartition Vs. Coalesce
    • Data Modeling
      • Introduction to Data Modeling
      • Fact Tables
      • Schema Types
      • Surrogate vs Natural Keys
      • Partitioning vs Bucketing
      • Kimball vs Inmon
      • Dimension Types
        • Conformed Dimension
        • Degenerated Dimension
        • Junk Dimension
        • Role Playing
        • Outrigger Dimension
        • Snowflake Dimension
        • Slowly Changing Dimension
        • Fast Changing Dimension
        • Shrunken Changing Dimension
        • Multi Valued Dimension
        • Swappable Dimension
        • Heterogeneous Dimension
    • Containerization
      • Short-lived containers
      • Long-lived containers
      • More than 1 container app
    • Big Data Engineering in Depth
      • Course Introduction
        • Introduction
        • Max Benefit
        • Assignments, Labs, & Textbooks
        • Course Content Overview
      • Data Warehouse
        • Introduction To Data Management
        • Data Abstraction
        • Data Warehouse Components
    • Hadoop and Distributed Systems
      • Introduction To Distributed Systems
      • Hadoop
      • HDFS
      • YARN
      • Map Reduce
      • Hive
  • Blog
  • Still need help?
  • Join Discord ↗
  • Agent Harness with Spring AI
    • Start here
      • Front matter
      • Glossary
    • Part 1: Foundations
      • 1. Why a harness?
      • 2. Project setup
      • 3. The model call
      • 4. Tools
    • Part 2: The Loop
      • 5. The agent loop by hand
      • 6. Termination
      • 7. Guardrails
      • 8. Graphs
      • 9. Human-in-the-loop
    • Part 3: Memory and Retrieval
      • 10. Short-term memory
      • 11. Embeddings and hybrid storage
      • 12. Hybrid retrieval
      • 13. Retrieval quality
    • Part 4: Skills and Agents
      • 14. Skills as files
      • 15. Skill selection
      • 16. Sub-agents
      • 17. Agent selection
      • 18. Context isolation
    • Part 5: Observability, Evaluation, and Cost
      • 19. Step logging
      • 20. A small eval set
      • 21. Failure drills
      • 22. Cost optimization
    • Part 6: Durable Execution with Temporal
      • Part 6 overview
      • 23. Run state and messages
      • 24. Temporal basics
    • Part 7: Capstone
      • 25. Assemble the watcher
    • About this course
      • Progress and changelog
  • Apache Spark
    • Course Introduction
    • Python Vs. Scala
    • Introduction
    • About Databricks
    • Spark In The Data Platforms
    • Running Spark
    • Demo: Running Spark on Linux Ubuntu
    • Demo: Running Spark on MacOS
    • Demo: Running Spark on Windows
    • Demo Running Spark On Databricks
    • From Map Reduce To Spark
    • Spark Characteristics
    • Spark Applications
    • Spark Driver
    • Spark Session
    • Spark Cluster Manager
    • Spark Execution Mode
    • Spark Executors
    • Spark Data Partitioning
    • Spark Operations
    • Transformations Narrow Vs Wide
    • Demo: Immutability In Spark
    • Demo: RDD Text Manipulation
    • Demo: GroupByKey Vs. ReduceByKey
    • Demo: Joining RDDs
    • Demo: RDD Operations Part 1
    • Demo: Repartition Vs. Coalesce
  • Data Modeling
    • Introduction to Data Modeling
    • Fact Tables
    • Schema Types
    • Surrogate vs Natural Keys
    • Partitioning vs Bucketing
    • Kimball vs Inmon
    • Dimension Types
      • Conformed Dimension
      • Degenerated Dimension
      • Junk Dimension
      • Role Playing
      • Outrigger Dimension
      • Snowflake Dimension
      • Slowly Changing Dimension
      • Fast Changing Dimension
      • Shrunken Changing Dimension
      • Multi Valued Dimension
      • Swappable Dimension
      • Heterogeneous Dimension
  • Containerization
    • Short-lived containers
    • Long-lived containers
    • More than 1 container app
  • Big Data Engineering in Depth
    • Course Introduction
      • Introduction
      • Max Benefit
      • Assignments, Labs, & Textbooks
      • Course Content Overview
    • Data Warehouse
      • Introduction To Data Management
      • Data Abstraction
        • Introduction
        • Physical Layer
        • Logical Layer
        • View Layer
        • Data Solution Thinking
      • Data Warehouse Components
        • Motivation
        • DWH VS Transactional DB
        • Business Types
        • Use cases
        • Multi-temperature Storage
        • Characteristics & Components
        • Source System Integration Process
        • Source System Extraction
        • Staging Layer
        • Data Modeling
        • Introduction to Data Modeling
        • ETL
        • Fact Tables
        • Schema Types
        • Dimension Types
  • Hadoop and Distributed Systems
    • Introduction To Distributed Systems
    • Hadoop
    • HDFS
    • YARN
    • Map Reduce
    • Hive
  • Still need help?
  • Join Discord ↗

On this page

  • Topics
Courses
Agent Harness with Spring AI
Part 5: Observability, Evaluation, and Cost

Part 5: Observability, Evaluation, and Cost

Step logging, a small eval set, failure drills, and cost optimization.

Topics

  1. Chapter 19: Step logging
  2. Chapter 20: A small eval set
  3. Chapter 21: Failure drills
  4. Chapter 22: Cost optimization
docs
Last updated on Oct 10, 2026

© 2026 Garage Education. This work is licensed under CC BY NC ND 4.0

Made with Hugo Blox Kit. Build yours →