Evaluating AI Agents with Google ADK

seeders: 0
leechers: 0
Added 6 days ago by freecoursewb in Other

Download Fast Safe Anonymous
movies, software, shows...

Files

Evaluating AI Agents with Google ADK (Size: 308.2 MB)
  Bonus Resources.txt 102.4 B
  Get Bonus Downloads Here.url 204.8 B
  ~Get Your Files Here !
  01. Introduction
  01. Kickstart evaluation of AI agents with Google ADK.mp4 5.3 MB
  01. Kickstart evaluation of AI agents with Google ADK.srt 1.5 KB
  02. 1. Evaluate a Working AI Agent
  01. Project kickoff Running a procurement agent.mp4 10.8 MB
  01. Project kickoff Running a procurement agent.srt 4.8 KB
  02. When “correct” is dangerous A policy violation demo.mp4 14.2 MB
  02. When “correct” is dangerous A policy violation demo.srt 5.1 KB
  03. 2. Make the Agent Eval‑Ready
  01. ADK project structure and agent.yaml.mp4 16.6 MB
  01. ADK project structure and agent.yaml.srt 7.7 KB
  02. Binding tools to the agent.mp4 14.9 MB
  02. Binding tools to the agent.srt 5.5 KB
  03. Schema as a contract Pydantic enforcement.mp4 17.8 MB
  03. Schema as a contract Pydantic enforcement.srt 8.1 KB
  04. 3. Expose Logic Failures
  01. Trap mocks Forcing the agent to reason.mp4 12.3 MB
  01. Trap mocks Forcing the agent to reason.srt 5.7 KB
  02. Anatomy of a trace Thought, action, observation.mp4 9.7 MB
  02. Anatomy of a trace Thought, action, observation.srt 5.3 KB
  03. Visual debugging with ADK Trace View.mp4 13.1 MB
  03. Visual debugging with ADK Trace View.srt 5.8 KB
  05. 4. Formalizing Evaluation
  01. Capturing golden traces.mp4 12.1 MB
  01. Capturing golden traces.srt 4.4 KB
  02. Trajectory matching rules.mp4 14.9 MB
  02. Trajectory matching rules.srt 6.9 KB
  03. Testing memory Context persistence.mp4 12.6 MB
  03. Testing memory Context persistence.srt 7.2 KB
  04. Organizing EvalSets for scale.mp4 8.2 MB
  04. Organizing EvalSets for scale.srt 6.2 KB
  06. 5. Scaling Evaluation with Metrics
  01. Running headless eval batches.mp4 10 MB
  01. Running headless eval batches.srt 5.9 KB
  02. Interpreting scores Trajectory vs. semantic.mp4 8.6 MB
  02. Interpreting scores Trajectory vs. semantic.srt 6.4 KB
  03. Pass@k and non‑determinism.mp4 8.9 MB
  03. Pass@k and non‑determinism.srt 5.5 KB
  04. Reliability vs luck.mp4 10.1 MB
  04. Reliability vs luck.srt 5.2 KB
  07. 6. Judges, Guardrails, and Production Readiness
  01. LLM‑as‑a‑judge Custom rubrics.mp4 11.1 MB
  01. LLM‑as‑a‑judge Custom rubrics.srt 6.5 KB
  02. Groundedness and faithfulness checks.mp4 20.8 MB
  02. Groundedness and faithfulness checks.srt 9.7 KB
  03. Safe refusal via negative logic.mp4 14.3 MB
  03. Safe refusal via negative logic.srt 7 KB
  04. Regression gates in CICD.mp4 7.1 MB
  04. Regression gates in CICD.srt 4.7 KB
  08. 7. Synthesis and Next Steps
  01. Debugging playbook Prompt vs. tool vs. model.mp4 11 MB
  01. Debugging playbook Prompt vs. tool vs. model.srt 7.4 KB
  02. From vibe checks to verifiable agents.mp4 7.1 MB
  02. From vibe checks to verifiable agents.srt 5.9 KB
  03. Congratulations and keep going.mp4 3.1 MB
  03. Congratulations and keep going.srt 1.1 KB
  04. First eval Did the agent call the right tool.mp4 17.3 MB
  04. First eval Did the agent call the right tool.srt 7.4 KB
  03. Why final answers lie for agents.mp4 7.4 MB
  03. Why final answers lie for agents.srt 4.8 KB
  04. Paths, not strings Execution trajectories.mp4 9 MB
  04. Paths, not strings Execution trajectories.srt 4.5 KB

Description


Evaluating AI Agents with Google ADK
https://WebToolTip.com
Released 6/2026

With Jigyasa Grover

MP4 | Video: h264, 1280x720 | Audio: AAC, 44.1 KHz, 2 Ch

Skill level: Intermediate | Genre: eLearning | Language: English + subtitle | Duration: 2h 25m | Size: 308.3 MB
Master a deterministic framework for building, auditing, and scaling production‑grade AI agents using trajectory‑based evaluation and the Google Agent Development Kit (ADK).
Course details

AI agents are transforming how organizations automate complex workflows, but deploying them reliably requires rigorous evaluation methods that go beyond traditional testing. In this course, instructor Jigyasa Grover teaches you how to build production-grade AI agents using the Google Agent Development Kit (ADK) with a focus on deterministic evaluation, trace analysis, and safety guardrails. Learn how to design eval-ready architectures using structured tool interfaces and Pydantic schemas, then audit agent reasoning through trajectory matching and Golden Trace baselines. Jigyasa shows you how to implement scalable benchmarking with headless batch evaluations, Pass@k reliability tests, and LLM-as-a-Judge scoring systems. Explore production safety patterns, including groundedness checks, negative logic guardrails, and CI/CD regression gates that ensure your agents behave reliably at scale. By the end of this course, you'll be equipped with hands-on experience architecting, debugging, and evaluating AI agents ready for real-world deployment.
Skills covered

AI Agents, Google Agent Development Kit (ADK), AI Evaluation, Agentic AI Development

Related Torrents

torrent name size uploader age seed leech
1