Claude Agent SDK [Full Workshop] — Thariq Shihipar, AnthropicUnderstand agent/harness choices, scoped access and verification. Long SDK workshop; recommend relevant sections, not exact book folder/check.py configuration.
Open video
Taming Rogue AI Agents with Observability-Driven Evaluation — Jim Bennett, GalileoTurn observed production failures into evaluations and feedback. Galileo/agent examples, not book's dashboard, database or retention policy.
Open video
Prompting 101 | Code w/ ClaudeConstruct prompts with task context, examples and output formatting. Not the book's one-change five-input test.
Open video
Claude Managed Agents and Evolution of Agentic Surfaces — Gagan Bhat & Isabella Kai He, AnthropicDistinguish model reasoning, the harness and tool execution. Technical vendor-specific companion, not comparison of the three book harnesses; no adoption of performance claims.
Open video
How to Build AI Governance in 5 Practical Steps Real UsecaseStart governance with an inventory and connect it to risk and monitoring. General governance, not current EU legal advice or deputy-drill proof.
Open video
Securing AI Agents: How to Prevent Hidden Prompt Injection AttacksRecognise indirect prompt injection in material an agent reads. Trap recognition only; not anonymisation or disclosure.
Open video
Learn 80% of OpenCode Desktop in 20 Minutes! | Full Beginner TutorialDesktop setup, model selection and Plan/Build workflow. Undo/Redo not verified; publication dates conflict; screens and model availability may differ.
Open video
Deep Dive into LLM Evaluation with Weights & BiasesSeparate retrieval evaluation from answer evaluation in RAG. Developer-oriented older tooling; model judges supplement human-confirmed answers.
Open video
Confidence metrics used in the AlphaFold Database multimersRead local, positional and interface confidence rather than trust structure images. AFDB multimer context, not Server submission; short-peptide limits require current docs.
Open video
Cellpose SAM TutorialUnderstand cellular segmentation and pretrained Cellpose-SAM. Not hand-counting protocol; research performance not a guarantee for learner images.
Open video
Connecting Claude Securely to Microsoft 365Connector administration, app registrations and audit logs. Entra logs do not prove complete MCP tool-call logging, per-person isolation, minimisation or retirement.
Open video
Open-Source Spotlight - Pandera - Niels BantilanDeclare table schemas, types and checks before accepting data. Historical APIs; not permissions/freshness checks. Separately flagged manuscript error: 1 mg/L equals 1 µg/mL, not a thousandfold change.
Open video
Python Tutorial: UV - A Faster, All-in-One Package Manager to Replace Pip and VenvReproduce Python environments with locks and sync. Does not validate analysis choices, exclusions or numeric results.
Open video
Learn to Automate Everything with Power Query in Excel (Download Files)Record cleaning transformations and refresh folder imports. Not unit-conversion rules, row accounting or handover.
Open video
How to Use Claude for Excel (Step-by-Step Tutorial)Ask Claude to summarise and analyse spreadsheet data. Excel add-in rather than file upload; independent recount/reconciliation not established; use synthetic copy.
Open video
Implement Authorization using Row Level Security (RLS) with Supabase (Step By Step Guide)Implement database row-level access policies. Historical interface; RLS alone not field restrictions, hosting security or restoration.
Open video
LiteLLM AI Gateway: Routing, API Keys, Budgets, and Guardrails for Local and Cloud ModelsScope gateway keys and set budgets. Logging/guardrails explicitly not covered despite title. No endorsement of shared-key practices.
Open video
Strategyzer Webinar: The Basics Of Testing Business IdeasChoose a hypothesis, design an experiment, run it and learn from results. Business experimentation, not AI-specific data permissions, rollback or stop controls.
Open video