📖

Agent Skills (SKILL.md): Writing Your First Skill

reading · M1 · 15 min

Preview

📖

Choosing the Three HITL Modes: Suggest, Approve, Co-Pilot

reading · M2 · 15 min

Preview

📖

Chunking Strategy for Real Documents

reading · M3 · 15 min

Preview

📖

Citing Sources So Stakeholders Trust the Agent

reading · M4 · 15 min

Preview

📖

Designing the Human's UI: Slack, Teams, and Embedded Approvals

reading · M5 · 15 min

Preview

📖

Feedback Loops: Turning Human Edits into Training Data

reading · M6 · 15 min

Preview

📖

Fine-Tuning a Small Model for Tool-Call Reliability

reading · M7 · 15 min

Preview

📖

Helicone as the Drop-In Proxy

reading · M8 · 15 min

Preview

📖

LLM-as-Judge Calibration Without a PhD

reading · M9 · 15 min

Preview

📖

MCP Servers in Practice: Atlassian, Stripe, Notion, Slack, Zapier

reading · M10 · 15 min

Preview

📖

MCP vs. Custom Tool vs. Skill: Picking the Right Packaging

reading · M11 · 15 min

Preview

📖

Pairing an Agent Observability Platform with Datadog or Honeycomb

reading · M12 · 15 min

Preview

📖

Permission Scoping: The Tool the Agent Should Not Have

reading · M13 · 15 min

Preview

📖

Picking a Vector Store Without Becoming an Engineer

reading · M14 · 15 min

Preview

📖

Post-Call Guardrails with Guardrails AI or NeMo Guardrails

reading · M15 · 15 min

Preview

📖

Pre-Call Guardrails: PII Stripping and Prompt Injection Defenses

reading · M16 · 15 min

Preview

📖

Regression Detection: Catching the Day the Agent Got Dumber

reading · M17 · 15 min

Preview

📖

Synthetic Eval Generation for Edge Cases

reading · M18 · 15 min

Preview

📖

The Decide-vs-Predefine Decision

reading · M19 · 15 min

Preview

📖

The Eval-and-Red-Team Platform Consolidation: Promptfoo, OpenAI, and the Build-vs-Buy Inflection

reading · M20 · 15 min

Preview

📖

The First Time You Build an Agent Loop in Lindy, Relevance AI, or n8n LangChain

reading · M21 · 15 min

Preview

📖

The Four-Layer Eval Recipe

reading · M22 · 15 min

Preview

📖

The Indirect Prompt Injection Playbook

reading · M23 · 15 min

Preview

📖

The MCP Credential Trap

reading · M24 · 15 min

Preview

📖

The Re-Ranker Step Most Builders Skip

reading · M25 · 15 min

Preview

📖

The Reasoning-vs-Tool-Restraint Trade-off

reading · M26 · 15 min

Preview

📖

The 'Refuse to Act' Pattern for High-Stakes Tools

reading · M27 · 15 min

Preview

📖

The Three Dashboards Every Agent Needs

reading · M28 · 15 min

Preview

📖

The Warehouse-Agent Control Plane: Snowflake Cortex, Databricks Genie, and dbt MCP

reading · M29 · 15 min

Preview

📖

Tool Boundary Design: Fewer, Better, Named Right

reading · M30 · 15 min

Preview

📖

Tool Idempotency and the 'Run Twice' Problem

reading · M31 · 15 min

Preview

📖

Tracing an Agent Run in LangSmith, Langfuse, or Arize Phoenix

reading · M32 · 15 min

Preview

📖

Wrapping a SaaS API as an Agent Tool

reading · M33 · 15 min

Preview

📖

Writing Your First Eval Set in Braintrust, LangSmith, or Langfuse

reading · M34 · 15 min

Preview