Software notes for teams building real systems.

Browse by workstream, open a focused guide, or search the library when you already know what you need.

Choose the workstream that matches the problem.

Browse practical notes by topic and need.

  1. AI Agent Context Budget: Allocate Tokens by Evidence ValueArtificial Intelligence
  2. Agent Context Provenance: Show Where Every Instruction and Fact Came FromArtificial Intelligence
  3. Structured Outputs for AI Agents: Version, Validate and RecoverArtificial Intelligence
  4. LLM Gateway Build vs Buy: A Control-Plane Decision for Enterprise AIArtificial Intelligence
  5. AI Model Routing: Match Each Agent Step to the Right ModelArtificial Intelligence
  6. AI Agent Evaluation Scenarios: Test the Workflow, Not Just the AnswerArtificial Intelligence
  7. OpenTelemetry AI Agent Tracing: Models, Tools and HandoffsArtificial Intelligence
  8. AI Agent Approval UX: What Reviewers Must See for High-Risk ActionsArtificial Intelligence
  9. AI Agent Sandbox: Isolation for Code, Files and BrowsersArtificial Intelligence
  10. Agent Workflow Compensation for Multi-Agent TransactionsArtificial Intelligence