Agent Incident Review
A structured process for reviewing failed AI agent runs and turning traces into controls, fixtures, owners, follow-up tests, and safer workflows.
Expanded incident process Updated 2026-06-12
Practical guides
Guides
Readable, action-oriented guides for teams that need AI output to be checked, logged, and turned into workflow value.
Agent Observability Guide
A practical observability model for AI agents that use tools, retrieval, state, retries, approvals, and human review in production workflows.
Expanded guide Updated 2026-06-12
Agent Permission Design
How to design AI agent permissions with read, draft, write, approval, rollback, and audit boundaries before production use or team rollout safely.
Expanded guide Updated 2026-06-12
Agent Reliability Scorecard
A scoring model for agent permissions, evidence, recovery, data exposure, and human review.
Scorecard Updated 2026-05-31
AI Agent Failure Modes
A field guide to common AI agent failures, the controls that reduce them, and the evidence reviewers need before launch, rollout, or incident review.
Expanded risk guide Updated 2026-06-12
AI Code Review Checklist
A practical checklist for reviewing AI-assisted code changes with scoped diffs, tests, security checks, and evidence before final merge approval.
Expanded checklist Updated 2026-06-12
AI Code Review Prompts
Prompt patterns for focused AI code review that ask for high-risk bugs, line evidence, reproduction steps, missing tests, and confidence notes.
Expanded prompt guide Updated 2026-06-12
AI Code Verification Tests
A practical guide to turning AI-generated code into testable behavior with regression tests, boundary checks, and evidence-focused review notes.
Expanded guide Updated 2026-06-12
AI Documentation Review
A documentation review guide for checking AI-written docs against source behavior, examples, links, version notes, and reviewer evidence before publishing.
Expanded guide Updated 2026-06-12
AI Hallucination Testing Guide
A practical hallucination testing process for finding unsupported claims, weak refusals, weak citations, and source-faithfulness failures early.
Expanded guide Updated 2026-06-12
AI Pilot Readiness Checklist
A practical AI pilot readiness checklist for scope, users, success metrics, data boundaries, validation, rollout gates, and stop conditions.
Expanded checklist Updated 2026-06-12
AI Readiness for Teams
An AI readiness guide for teams covering workflow fit, data boundaries, review capacity, tool ownership, risk controls, and pilot evidence first.
Expanded guide Updated 2026-06-12
AI Summary Verification
A summary verification guide for checking AI summaries against sources, preserving caveats, detecting omissions, and logging reviewer decisions.
Expanded guide Updated 2026-06-12
AI Tool Change Log Process
A change log process for tracking AI tool approvals, risks, owners, data access, workflow changes, validation evidence, and renewal decisions.
Expanded operating pattern Updated 2026-06-12
AI Tool Privacy Checklist
A privacy checklist for evaluating AI tools before uploading customer data, source code, employee records, strategy notes, or private documents.
Expanded checklist Updated 2026-06-12
AI Tools for Product Managers
A practical guide to AI tools for product managers, focused on research, specs, prioritization, review gates, and source-backed decisions at work.
Expanded tool selection guide Updated 2026-06-12
AI Tools for Startup Founders
A founder guide to AI tools for startup work, covering research, support, coding, operations, automation, privacy, and verification gates for teams.
Expanded tool selection guide Updated 2026-06-12
AI Workflow Automation for Startups
How startups can automate AI workflows with clear owners, narrow permissions, review gates, evidence logs, and measurable operational wins safely.
Expanded guide Updated 2026-06-12
AI-Generated Code Testing
A practical testing workflow for AI-generated code that covers expected behavior, edge cases, regression checks, and reviewer confidence before merge.
Expanded guide Updated 2026-06-12
Benchmark Methodology
A benchmark methodology guide for creating fair AI tool evaluations with frozen fixtures, dated evidence, scoring rubrics, and retest rules.
Expanded methodology Updated 2026-06-12
Eval Rubric Design
A practical guide to designing AI evaluation rubrics with clear scoring dimensions, weights, failure labels, and decision thresholds for teams.
Expanded framework Updated 2026-06-12
How to Choose an AI Coding Assistant
A buyer and operator guide for choosing AI coding assistants by workflow fit, privacy boundary, validation burden, and reviewer effort in practice.
Expanded tool selection guide Updated 2026-06-12
How to Reduce Hallucinations in LLM Apps
A practical system design checklist for reducing unsupported LLM claims with retrieval, refusal behavior, verification, and review controls.
Expanded guide Updated 2026-06-12
How to Verify AI-Generated Code
A practical guide for reviewing AI-generated code with behavior checks, scoped diffs, tests, security review, and merge evidence notes for teams.
Expanded core guide Updated 2026-06-12
Human-in-the-Loop AI Workflows
Where human review belongs in AI coding, RAG, agent, support, and documentation workflows, with approval gates, evidence checks, and owner roles.
Expanded guide Updated 2026-06-12
LLM Evaluation Framework
A practical LLM evaluation framework for testing correctness, faithfulness, format compliance, safety, latency, and human review effort before launch.
Expanded framework Updated 2026-06-12
LLM Output Verification Guide
A practical workflow for checking LLM output against sources, tests, logs, and human review before using it safely in products or team decisions.
Expanded guide Updated 2026-06-12
MCP Workflow Guide
How to evaluate MCP-style tool connections for AI workflows with narrow permissions, logging, approval gates, and data exposure controls before launch.
Expanded guide Updated 2026-06-12
Model Pricing Change Tracker
A model pricing change tracker workflow for monitoring plan changes, source evidence, affected pages, retest needs, and update decisions over time.
Expanded operating pattern Updated 2026-06-12
Product Manager AI Research Workflow
A product manager AI research workflow for source-backed discovery, synthesis, opportunity notes, stakeholder review, and decision evidence.
Expanded workflow guide Updated 2026-06-12
Prompt Testing Framework
A practical framework for testing prompt variants with frozen fixtures, model settings, scoring rubrics, failure labels, and review notes for teams.
Expanded framework Updated 2026-06-12
RAG Evaluation Checklist
A practical checklist for evaluating RAG retrieval quality, source faithfulness, citations, no-answer behavior, latency, and human review effort.
Expanded checklist Updated 2026-06-12
RAG No-Answer Testing
A practical guide to testing whether a RAG system refuses unsupported, missing-source, ambiguous, stale, or out-of-policy questions safely today.
Expanded guide Updated 2026-06-12
Source-Backed AI Writing
A source-backed AI writing workflow for claims, citations, drafts, verification, reviewer notes, and publication decisions without invented evidence.
Expanded guide Updated 2026-06-12
Startup AI Stack Guide
A startup AI stack guide for choosing lean tools across coding, research, support, content, analytics, automation, and governance without sprawl.
Expanded tool selection guide Updated 2026-06-12
Weekly AI Workflow Operating System
A weekly operating system for reviewing AI workflows, incidents, evidence, tool changes, owner actions, and measurable reliability improvements.
Expanded operating system Updated 2026-06-12
What Is an AI Agent?
A practical definition of AI agents focused on goals, tools, state, permissions, evidence, stop rules, and operator review for real workflows.
Expanded guide Updated 2026-06-12