- What Does It Mean to Debug?
- The First Divergence
- Evidence Before Explanation
- The Debugging Stack
- From Prompt Demo to AI Debugger
- Reading Python Exceptions
- Inspect State, Don't Guess
- Debug the Boundary
- Assertions, Invariants, and Contracts
- Environment Bugs
- The Notebook Is Not the Program You See
- Hidden Notebook State
- Reproducible Notebooks
- Debug the Data Before the Model
- Shapes, Types, Devices, and Tensors
- When Training Goes Wrong
- Debugging Evaluation
- Debugging What You Cannot See
- Is the Model Actually the Problem?
- Inspect the Actual Model Input
- Context Windows and Truncation
- Sampling Is Part of the Program
- Internal Signals
- Representation and Behavioral Diffs
- AI as Builder, Designer, Researcher, and Reviewer
- Debugging Intent
- Debugging Context for Coding Agents
- Debugging AI-Generated Designs
- Debugging AI Research
- Debugging Coding Agents
- Treat Prompts as Programs
- Minimize the Prompt
- Retrieval Is a Pipeline
- Retriever Failure or Generator Failure?
- Debugging Hallucinations
- The Model's Explanation Is Not a Trace
- An Agent Is a Trajectory
- Trace the Agent
- Agent Failure Taxonomy
- Loops, Thrashing, and Retry Storms
- Time Travel, Replay, and Forking
- Causal Replay
- Trajectory Diff
- Multi-Agent Systems
- Can One AI Debug Another?
- The AI Crash Dump
- Diagnostic AI Invariants
- From Symptom to Hypotheses
- Discriminating Experiments
- How Do You Know the Diagnosis Is Right?
- AIDebugBench
- Debug the Debugger
- AI Observability
- From Production Failure to Regression
- Runtime Invariants and Guardrails
- Debugging Cost and Latency
- Debugging in Production
- The Ten-Minute Debug
- The One-Hour Investigation
- The Full AI Incident Investigation
- The Debugging AI Toolkit
- Signs, Not Directions: Compiling AI Policy into Visual Artifacts
- ZeroModel: Visual AI you can scrutinize