Changelog · field notes
Dispatches on behavior, agents, and memory.
ARCHITECTURE
APR 25 · 2026 · 9 MIN READ
What is behavioral observability?.
Behavioral observability is the practice of detecting how an AI agent behaves across sessions and users, not just whether each LLM call succeeded. Here is the definition, the signals, and how it differs from execution observability.
APR 10 · 10 MIN
How to detect agent drift in production.
Agent drift is the failure mode every AI team talks about and nobody measures. Here is how to detect it, which signals matter, and how structured memory stops it.
MAR 15 · 5 MIN
How to integrate Flowlines in 5 minutes.
Add behavioral observability and structured memory to any Python AI agent. Install the SDK, init before your LLM client, wrap calls in context, and retrieve memory. Works with OpenAI, Anthropic, and any agent framework.