Moyai Mail
Writing on observability and modern software engineering from the agent reliability people.
The missing oysters: unverified tool output when every component passes its own tests
This blog is part of a series on common failure modes of agents. How do they occur despite following best practices? And why do they often go unnoticed? In this edition: unverified tool output, where the agent takes a tool result at face value without verifying it against available information. With potentially expensive consequences.
A short and sweet guide to choosing an agent observability platform
Most buyer guides for agent observability are marketing from the platforms themselves. Here is our short and sweet take on which platform to pick, depending on your stack, budget and industry.

The unauthorised refund: detecting goal misinterpretation when your traces look clean
This blog is part of a series on common failure modes of agents. How do they occur despite following best practices? And why do they often go unnoticed? In this edition: goal misinterpretation, where the agent misunderstands the intent and optimises for the wrong objective. With potentially expensive consequences.

Reproducing LLM-as-a-Verifier with open-source models on Terminal-Bench 2.0
We reproduce the verification results from LLM-as-a-Verifier with GLM-5.2, testing continuous score distributions, repeated evaluations, and criteria decomposition on Terminal-Bench 2.0.

Behind the Myth: Can One API Call Rule Them All? (Part 1/2)
OpenRouter's Fusion plugin collapses a three-judge deliberation panel into a single model call. Part 1 puts our old and new checker agents head to head on speed, and asks whether one call is really faster than three.

Mission defines strategy, and strategy defines structure
How our five phase pipeline revealed a bigger image on its own, and what that teaches us about context engineering across agent boundaries

Robustness through meaning - one triple at a time
Exploring how ontologies cross-validate with LLMs, making robust failure detection in agentic systems. Why this is a different approach than Palantir's operational ontology.

Can Your Prompts Optimize Themselves?
Exploring how DSPy's declarative approach to prompt engineering replaces hand-crafted templates with Bayesian-optimized programs and what happens when you apply it to a real failure detection pipeline.

See what Moyai finds in your traces. First agent scan is free.