Trusted AI
Subscribe
Sign in
Home
Governance
Observability
Resources
Archive
About
Observability
The Metric Is Not Cost Per Token
AI unit economics and what you pay for each task it gets right
Oct 31
•
Jon Knisley
2
Can You Prove What Your Agent Did?
Building agent records that hold up with auditors and regulators
Oct 17
•
Jon Knisley
6
1
You Cannot Evaluate an Agent by Its Answer
Trajectory-level evaluation and why turn-level scoring hides the failures that matter
Sep 30
•
Jon Knisley
3
The Feedback Gap
How in-product flags, annotation programs, and RLHF-style pipelines turn feedback into safer, smarter AI systems
May 27
•
Jon Knisley
4
Evaluating Generative AI: Practical Tests for Safety, Bias and Fairness
How to assess toxicity, hallucinations, representational harms and group fairness
May 16
•
Jon Knisley
3
Stop Guessing: How to Evaluate Modern LLM Applications
A practical framework for measuring what matters across prompts, retrieval, and tool behavior
May 11
•
Jon Knisley
3
Your AI Passed Testing. Will It Survive Production?
Experiments, staged rollouts, and runtime guardrails that turn deployment risk into repeatable control
May 2
•
Jon Knisley
3
Why Most LLM Evaluations Fail Before Production
How to build test sets, use synthetic data wisely, and trust LLM-as-a-judge without fooling yourself
Apr 25
•
Jon Knisley
3
The Wrong Scorecard: Why Most Organizations Are Failing at AI Evaluation
A decision framework for investing evaluation resources where they matter most
Apr 19
•
Jon Knisley
3
Your AI is Running. But is It Working?
The observability stack that makes AI systems debuggable, auditable, and improvable
Apr 9
•
Jon Knisley
3
From ML Monitoring to AI Observability: What Changes with LLMs and Agents
Closing the visibility gap that separates AI leaders from liabilities
Mar 31
•
Jon Knisley
4
1
This site requires JavaScript to run correctly. Please
turn on JavaScript
or unblock scripts