Company News
Reports from VAIL on agent behavior, model integrity, and verifiable AI.
Reports
- Sep 21, 2026
-
Sep 11, 2026
Who You Gonna Call? Evaluating Tool Calling Reliability and Behavior
Serving stacks change tool calling reliability and accuracy. Benchmarks can’t measure failure in live deployments.
-
Aug 2, 2026
From Provenance to Continuous Verification
Cisco’s AI Supply Chain Provenance Explorer strengthens the evidence available before deployment. Model Informatics extends verification into runtime.
-
Jul 15, 2026
Measuring the Integrity of Infrastructure for Frontier Intelligence
What happens to older Claude models when a newer one ships and why "pin the version" isn't the safety net you think it is.
-
Apr 13, 2026
Misbehaving Agents & The Impacts of Extreme Instability
Endpoints with extreme levels of behavioral instability show high levels of task instability compared to peer endpoints serving the same nominal model.
-
Mar 11, 2026
Introducing Stability Arena and The Seven Metrics of Model Hosting
Why Latency, Throughput, Error Rate, and Cost Are No Longer Enough
-
Jan 16, 2026
Reliability ≠ Stability
We shouldn't assume reliable model APIs mean we are getting intelligent outputs.
-
Dec 24, 2025
Building a Vocabulary for AI Assurance
Part II: Establishing Ground Truth via Verifiability and Accuracy
-
Dec 15, 2025
Building a Vocabulary for AI Assurance
Part I: Making Sense of Explainability and Interpretability
-
Sep 19, 2025
What is Model Informatics? What does it mean to "Verify" AI?
We first started exploring verifiability almost 3 years ago and first shared a few initial ideas in early 2024.
-
Mar 3, 2025
Agents, Task Time Compute, & Task Time Marketplaces
Agents coordinating to complete complex, multi-step tasks for users and using a marketplace to bid out individual tasks to specialty agents.
-
Jan 17, 2025
The Security Evolution of Core Technologies: What It Means for AI (Part I)
There is a consistent pattern of increasing the robustness of security features and capabilities for core computing technologies. AI shouldn’t be any different.
-
Nov 11, 2024
Product Development in the Age of AI
Developing on top of probabilistic compute changes how we build software, software products, and eventually anything.
-
Oct 3, 2024
Transparency vs Interpretability
While we may not know how a model generates its result, we should still know what was asked of the model to get the result.
-
Jul 26, 2024
Which model am I getting?
Just reviewing outputs from a model won't tell you which model you're using. Even if your API provider is telling you which model you're using, you have very little ability to know if that's true.
-
Jul 1, 2024
VAIL Use Case: Verifiable Evals
How can you prove a model passed an eval with the reported score?
- Jun 21, 2024
-
Mar 18, 2024
The Need for Public Goods Infrastructure for AI
What is it, who leads it, and why it matters.
-
Feb 24, 2024
Part 4: Stochastic Computation needs Verifiable Computing
A credibly neutral system to verify inputs and outputs from AI-based systems.
- Feb 23, 2024