Understand the AI system you are building, buying, or operating.

Viewyonder connects what people experience in an AI application with the models, providers, data, identities, tools, and controls that make it work.

A system of surfaces and inference A layered graph connects chat, agent, harness, and IDE surfaces through server-side systems, tools, data, policies, identities, and unknown nodes to inference routes, models, and providers. An Injectionator trace follows one path through the system. Visible surfaces Application body Inference Chat Agent Harness IDE Server Router Tool Policy Data API Queue ID ID ID ID ? ? ? Route Model Provider Injectionator trace
Known node Identity Unknown Evidence trace

The work

One system. Two layers.

We follow what an AI application can do, and examine the inference choices that shape what it becomes.

AI application security

Surfaces

The application is the attack surface.

Surfaces is Viewyonder’s programme for investigating the whole AI application: identities, data, permissions, tools, services, and downstream effects—not just the model response.

Injectionator is the working platform inside Surfaces. It exercises meaningful paths, finds the owning controls, and connects an apparent AI outcome to evidence from the systems behind it.

Explore Surfaces See Injectionator

Under the application layer, the models and providers shape how it behaves.

Evidence-backed decisions

Inference

The model is an infrastructure decision.

Inference examines the providers, models, routes, regions, plans, contracts, and configurations behind an AI capability. The aim is practical understanding, not a universal leaderboard.

Claims stay attached to their evidence, applicable scope, confidence, and observation date—so a team can see what is known, what remains uncertain, and what the choice means in practice.

Explore Inference Bring an inference decision

Know what you are looking for?

Find public pages, field notes, and deliberately published knowledge from across Viewyonder.

Signals from the field

Current observations

  1. security

    A Chatbot Is Not the Surface: Testing the Path From Prompt to Consequence

    Testing an AI feature means following the path from a prompt through its tools, data and consequences—not just testing the chat box.

  2. security

    Before and after AI Application Security testing: one HR chatbot

    A bounded synthetic example of why model output, application enforcement, and downstream effect must be tested separately.

  3. development

    JUNIE: The Customer Proxy in Our Development Workflow

    Why we are putting a customer-proxy agent inside pull requests, and why passing tests is no longer enough proof.
Read all field notes

Bring us the system you cannot quite see.

Start with one application surface or one inference decision. We’ll establish the boundary, the evidence, and the first useful question.

Start a conversation