Weak to strong. Risk to fix.

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

Try n8r-surface Join n8r-labs early access

Open-source exploration. Practitioner help when you need it — £750/day.

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

  1. security

    From AI security tests to a description of the system

    How Injectionator’s n8r-surface work records the components, connections and evidence behind an AI experiment—and why that matters for Surfaces.

  2. security

    How the fk did we end up here?

    My journey from researching prompt injections to Injectionator, Surfaces, and the question of who owns the security of the whole AI system.

  3. development

    AI Surface Models need loosely coupled maps

    Lessons and open questions from my Injectionator work: connecting partial maps of AI systems, preserving uncertainty and learning from SBOMs.
Read all field notes

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.

Start exploring with Injectionator’s n8r-surface. Its experimental open-source tools help describe the system and retain evidence and unanswered questions. n8r-labs is the direction for controlled experiments with those surfaces.

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.

Analyze your AI surface.

Work with Steve Chambers at £750/day. Get a map of the system, investigate a specific concern, or review what changed. We agree the scope, deliverables and number of days with you.

See analysis packages