Looking for AI builders to test NEES Core Engine — a governed runtime layer for AI apps
I’m opening NEES Core Engine for developer feedback.
NEES Core Engine is a governed AI runtime layer that sits between your application and the model provider:
User → App → NEES Core Engine → Model Provider → Governed Response
The goal is not to replace the model.
The goal is to make AI product behavior more controllable, traceable, and reviewable.
I’m looking for developers building:
- AI agents
- customer support bots
- internal copilots
- workflow automation tools
- AI apps using memory, tools, roles, or escalation logic
The problem I’m exploring:
Most AI product failures are not only model failures.
They often come from the system around the model:
- unclear role boundaries
- messy memory/context scope
- missing escalation paths
- weak permission boundaries
- no traceability
- no reviewable decision history
- behavior drift across sessions
- prompt fixes scattered across the product
NEES Core Engine is designed to help with:
- behavior governance
- role consistency
- memory boundaries
- intent-aware policy decisions
- runtime trace IDs
- escalation/fallback visibility
- reviewable AI responses
Developer preview repo:
https://github.com/NEES-Anna/nees-core-developer-preview
Live sample app:
What I’m looking for:
If you are building real AI workflows, I’d love your feedback on:
- Is the quickstart clear?
- Does the governance flow make sense?
- Are trace IDs and metadata useful?
- What fields would you need in production?
- Where does the runtime feel incomplete?
- What would stop you from integrating this?
- What failure modes should NEES handle better?
This is still an early developer preview, so I’m not looking for praise.
I’m looking for honest technical feedback from builders.
If you test it, even for 15 minutes, your feedback would help shape the next version of NEES Core Engine.
