# The Judgment Layer: Turning Agent Memory into Wisdom

Turning agent memory into wisdom — and the layer nobody has built

- Author: Mike Norton (ORCID 0009-0003-1866-6249), DHARE, Brisbane, Australia
- Published: 2026-08-20 · Version 1.0 · Position paper
- DOI: [10.5281/zenodo.22025638](https://doi.org/10.5281/zenodo.22025638) · Record: https://zenodo.org/records/22025638
- PDF: https://dhare.ai/papers/the-judgment-layer.pdf (md5 76d68e982a1fdf60c57c7b7ee16edabd)
- Licence: CC BY 4.0
- Keywords: agent memory, judgment layer, cognitive architecture, constitutional governance, continuity

## Abstract

Persistent memory for AI agents is becoming a commodity. The funded field — Mem0, Zep/Graphiti, Letta, Cognee, LangMem, and now platform offerings like Cloudflare’s Agent Memory — handles extraction and provenance well. But agent memory breaks down into four steps: extract what happened, attribute where it came from, judge what it means, and govern how it changes behaviour — and every shipping system stops after step two. Recent formal work (Roynard, 2026) identifies the same missing tier and reports near-zero contradiction-resolution across the field. I stake four claims about that empty rung. One: memory should be shaped like attention — a tree of focus sessions with depth-proportional compression — not shredded into atomic facts. Two: continuity belongs to the judgment layer, not the model — treat the LLM as stateless by design and identity survives model swaps, context compaction and provider churn. Three: typed persistence needs an ignorance ledger — a first-class store for known unknowns, with suspension of judgment (epochē) as a routing outcome alongside accept and refuse. Four: the layer that turns memory into behavioural guidance has to be constitutionally governed — promotion gated on evidence rather than user approval, amendment restricted to the human owner, and no agent ever self-ratifying the law that governs it. I finish with an evaluation protocol — architectural property tests plus a continuity test I call the ache test — and an open invitation to tear it apart.

Status: architecture and evaluation protocol. A results paper follows the build.

## Cite

Norton, M. (2026). *The Judgment Layer: Turning agent memory into wisdom* (Version 1.0). Zenodo. https://doi.org/10.5281/zenodo.22025638

```bibtex
@misc{norton2026layer,
  author    = {Norton, Mike},
  title     = {The Judgment Layer: Turning Agent Memory into Wisdom},
  year      = {2026},
  version   = {1.0},
  publisher = {Zenodo},
  doi       = {10.5281/zenodo.22025638},
  url       = {https://doi.org/10.5281/zenodo.22025638}
}
```