Selected research / Nils Holmager
AI governance research and practice
Explore Nils Holmager’s connected research into human–AI partnership, accountable autonomy, governance-first memory and evidence capture.
Augmented Individual Intelligence
What changes when AI becomes a continuing part of someone’s thinking rather than an occasional tool?
Read the overview →AI governance frameworkPrinciples of Earned Autonomy
A proposed governance framework for autonomy that is earned through evidence and remains revocable.
Read the overview →AI agent skills suitePEA Skills Suite
The working practice behind the product stories: interpret the purpose, make a justified change, verify it and retain the decision record.
Read the overview →Agent memory specificationAgent Context Memory
Persistent memory is not enough. An agent also needs to know whether it is authorized to act.
Read the overview →LLM traffic recording proxyLLM Harness Proxy
A structural recording layer between an LLM client and its provider, designed to persist a record before releasing a response.
Read the overview →AI code improvement toolAI Steward
An improvement loop that proposes and verifies code changes while leaving the final commit decision with the operator.
Read the overview →AI agent workflow skillWork Skill
A compact standalone skill for improving a real target without treating delegation as unlimited permission.
Read the overview →Articles / Evidence / Open questions
Research notes
Why I built Principles of Earned Autonomy
An agent can finish a task without making its work easy to take responsibility for. That gap is the starting point.
Read the note →Pilot reportCode that works is not the whole result
Four functional passes. A missing decision record. Why the first author-run pilot does not demonstrate a PEA advantage.
Read the note →Open research questionsWhat would change my mind about PEA?
A framework for examining AI work should face the same scrutiny it asks agents to face.
Read the note →