An international technical initiative
PESAEASContainment for autonomous systems that may try to evade or exploit their boundaries.
PESAEAS connects versioned working notes with small technical sessions on enforceable boundaries for autonomous AI and robotic systems.
Containment model
Conceptual sequence · not telemetry
A request reaches the autonomous system. Its outbound action is evaluated against externally enforced policy, stopped at the enclave boundary, and recorded for review.
- 01Autonomous system
- 02External enforcement point
- 03Enclave boundary
- 04Audit record
Work in public
Concrete artifacts, with their status visible.
Each note is scoped, versioned, and connected to a technical session. Unresolved questions remain visible rather than being polished away.
Browse all working notes- 01Working noteVersion 0.1Awaiting revision
Adversarial Containment Foundations
A short working note for the Rabat session: the boundary assumptions, minimum controls, and questions that need practical examination.
- 02Working noteVersion 0.1Awaiting revision
Policy Enforcement in Secure Enclaves
A short working note for the second Rabat session: policy meaning, enforcement placement, evidence, and failure handling.
Programme
Small sessions built around questions that can be examined, challenged, and carried back into the work.
View all →Follow the programme
Get an email when a technical session opens or its status changes.
Focus
A credible containment boundary joins three concerns that are often treated separately.
Adversarial threat model
Assume the contained agent may try to escape, deceive, or exploit its boundaries.
Policy-enforced boundaries
Safety as declarative, auditable rules — not ad-hoc checks or hope.
Enclave isolation
Hardened containment from software agents today to physical systems tomorrow.
About
Containment concerns the whole operating boundary, not the model in isolation.
PESAEAS advances policy-enforced adversarial enclaves — hardened environments that assume the contained system may try to escape, deceive, or exploit its boundaries, from software agents today to physical systems tomorrow.
The initiative convenes technical discussion through meetups and shared practice, toward better containment standards over time.
Relevant perspectives
Systems engineering, security, trusted computing, AI safety, robotics, and policy practice around autonomous software or physical systems.
Most useful when you can bring a threat model, an implementation constraint, or an evaluation question.
An initiative by Akioud AI, Paris. Technical work is intended for open publication as it develops.
Related open-source work includes Akios and EnforceCore.
Participate
Choose the contribution that matches what you can bring now.
There is no formal membership programme at this stage.
- 01See the programme
Attend a session
Join a focused technical discussion. Registration is handled on Eventbrite when a listing is open.
- 02Read and review
Review a working note
Challenge an assumption, identify a missing constraint, or send a correction. Open questions are part of the record.
- 03Start a conversation
Propose a session
Suggest a focused question, a city, or a small session through the initiative’s contact channel.
News
All news →July 2026
PESAEAS Technical Event Series — MENA & Europe, 2026
Launch of the first PESAEAS technical event series across MENA and Europe, beginning August 2026.
July 2026
Introducing PESAEAS
An international technical initiative for policy-enforced adversarial enclaves — containment architecture for autonomous AI and robotic systems.