Human in the Loop Control for OpenClaw
Some agent actions are too consequential to leave to policy alone. This post describes a new OpenClaw demo that uses Cedar and a Yubikey to put a human in the loop, binding each approval to the exact action being approved. Because the control lives in the harness rather than the prompt, the agent can't reason its way around it.
Continue reading {Human in the Loop Control for OpenClaw}
There's a Personal App for That
My twenty-five-year-old Intel Play QX3 microscope had no software that would run on a modern Mac, so I used Claude to write one in a morning. When an app takes a morning instead of two weeks, software can stop being a product and start being personal.
Continue reading {There's a Personal App for That}
The Shape of Context in Agentic Authorization
In agentic systems, the principal, action, and resource are often unknown until the moment an agent acts, and the context that governs the decision arrives as a flood of signals from many sources. This post looks at how that context takes shape, where each signal is actually consumed, and why a non-directed world of agents still needs decisions that humans can inspect and predict.
Continue reading {The Shape of Context in Agentic Authorization}
Internet Identity Workshop XLII Report
IIW XLII brought 287 people to the Computer History Museum in Mountain View for three days of sessions on identity, agents, and the legal and technical foundations of first person digital life. The agenda reflected a community grappling with real deployment challenges: SEDI and duty of loyalty, agentic identity, MyTerms, post-quantum cryptography, and the EUDI wallet. AIW2 followed on Friday, continuing the agentic internet conversation.
Continue reading {Internet Identity Workshop XLII Report}
Building a Conversational Interface for Manifold with MCP and Picos
GUIs are dead—at least for most user experiences. This post describes a BYU capstone project where five seniors built a conversational interface for Manifold using MCP and picos. The result shows how natural language can replace a GUI entirely, letting users create, tag, and manage digital things through dialogue instead of learning a standard graphical user interface.
Continue reading {Building a Conversational Interface for Manifold with MCP and Picos}
It's Not Just What Agents Can Do...It's When They Can Do It!
Agents don't just perform actions; they execute plans where the safety of each step depends on what has already happened. That makes sequencing an authorization problem. This post explores how policy, delegation data, and multi-signature approval can govern the order in which agents receive authority, not just the scope of it.
Continue reading {It's Not Just What Agents Can Do...It's When They Can Do It!}
Agentic AI and Dynamic Authorization: A Series Recap
I've been exploring how policy, delegation, and continuous authorization can make agentic AI systems useful without making them ungovernable. This post ties together nine essays that trace that journey from foundational ideas to practical patterns.
Continue reading {Agentic AI and Dynamic Authorization: A Series Recap}
Cross-Domain Delegation in a Society of Agents
Cross-domain delegation requires more than transferring a credential. In a society of agents, policies define boundaries, promises communicate intent derived from those policies, credentials carry delegated authority, and reputation allows trust to emerge through repeated interactions.
Continue reading {Cross-Domain Delegation in a Society of Agents}
Delegation as Data: Applying Cedar Policies to OpenClaw Subagents
Intra-domain delegation enables an agent to grant constrained authority to subagents without expanding the system’s trust boundary. In the OpenClaw + Cedar demo, delegation is modeled as data and enforced by a stable policy set, preserving policy integrity while allowing dynamic scoping of power.
Continue reading {Delegation as Data: Applying Cedar Policies to OpenClaw Subagents}
Childproofing the Control Plane: Using Cedar to Build Frontal Lobes for Agentic Systems
Connecting an agent like OpenClaw to Home Assistant can make home automation more adaptive and intelligent, but it also introduces real risks if authority is not clearly bounded. By externalizing decision logic into deterministic Cedar policies, we can create governed autonomy that allows agents to act usefully while preventing them from crossing safety, security, and privacy boundaries.
Continue reading {Childproofing the Control Plane: Using Cedar to Build Frontal Lobes for Agentic Systems}
Beyond Denial: Using Policy Constraints to Guide OpenClaw Planning
OpenClaw agents plan, adapt, and act over time, so authorization that functions merely as a reactive gate isn't the best architecture. In this post, I show how integrating Cedar's query constraints and Typed Partial Evaluation lets OpenClaw discover what is allowed before acting. The result is an agent that plans within policy-defined boundaries while still enforcing every concrete action at runtime.
Continue reading {Beyond Denial: Using Policy Constraints to Guide OpenClaw Planning}
A Policy-Aware Agent Loop with Cedar and OpenClaw
This article demonstrates how to move authorization inside the agent loop by inserting a Cedar-backed policy decision point into OpenClaw, so that every tool invocation is evaluated at runtime. Instead of acting as a one-time gate, authorization becomes a continuous feedback signal that guides replanning and enforces Zero Trust principles for agentic systems.
Continue reading {A Policy-Aware Agent Loop with Cedar and OpenClaw}
Why Authorization Is the Hard Problem in Agentic AI
Agentic AI systems expose the limits of static authorization models, which assume permissions can be decided once and remain valid over time. As agents plan, act, and replan, authorization must become a continuous feedback signal that constrains behavior at each step rather than a one-time gate. Dynamic, policy-based authorization enables delegation to be enforced through purpose, scope, conditions, and duration, turning denial into a productive signal that guides replanning instead of a terminal failure.
Continue reading {Why Authorization Is the Hard Problem in Agentic AI}
From Architecture to Accountability: How AI Helps Policy Become Practice
Architecture alone does not make authorization trustworthy. Over time, access control only works if intent can be understood, traced, and shown to produce legitimate outcomes in real systems. This post explores how AI can support the governance of access control by helping teams connect policy intent to effective access, producing coherent evidence that policy behaves the way it is meant to.
Continue reading {From Architecture to Accountability: How AI Helps Policy Become Practice}
Authorization Before Retrieval: Making RAG Safe by Construction
Retrieval-augmented generation makes language models far more useful by grounding them in real data, But it also raises a hard question: who is allowed to see what? This post shows how authorization can be enforced before retrieval, ensuring that RAG systems remain powerful without becoming dangerous.
Continue reading {Authorization Before Retrieval: Making RAG Safe by Construction}
What AI Can Tell You About Your Authorization Policies
AI shouldn't decide who can access what, but it can help you understand what the system already allows. Used as an auditor or reviewer, AI becomes a lens for exposing scope, risk, and undocumented assumptions in authorization systems.
Continue reading {What AI Can Tell You About Your Authorization Policies}
Policy Authoring and Analysis with AI
AI doesn’t belong in the business of deciding who can access what, but it can be an effective partner in reasoning about authorization policies. When used inside clear guardrails, AI helps humans author, analyze, and refine policies without taking over access decisions.
Continue reading {Policy Authoring and Analysis with AI}
AI Is Not Your Policy Engine (And That's a Good Thing)
If your access control lives in a prompt, it isn’t access control. Authorization decisions must be deterministic and enforced before an LLM ever sees data. Treating AI as a policy engine is a category error with real consequences.
Continue reading {AI Is Not Your Policy Engine (And That's a Good Thing)}
The First Agentic Internet Workshop
The first Agentic Internet Workshop (AIW1) took place on October 24, 2025, the day after IIW 41, bringing together a global group to explore how agents, identity, and infrastructure intersect. With 40+ sessions and participants from 10 countries, AIW I marked the beginning of a focused conversation on building an internet that acts on our behalf—securely, transparently, and with human agency at its core.
Continue reading {The First Agentic Internet Workshop}
Internet Identity Workshop XLI Report
IIW XLI brought 287 people together at the Computer History Museum in Mountain View for three days of dynamic sessions on identity, personal agents, and the agentic internet. As always, the agenda was created live each morning, reflecting the priorities of a passionate, deeply engaged community. We also held the first Agentic Internet Workshop the day after IIW, continuing the momentum in a new direction.
Continue reading {Internet Identity Workshop XLI Report}
From IIW to the Agentic Internet Workshop
The Internet Identity Workshop returns October 21–23 at the Computer History Museum, bringing together the community that builds the protocols behind digital identity. This year, we’re adding something new: the Agentic Internet Workshop on October 24, focused on the next generation of protocols for the agentic internet.
Continue reading {From IIW to the Agentic Internet Workshop}
Internet Identity Workshop XL Report
IIW XL brought together over 300 participants from 27 countries, highlighting the growing global momentum behind decentralized identity, digital wallets, and agent-based architectures.
Continue reading {Internet Identity Workshop XL Report}
SSI is the Key to Claiming Ownership in an AI-Enabled World
I've been trying to be intentional about using generative AI for more and more tasks in my life. For example, the image above is generated by DALL-E. I think generative AI is going to upend almost everything we do online, and I'm not alone. One of the places it will have the greatest impact is its use in personal agents, determining whether or not these agents enable people to lead effective online lives. Jamie Smith recently wrote a great article in Customer Futures about the kind of AI-enabled personal agents we should be building. As Jamie points out: "Digital
Continue reading {SSI is the Key to Claiming Ownership in an AI-Enabled World}
Explore Technometria
Popular Topics
- Actor Model
- Agentic AI
- Authentication
- Authorization
- Blogging
- Decentralization
- Event Programming
- Identity
- IIW
- Internet of Things
- IT Conversations
- Javascript
- KRL
- Kynetx
- Picos
- Programming
- Programming Languages
- Reactive Programming
- Reputation
- Sovrin
- Startups
You Might Also Enjoy
- Self-Sovereign Identity References
- Best Food Blog on the Planet
- Live Web Whitepapers
- My Slides
- My Videos
- CTO Breakfast
- Essays
- CIO Whitepapers
My Books
