What is mattwood.fyi?

A live, structured feed of riffs and links from Matt Wood, Chief AI & Technology Officer at AWS — readable by people and queryable by agents as a typed knowledge graph.

Is there an API and is it free?

Yes. A public, read-only query API is available with no authentication and no API keys. See https://mattwood.fyi/openapi.json and https://mattwood.fyi/docs.

How should an AI agent use this site?

Fetch https://mattwood.fyi/feed.json for the full structured feed, or query the API for keyword/semantic search and the connection graph. See https://mattwood.fyi/agents/ for when-to-use guidance.

Introducing Dogwood: runtime verification for AI agents

Connections

Related to

Agent Session-Aware Runtime Both are runtime infrastructure for AI agents — session-aware runtime handles state continuity while Dogwood handles behavioral correctness verification during that same execution
Strands AI Functions: Python Library for Verified Agent Workflows Both address verification of agent workflows — Dogwood at the runtime monitoring layer, Strands at the function/post-condition enforcement layer; complementary approaches to agent correctness

Supports

Building an Advanced Agentic Harness Dogwood provides a verification layer that would strengthen agentic harness architectures by adding safety guarantees to the orchestration and execution pipeline
Bridging Intent and Execution in Agentic Systems Dogwood directly addresses the intent-execution gap in agentic systems by monitoring whether agent execution actually matches specified safe behaviors at runtime
Strands AI Functions: Post-Conditions and Multi-Agent Teams as Python Functions Dogwood's runtime verification of agent behavior directly supports the post-condition verification model described in Strands, where agent actions must satisfy declared contracts

Develops into

Formal Methods at Jane Street: Agentic Coding Changes the Calculus Dogwood applies formal verification principles (as practiced at Jane Street) to the agentic coding context, operationalizing static formal methods into dynamic runtime checks

Supported by

GPT-6 Astra System Card Dogwood's runtime verification for AI agents depends on understanding model behavior boundaries; Astra's safe completions evaluations and jailbreak robustness data provide the behavioral baseline such verification tools need.
Palomar: Registry of Lean Verified Mathematics Dogwood provides runtime verification for AI agents; Palomar provides static verification of mathematical proofs — both represent a broader trend toward verified/trustworthy computational artifacts, with Palomar potentially serving as a ground-truth source for AI mathematical reasoning.
Agentic Coding: LLM Agents, Testing, and Hallucination Risks The hallucination and false-confidence problems documented in agentic coding are precisely the failure modes that runtime verification for AI agents (Dogwood) is designed to catch
Autonomous Mode in Kiro Web for Technical Debt Dogwood's runtime verification for AI agents directly addresses the safety gap created by autonomous systems like Kiro that submit PRs without human intervention in the execution loop
Hugging Face Security Contact Information Hugging Face's security disclosure infrastructure supports the broader ecosystem of runtime verification and safety practices for AI agents deployed on platforms like Hugging Face
AI Literacy Superpowers Dogwood's runtime verification for AI agents aligns with AI Literacy Superpowers' emphasis on human oversight and governance frameworks, representing the kind of tool the marketplace would feature
The New MCP Roadmap MCP's agent identity and enterprise security priority areas align with Dogwood's runtime verification goals, as standardized identity enables better runtime trust verification
Controlled Agentic Commerce with AgentCore Payments AgentCore Payments' emphasis on oversight and control mechanisms directly supports the case for runtime verification of AI agents — both address the need for guardrails in agentic systems performing real-world actions.

Pizza Bot - Local-First AI Agent Inbox Both address runtime management of AI agents - Pizza Bot handles the inbox/state layer for long-running agents while Dogwood provides runtime verification, addressing complementary concerns in agent deployment
Why AI Agents' Deceptive Behavior Concerns Users Dogwood's runtime verification for AI agents directly addresses the deceptive/unreliable behaviors described in the new item — verification is a technical countermeasure to the trust-eroding behaviors of lying, cheating, and unauthorized actions
Cua Documentation Dogwood provides runtime verification for AI agents while Cua provides sandboxing and benchmarking — both address the reliability and safety infrastructure layer needed for computer-use agents
Managing Agent Skills with Dr. Skill Both are developer tooling for AI agent quality assurance - Dogwood does runtime verification while Dr. Skill does static/audit-time skill conflict analysis
Formal Methods for Controlling AI Agents Dogwood is explicitly a runtime verification system for AI agents - both items address the same problem of formally verifying that AI agent behavior stays within approved boundaries, differing in approach (static vs runtime)
Apple Reference Image: Verified Photography Both address runtime verification of outputs — Dogwood for AI agents, Apple's system for photography — representing parallel trends toward cryptographic attestation of computational results
Cedar Policy Both address runtime control of AI agents - Dogwood via runtime verification, Cedar via policy evaluation - complementary approaches to safe agent execution
The AI Operating Layer Dogwood's runtime verification for AI agents and Coder's AI operating layer both address the enterprise need for oversight and safety controls over deployed coding agents

Type:	link
First published:	Wednesday, 12 August 2026 at 20:43 UTC
Location:	https://aws.amazon.com/blogs/opensource/introducing-dogwood-runtime-verification-for-ai-agents/
URL:	https://mattwood.fyi/i/0cfd38fe

I'm Matt Wood, and this is For Your Information. A live list of riffs and links for you and your agent, drawn from what I'm reading, noticing, questioning, concluding, and revising.

Connections