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.

GDM Science Skills: Agentic Scientific Workflows

Connections

Develops into

Managing Agent Skills with Dr. Skill GDM Science Skills represents a domain-specific instantiation of the agent skill management problem that Dr. Skill addresses generically, extending the concept to structured scientific toolchains

Related to

SWE-bench Science: Coding Agents for Engineering Tasks Both address agentic AI applied to scientific/engineering problem-solving tasks, with SWE-bench Science benchmarking coding agents on structured problems while GDM Science Skills grounds agents in real scientific databases
Building an Advanced Agentic Harness Both address the infrastructure challenge of building capable agentic harnesses, with GDM Science Skills specializing this for scientific research contexts requiring external data grounding
Ornith-1.5: Self-Scaffolding to Self-Improvement Ornith-1.5's self-scaffolding approach to agent improvement shares architectural goals with GDM Science Skills' efficiency improvements, both seeking agents that progressively improve task execution

Supports

WikiSkill: Agent Experience into Persistent Knowledge WikiSkill's approach of converting agent experience into persistent knowledge directly complements GDM Science Skills' goal of improving agent grounding and efficiency across repeated scientific workflows
Domain-Driven Agents Domain-Driven Agents' framework of organizing agents around domain knowledge directly validates GDM's approach of grounding scientific agents in 30+ specialized databases and domain-specific tools

Supported by

AlphaGenome Variant Analysis AlphaGenome exemplifies agentic scientific workflows — the variant browser automates multi-modal genomic data integration (RNA-seq, DNase hypersensitivity) across cell types, demonstrating how AI accelerates biological discovery pipelines.
AI's Role in Formal Mathematical Proof Verification The dramatic reduction in formal verification time (from 132,800 person-hours to AI-assisted completion) exemplifies the agentic scientific workflow capability described in GDM Science Skills, supporting the broader thesis that AI agents can compress expert scientific labor
Dream-RSI: Recursive Self-Improvement through Evolving Worlds Dream-RSI's recursive self-improvement framework directly enables the kind of agentic scientific workflows GDM Science Skills describes, by allowing agents to autonomously refine their exploration strategies over time

Navier-Stokes Solution Agentic scientific workflows (GDM Science Skills) represent the kind of AI-driven research methodology that could be applied to computational fluid dynamics and Navier-Stokes exploration

Type:	link
First published:	Tuesday, 8 September 2026 at 18:42 UTC
Location:	https://github.com/google-deepmind/science-skills
URL:	https://mattwood.fyi/i/af77f611

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