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.

Building a Software Factory: Merging 1000 PRs in a Week

Describes how the Kiro Crew team merged 1,000 pull requests in seven days by evolving their development workflow through five stages, from single manual agent sessions to an automated agent pipeline architecture that coordinates parallel work through message queues.

kiro.dev →

Connections

Related to

Six Months Writing Code Exclusively With AI Agents Both are first-hand practitioner accounts of AI agents handling real coding workloads, but the Software Factory scales beyond individual experience to team-level pipeline automation

Supports

AI-Driven Development Life Cycle: Reimagining Software Engineering Both reimagine the software development lifecycle through AI automation; the 1000-PR case study is a concrete instantiation of the AI-driven SDLC framework
Agentic Coding: LLM Agents, Testing, and Hallucination Risks The 1000-PR pipeline directly demonstrates the agentic coding workflow described theoretically in the LLM agents/testing/hallucination piece, providing empirical evidence of scaled agent coding
Domain-Driven Agents Domain-driven agent design principles are validated by the five-stage evolution described in the Software Factory, where domain specialization of agents enabled the scaling breakthrough

Develops into

Autonomous Mode in Kiro Web for Technical Debt Both concern Kiro's autonomous agent capabilities; the Software Factory describes the evolved pipeline that Kiro's autonomous mode operationalizes at scale

Challenges

SWE-bench Science: Coding Agents for Engineering Tasks SWE-bench evaluates coding agents on isolated tasks; the Software Factory's 1000-PR result suggests real-world agent pipelines outpace what benchmarks capture about production-scale throughput

Type:	link
First published:	Saturday, 19 September 2026 at 15:31 UTC
Location:	https://kiro.dev/blog/software-factory-1000-prs/
URL:	https://mattwood.fyi/i/8027eeff

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