Chapter 1 - The Convergence: Four Practices, One Architecture
Loop Engineering by Fabio Correa, the Applied AI foundation volume on working with AI through framing, feedback, verification, memory, and human judgment.
Last updated 2026-10-25. Review the primary sources behind the convergence-as-evidence argument and the dated trail of practices that arrived at related mechanisms without shared vocabulary.
The question this chapter takes up
Why did three public practices and one personal practice arrive at the same remedies for AI-assisted work, and what single architecture do those remedies imply?
Put it to work
Use the seven design commitments mapping to compare one commitment across the four practices, then name the failure pressure that commitment is meant to prevent.
Key sources
Chapter 1 cites in the print book: D1, D4, D5, D6, D7, D8, D9, D10, D21, D59. Entries below are the sources this page draws on; some are related literature cited elsewhere in the book rather than in this chapter.
- D1 - Correa, F., and contributors. (2025-2026). Alex ACT ONE [Computer software collection]. Latest release v0.5.0: a single-install ACT runtime for Copilot CLI, VS Code, and Microsoft Scout, and the successor to the Alex ACT Core / Manager / Plugin Mall constellation. The 2025 portion of the date range refers to that predecessor lineage; this repository dates from September 2026. github.com/fabioc-aloha/Alex_ACT_ONE/releases/tag/v0.5.0
- D4 - OpenAI. (2024). Learning to reason with LLMs. openai.com/index/learning-to-reason-with-llms/
- D5 - Anthropic. (2024). Introducing computer use, a new Claude 3.5 Sonnet, and Claude 3.5 Haiku. anthropic.com/news/3-5-models-and-computer-use
- D6 - Anthropic. (2024). Introducing the Model Context Protocol. anthropic.com/news/model-context-protocol
- D7 - DeepSeek-AI et al. (2025). DeepSeek-R1 (arXiv:2501.12948). arxiv.org/abs/2501.12948
- D8 - Huntley, G. (2025). Ralph Wiggum as a Software Engineer. ghuntley.com/ralph/
- D9 - Osmani, A. (2026). Loop Engineering. addyosmani.com/blog/loop-engineering/
- D11 - Willison, S. (2025). Designing agentic loops. simonwillison.net/2025/Sep/30/designing-agentic-loops
- D21 - Anthropic. (2025). Claude's extended thinking. anthropic.com/news/visible-extended-thinking
- D23 - Runkle, S. (2026). The Art of Loop Engineering. LangChain. langchain.com/blog/the-art-of-loop-engineering
- D3 - Correa, F. (2024). Dialog Engineering: AI as Your Research Assistant. medium.com/@fabioc/dialog-engineering-ai-as-your-research-assistant-616a625e9853
Primary-source links
The dated public trail that the convergence argument rests on. Each link points to the original record at the source.
- OpenAI, Learning to reason with LLMs (September 2024) - the reasoning-model tradition's first production milestone.
- Anthropic Computer Use (October 22, 2024) - public-beta autonomous-agency capability.
- Anthropic MCP launch (November 25, 2024) - the protocol-interop tradition's first formal spec. Status, October 2026: in December 2025, Anthropic donated the protocol to the Agentic AI Foundation, a Linux Foundation directed fund; as of October 2026, its governance sits with that foundation rather than a single vendor.
- DeepSeek-R1 (January 2025) - the open-model reasoning tradition's primary record; the journal version appeared in Nature 645 (2025).
- Huntley, "Ralph Wiggum as a Software Engineer" (July 2025) - the coding-agent tradition's scaffolding-loop pattern named.
- Willison, "Designing Agentic Loops" (September 2025) - successor-skill framing that anchored mainstream practitioner vocabulary.
- Osmani, "Loop Engineering" (June 2026) - the trade-press term that prompted this book's title.
- LangChain, "The Art of Loop Engineering" (2026) - framework-vendor framing that confirmed loop engineering crossed from blog post to commercial vocabulary.