Transparency label: AI-assisted. NotebookLM worked with Nishigaya’s post to outline the five levels.<\/p>\n\n\n\n
In a recent post on SubStack<\/a>, Nori Nishigaya<\/a> wrote:<\/p>\n\n\n\n Being effective in your use of AI isn\u2019t just figuring out the ideal prompt. There\u2019s so much that goes into skillful use of AI. Done poorly, it can become a tool for chaos. This post lays out the framework that I\u2019ve been exploring as a way of taming this chaos and getting really powerful results from AI.<\/p>\n<\/blockquote>\n\n\n\n His framework captures the moment perfectly, and it resonates with my own learning and experience. Nishigaya’s beautifully clear explanation, which identifes the five levels outlined below, is a powerful (though deceptively simple) aid to thinking about the human | AI interaction. <\/p>\n\n\n\n See also this infographic<\/a> or this one<\/a> or this one<\/a>, all produced by NotebookLM.<\/p>\n\n\n\n In my (small-scale) project to develop an agent for a recruitment agency, I am currently working at Levels 1 to 3. Once the harness has proved its worth, we’ll explore Level 4. <\/p>\n\n\n\n Produced by NotebookLM from Nishigaya’s post<\/em><\/p>\n\n\n\n Level 1: Prompt Engineering<\/strong> – The foundational skill of writing effective prompts. <\/p>\n\n\n\n Level 2: Context Engineering<\/strong> – Shaping the environment and giving AI memory by providing custom context, files, and notes so the AI can formulate its thinking around your specific needs.<\/p>\n\n\n\n Level 3: Harness Engineering<\/strong> – Creating skills, scripts, verification steps, and feedback loops to make AI output more repeatable, trustworthy, and verifiable.<\/p>\n\n\n\n Level 4: Agentic Engineering<\/strong> – Deploying autonomous agents equipped with identity, goals, memory, and a strong harness, transforming them from a tool into an active, autonomous member of a team.<\/p>\n\n\n\n Level 5: The Murmuration<\/strong> – The complex coordination of multiple autonomous actors (both humans and agents) moving together with emergent coherence and a shared purpose, drawing on principles from organizational design.<\/p>\n","protected":false},"excerpt":{"rendered":" Transparency label: AI-assisted. NotebookLM worked with Nishigaya’s post to outline the five levels. In a recent post on SubStack, Nori Nishigaya wrote: Being effective in your use of AI isn\u2019t just figuring out the ideal prompt. There\u2019s so much that goes into skillful use of AI. Done poorly, it can become a tool for chaos. […]<\/p>\n","protected":false},"author":2,"featured_media":0,"comment_status":"closed","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[5],"tags":[477,236,44],"class_list":["post-1046","post","type-post","status-publish","format-standard","hentry","category-diary","tag-context-engineering","tag-human-ai-interaction","tag-prompting"],"_links":{"self":[{"href":"https:\/\/anapoly.co.uk\/labs\/wp-json\/wp\/v2\/posts\/1046","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/anapoly.co.uk\/labs\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/anapoly.co.uk\/labs\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/anapoly.co.uk\/labs\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/anapoly.co.uk\/labs\/wp-json\/wp\/v2\/comments?post=1046"}],"version-history":[{"count":10,"href":"https:\/\/anapoly.co.uk\/labs\/wp-json\/wp\/v2\/posts\/1046\/revisions"}],"predecessor-version":[{"id":1059,"href":"https:\/\/anapoly.co.uk\/labs\/wp-json\/wp\/v2\/posts\/1046\/revisions\/1059"}],"wp:attachment":[{"href":"https:\/\/anapoly.co.uk\/labs\/wp-json\/wp\/v2\/media?parent=1046"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/anapoly.co.uk\/labs\/wp-json\/wp\/v2\/categories?post=1046"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/anapoly.co.uk\/labs\/wp-json\/wp\/v2\/tags?post=1046"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}\n
\n\n\n\nThe Five Levels of Working with AI<\/h2>\n\n\n\n
![this infographic<\/a> or](\"https:\/\/anapoly.co.uk\/labs\/media\/Five-Levels-of-Working-with-AI.jpg\"){kind=link}
![this one<\/a> or](\"https:\/\/anapoly.co.uk\/labs\/media\/AI-Maturity-Framework.jpg\"){kind=link}
![this one<\/a>, all produced by NotebookLM.<\/p>\n\n\n\nIn my (small-scale) project to develop an agent for a recruitment agency, I am currently working at Levels 1 to 3. Once the harness has proved its worth, we’ll explore Level 4. <\/p>\n\n\n\n\n\n\n\nThe Five Levels of Working with AI<\/h2>\n\n\n\nProduced by NotebookLM from Nishigaya’s post<\/em><\/p>\n\n\n\nLevel 1: Prompt Engineering<\/strong> – The foundational skill of writing effective prompts. <\/p>\n\n\n\nLevel 2: Context Engineering<\/strong> – Shaping the environment and giving AI memory by providing custom context, files, and notes so the AI can formulate its thinking around your specific needs.<\/p>\n\n\n\nLevel 3: Harness Engineering<\/strong> – Creating skills, scripts, verification steps, and feedback loops to make AI output more repeatable, trustworthy, and verifiable.<\/p>\n\n\n\nLevel 4: Agentic Engineering<\/strong> – Deploying autonomous agents equipped with identity, goals, memory, and a strong harness, transforming them from a tool into an active, autonomous member of a team.<\/p>\n\n\n\nLevel 5: The Murmuration<\/strong> – The complex coordination of multiple autonomous actors (both humans and agents) moving together with emergent coherence and a shared purpose, drawing on principles from organizational design.<\/p>\n","protected":false},"excerpt":{"rendered":"Transparency label: AI-assisted. NotebookLM worked with Nishigaya’s post to outline the five levels. In a recent post on SubStack, Nori Nishigaya wrote: Being effective in your use of AI isn\u2019t just figuring out the ideal prompt. There\u2019s so much that goes into skillful use of AI. Done poorly, it can become a tool for chaos. […]<\/p>\n","protected":false},"author":2,"featured_media":0,"comment_status":"closed","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[5],"tags":[477,236,44],"class_list":["post-1046","post","type-post","status-publish","format-standard","hentry","category-diary","tag-context-engineering","tag-human-ai-interaction","tag-prompting"],"_links":{"self":[{"href":"https:\/\/anapoly.co.uk\/labs\/wp-json\/wp\/v2\/posts\/1046","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/anapoly.co.uk\/labs\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/anapoly.co.uk\/labs\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/anapoly.co.uk\/labs\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/anapoly.co.uk\/labs\/wp-json\/wp\/v2\/comments?post=1046"}],"version-history":[{"count":10,"href":"https:\/\/anapoly.co.uk\/labs\/wp-json\/wp\/v2\/posts\/1046\/revisions"}],"predecessor-version":[{"id":1059,"href":"https:\/\/anapoly.co.uk\/labs\/wp-json\/wp\/v2\/posts\/1046\/revisions\/1059"}],"wp:attachment":[{"href":"https:\/\/anapoly.co.uk\/labs\/wp-json\/wp\/v2\/media?parent=1046"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/anapoly.co.uk\/labs\/wp-json\/wp\/v2\/categories?post=1046"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/anapoly.co.uk\/labs\/wp-json\/wp\/v2\/tags?post=1046"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}](\"https:\/\/anapoly.co.uk\/labs\/media\/AI-Maturity-Stack.jpg\"){kind=link}