The CM 4-Phase Method is an systematic way of interacting with a LLM to do curriculum planning. It is designed to customised units of work to meet your students learning needs, from the first moment you upload your first documents onto your LLM's context window to producing a dynamic daily lesson plan that allows you to monitor and evaluate the learning progress of every student.

The method requires some working knowledge of a LLM. It is helpful to know some basic facts of what is a Large Language Model, the importance of a context window and how AI is a new agentic technology, with the capacity to simulate human reasoning and generate responses to human prompting.

The Curriculum Makers approach is to favour embedding technological skills within the pedagogical process of curriculum planning.So, our assumption is that a Curriculum Leader and teacher will simply be making use of the hardware and software in their school.

As such, we don't deliver the kind of 'how to use AI technology' that you view, for instance, on Education Services Australia.  However, we do link you to LLM Tips which enable you to make better use for you curriculum planning and lesson preparation. 

Furthermore, we set up a Curriculum Makers online community in which we continuous deal with issues of accessing a LLM and through which we deliver specific technology issue workshops.  We also have a Curriculum Makers glossary through which we explain the implications and impact, along with references, of interacting with a LLM.  

The CM Method shifts experiential learning from being activity-driven to outcome-driven. It uses AI to ensure that every creative, hands-on task is structurally anchored to assessable curriculum standards, proving that high student engagement and intense academic rigor are not mutually exclusive.

A teacher might design a fun activity—like building a cardboard diorama —but struggle to articulate exactly what academic standards were achieved. When experiential learning lacks a rigorous framework, assessing it becomes subjective ("Did they try hard? Is it pretty?"), which frustrates teachers, raises eyebrows from leadership, and fails to prepare students for standardised testing like NAPLAN.

The CM Method acts as the structural engine for your PLC Inquiry Cycle. It translates complex, multidisciplinary goals into observable, data-rich metrics, allowing PLCs to evaluate integrated units with the same precision they use for a standard spelling or maths test.

The traditional PLC Inquiry Cycle (driven by questions like "What do we want them to learn?" and "How will we know if they learned it?") works brilliantly for isolated subjects. However, when a PLC tries to evaluate how a story is allowing students to learn mathematics—the cycle often comes up with ‘blockers’. Teachers struggle to find a shared baseline. They end up looking at a creative project and asking, "Are we grading the Maths, the teamwork, or the presentation?" Without clear, integrated data, the PLC cycle stalls in subjective debate

Our methodology ensures curriculum consistency and compliance into an unapologetic focus on pedagogy-first. By providing a standardised, AI-powered workflow for curriculum mapping, the method gives leaders a reliable system to unite disparate teachers across many classrooms to ensure academic rigour, and drastically reduce teacher burnout.

Curriculum leaders face a near-impossible balancing act when implementing cross-curricular initiatives. You must convince teachers with different strengths, knowledge and interests to speak the same language. You are tasked with ensuring that innovative projects strictly comply with mandated standards (like the Victorian Curriculum Version 2.0). Often, leaders end up manually double-checking curriculum or making changes away from the group. This can lead to resentment that the leader did not believe in collaboration after all.

The CM 4-Phase Method turns APST compliance from a tedious tick-box exercise into an automatic byproduct of excellent planning. By using the method's structured workflow, teachers naturally generate the exact documentation needed to evidence their Professional Knowledge, Practice, and Engagement.

Many teachers feel that doing innovative, transdisciplinary work is risky. They worry that straying from traditional, textbook-driven teaching makes it harder to prove they are meeting the strict requirements of the APSTs (especially those seeking full registration or Lead Teacher status). Gathering evidence to prove they are differentiating, assessing, and mapping curriculum often requires hours of retrospective paperwork, completely disconnected from the joy of actual teaching.

Yes. In fact, student data is the engine that drives the method. The CM 4-Phase Method uses your class’s specific proficiency data at the very beginning of the planning cycle to actively shape the curriculum, ensuring the resulting unit is differentiated for the students sitting in your room.

Schools are data-rich but often information-poor. Teachers are handed massive spreadsheets of standardised data (like NAPLAN or PAT scores) at the start of the year, but translating those numbers into actionable, daily lesson plans is incredibly difficult. When teaching a complex class, teachers often default to teaching to the "middle" because mapping a 3-year achievement gap across multiple subjects manually is simply too overwhelming. Data ends up sitting in a folder rather than actively shaping the lesson.

The CM 4-Phase Method moves AI out of the teacher's hidden planning folder and onto the classroom whiteboard. It models the "Human + Machine" partnership, teaching students to use AI as an object to think with that processes data and organises information, while the students remain the ultimate creative and ethical decision-makers.

Currently, many schools are stuck between teachers and students using AI independently of each other. When AI is addressed in the classroom, it is usually framed negatively around plagiarism policies. This creates a massive gap in authentic education. If we don't explicitly teach students how to ethically and productively pilot AI tools, we are failing to prepare them for the modern technological workforce.

The CM 4-Phase Method is built on the philosophy of the Agentic Pilot. Because the CM Method uses AI forensically—to construct highly specific, data-rich rubrics and rigorous scenarios—the teacher does not need to hide the tool. Instead, the teacher models the collaborative enactment live for the students. The teacher demonstrates how to prompt the AI with precise, subject-specific vocabulary (e.g., using proper mathematical or dramatic terminology) to analyse data or generate possibilities. It shifts the student's mindset: AI is not a machine that gives you the answer; it is a machine that interacts with your questions.

You absolutely do not need to start from scratch. The CM 4-Phase Method allows you to take an existing, well-loved single-subject unit and use AI to seamlessly upgrade it into a rigorous, fully integrated experience. You avoid the blank page problem. When schools announce a shift of some kind , teachers often feel they are being asked to throw away years of highly refined, successful lesson plans and start over. Staring at a blank planning document and trying to invent a new unit of work.

The method champions evolution, not revolution. Phase 1 of the workflow allows you to input a legacy unit—perhaps a favorite novel study, a history topic, or a basic science experiment. You then use the AI as a collaborative partner to ask, "If I keep the core narrative of this unit, how can I authentically map [Mathematics] and [Critical and Creative Thinking] onto it?" The AI preserves the heart of your original teaching while generating the new, cross-curricular layers and assessment rubrics required for a rigorous approach.

The CM Method was largely devised to ensure that the use of AI in curriculum planning took special care to align content descriptors to tasks and activities within units of work. Put plainly, we were tired of the long-list approach, you know the look of curriculum codes that preference a curriculum plan typed out in table form.

Instead, we wanted the capacity of LLMs to simulate language patterns to be put to work and literally show links between the specialised language of Curriculum Frameworks and their dynamic relationship to what happens in the classroom.

For instance, the Method transforms abstract, difficult-to-measure capabilities (like Ethics or Critical Thinking) into concrete, observable actions anchored in hard subject-specific data.

Traditionally, teachers struggle to genuinely integrate capabilities with core subjects. Often, integration looks like a siloed approach: teaching a math lesson on grids, and then later having a separate class discussion about 'being a good person.'

Trying to map these separate curriculum documents together manually takes hours of co-planning and often results in forced, unnatural lesson designs. Furthermore, teachers struggle to objectively assess soft skills like the Ethical Capability. 

Instead, the Curriculum Makers methodology favours beginning with the 'end in mind', as Wiggins' & McTighe's UbD methodology has shown to successfully prepare teachers, through its use of AI to deal with the numerous variables facing teachers in curriculum planning.

Anim pariatur cliche reprehenderit, enim eiusmod high life accusamus terry richardson ad squid. 3 wolf moon officia aute, non cupidatat skateboard dolor brunch. Food truck quinoa nesciunt laborum eiusmod. Brunch 3 wolf moon tempor, sunt aliqua put a bird on it squid single-origin coffee nulla assumenda shoreditch et. Nihil anim keffiyeh helvetica, craft beer labore wes anderson cred nesciunt sapiente ea proident. Ad vegan excepteur butcher vice lomo. Leggings occaecat craft beer farm-to-table, raw denim aesthetic synth nesciunt you probably haven't heard of them accusamus labore sustainable VHS.