What makes this different from general AI use

Most teachers use AI to create.
Agile teachers use it to improve.

Most teacher AI use follows the same pattern: “Write me a lesson on [topic].” The output is a generic lesson that may or may not suit the class, and which requires heavy modification before it can be used. It is generation from scratch — useful for new content, poor for iteration.

The agile AI workflow is different. You are not asking AI to create a lesson — you are asking it to modify a specific lesson you already taught, in a specific way, to address a specific failure. The inputs are more constrained, the output is more targeted, and the editing pass is shorter because you're reviewing a modification rather than generating from nothing.

The generative AI workflow asks: what should this lesson look like? The iterative workflow asks: what did this lesson look like, what failed, and what does the fixed version look like? The second question is easier for AI to answer well — because it has more constraints.
P6 · Agile teaching — C8 · AI as the agile tool
The three-input structure

Three inputs.
One targeted lesson modification.

The AI lesson regeneration prompt has three required inputs and one optional constraint. Each input has a specific purpose — removing any one of them degrades the output quality significantly.

1
The original lesson or element — the baseline
What existed before the lesson

Paste the specific lesson element you are modifying: the explanation, the activity, the worked example, or the assessment task. More specific is always better — if only the explanation needs changing, paste only the explanation rather than the full lesson. Without the original, AI generates from scratch — producing something that may contradict your other lesson elements, reuse examples you've already used, or use vocabulary your class hasn't encountered.

Precision tip
If the full lesson has 5 elements and only one failed, paste only that element. The constraint makes the AI's job cleaner and the output more targeted. Pasting the full lesson invites AI to modify things that don't need modifying.
2
Your observation notes — the diagnostic data
What failed and why

Paste the observation notes you wrote during or after the lesson. As covered in C4/A3, these need four components: the specific wrong answer, the mechanism behind it, the element to change, and the constraint on the new approach. If your notes are vague, upgrade them before pasting — the quality of this input determines everything.

Minimum viable observation note
"18/25 students described osmosis as the concentrated solution pulling water. Mechanism: they are attributing agency to the direction rather than understanding diffusion as a passive process. Element to change: the explanation. Constraint: no arrows, no directional language."
3
A specific instruction — the change specification
What the output should be

Tell the AI exactly what the output should be: an explanation replacement, a new worked example, a redesigned activity. Specify format (word count, structure, level), audience (year group, prior knowledge), and purpose (to address the specific misconception named in Input 2).

Specific vs vague instruction
Vague: "rewrite the osmosis explanation." Specific: "Replace the osmosis explanation with one that uses a particle-density analogy rather than water-movement arrows. 150 words maximum. Year 9. Must specifically address the misconception that the concentrated solution actively pulls water."
🤖The full three-input prompt — copy and fill
“Here is a lesson element I taught today: [paste original element]. Here are my observation notes: [paste notes with all four components]. Please generate a replacement [explanation / activity / worked example] that: addresses the misconception that [specific wrong mental model]; does not use [specific framing to avoid]; is [word count] words or fewer; is suitable for [year group] students who know [relevant prior knowledge]; and can be dropped directly into my existing lesson plan to replace the original element. Do not change any other part of the lesson.”
The editing pass — 90 seconds

What to check before using
the AI output tomorrow.

Run these three checks on every AI-generated element before use. No exceptions — AI is accurate often enough to develop false confidence, and wrong often enough that unchecked output occasionally contains significant errors.

Check
What to look for
Fix if found
Factual accuracy
Technically correct statements that are missing a qualification; generalisations that break in edge cases your class will encounter
Add the qualification or replace with an example that doesn't have the problematic edge case
Vocabulary level
Terms the class hasn't encountered; technical language used without definition; register too formal for the year group
Replace technical terms with accessible equivalents; add a brief "this is what we've called X" bridge
Avoided framing
The specific thing you told AI not to use, reintroduced in different words or through a different example with the same effect
Flag the reintroduction, manually remove and substitute
Daily practice

The 3-minute iteration as
a teachable habit.

Teachers who use this workflow daily report a consistent experience: the first few uses feel mechanical and produce output that needs significant editing. By the third or fourth use, the observation notes are sharper, the prompt is more precise, and the output requires minimal adjustment. By the second week, the full cycle — scan, diagnose, prompt, edit — takes under 4 minutes and produces output that is usually better than a manually written first draft.

The habit formation depends on one condition: the observation notes must be written before the lesson ends, not reconstructed from memory at 9pm. A 2-minute note written at the classroom door while students are filing out is worth more than a 20-minute reconstruction attempt after dinner.

📝The 2-minute end-of-lesson note template
Keep this structure on a sticky note or phone home screen:

(1) Most common wrong answer: ___
(2) Why they got it wrong (my hypothesis): ___
(3) Element to change: ___
(4) What the new version must avoid: ___

Fill it before leaving the room. Use it verbatim as Input 2 in tonight's prompt.