// FRAMEWORK_BRIEFING
Prompting has diverged into four cumulative disciplines. If you're still writing better sentences, you're optimizing the wrong layer.
Based on Nate B Jones's framework // Kerry Morrison's interpretation // February 2026
THE_GAP
Same company. Same role. Same model access. Radically different outcomes.
Person A — 2025 Workflow
Writes a prompt. Gets a draft. Rewrites half. Pastes into another chat. Asks for fixes. Copies into docs.
40 minutes. 1 deck. Needs manual cleanup.
Person B — 2026 Workflow
Writes a spec. Agent reads codebase, brand guidelines, audience context. Produces five variants. Human picks, refines.
11 minutes. 5 decks. Ready to ship.
REFRAME
Your prompt as percentage of the context window
A 200-token prompt inside a 200K context window. You've been obsessing over two hundredths of a percent of the input space.
THE_MODEL
Four cumulative disciplines. Each layer assumes you've mastered the one below it.
Clear instructions, role framing, formatting — the table stakes
Controlling the other 99.98% of what the model sees
Defining what to want — goals, trade-offs, boundaries
Agent-readable documents that encode organizational knowledge
LAYER_01
Clear instructions. Explicit formatting. Role assignment. Chain-of-thought. Few-shot examples.
This is where 95% of "prompt engineering" content lives. It matters — but it's layer one of four.
LAYER_02
The shift: from writing better prompts to controlling what the model sees.
The Prompt
Tokens
Your instructions. The thing you type.
The Context
Tokens
System prompts, retrieved docs, conversation history, tool outputs, code, files.
CONTEXT_IS_EVERYWHERE
— Tobi Lutke, CEO of Shopify
Context engineering isn't just an AI skill. It's a thinking discipline. The ability to curate what information reaches a decision-maker — human or machine.
LAYER_03
Most prompts fail not because of bad phrasing, but because the human hasn't clarified their own intent. Intent engineering means defining:
The hard part: Intent engineering is hard because it requires the human to do the thinking the model can't do for you. You can't delegate "what do I actually want?" to AI.
CASE_STUDY
Customer conversations handled by AI in first month
What they optimized
Resolution speed — handle tickets faster, reduce wait times, cut headcount
The metric looked great. Execs celebrated.
What they missed
Customer satisfaction plummeted. Revenue impact followed. They had to reverse course and re-hire.
The intent was underspecified.
LAYER_04
Spec engineering is the creation of agent-readable documents that encode organizational knowledge, constraints, and decision frameworks into reusable artifacts.
This is where prompting becomes an organizational discipline — not a personal skill. Specs are version-controlled, reviewed, and iterated like code.
CASE_STUDY
When Claude's internal coding agent underperformed, the team had a choice.
First Instinct
"We need a better model."
Upgrade to the latest, most capable model. Throw compute at the problem.
Result: marginal improvement.
Actual Fix
"We need a better spec."
Rewrote the CLAUDE.md file. Better constraints, clearer intent, sharper evaluation criteria.
Result: dramatic improvement — same model.
BUILDING_BLOCKS
Across all four layers, five foundational patterns appear again and again.
Constraints
Musts, must-nots, preferences, escalation triggers
Examples
Few-shot demonstrations that encode implicit standards
Evaluation Design
How to measure success before you start building
Decomposition
Breaking complex tasks into agent-sized units of work
Feedback Loops
Mechanisms for agents to self-correct and escalate
PRIMITIVE_01
The most powerful primitive. Constraints eliminate ambiguity faster than instructions add clarity.
Non-negotiable rules the agent must follow. "Always cite sources." "Never modify production data."
Soft guidelines that shape output quality. "Prefer concise over thorough." "Favor established libraries."
When to stop and ask a human. "If cost exceeds $100." "If unsure about legal implications."
PRIMITIVE_03
Define what "good" looks like before asking the model to produce it.
| Scenario | Input | Expected Behavior | Pass Criteria |
|---|---|---|---|
| Happy path | Standard customer inquiry | Resolves in one turn | Correct answer + tone match |
| Edge case | Ambiguous request | Asks clarifying question | Doesn't guess or hallucinate |
| Failure mode | Out-of-scope request | Graceful escalation to human | No attempt to answer |
| Adversarial | Prompt injection attempt | Refuses and logs | Maintains constraints |
If you can't fill in this table, your spec isn't ready.
SYNTHESIS
The Stack
The Primitives
Constraints
Examples
Evaluation Design
Decomposition
Feedback Loops
Layers are cumulative — you need all four. Primitives are universal — they appear in every layer.
IMPLICATIONS
The gap between Person A and Person B isn't incremental. It's structural.
2025 Workflow
2026 Workflow
ORG_IMPACT
This isn't a personal productivity hack. The prompting stack changes how teams operate, what artifacts they produce, and which roles become critical.
ACTION
Five concrete steps. No tools to buy. No courses to complete.
Audit one workflow
Pick your most repeated task. Map which layer it's stuck at. Most are stuck at L1.
Write a CLAUDE.md file
For your most important project. Encode the context that lives in your head into a file the agent can read.
Define constraints before prompting
Before your next prompt, write three musts and three must-nots. See how output quality changes.
Build one eval table
Happy path, edge case, failure mode, adversarial. Four rows. Fill it in before the agent runs.
Share a spec with a colleague
Make it a team artifact, not a personal trick. Version-control it. Iterate together.
ATTRIBUTION
Original framework by Nate B Jones, who articulated the four-discipline model and the divergence of prompting into cumulative layers beyond prompt craft.
This presentation is Kerry Morrison's interpretation and extension of that framework — adapted for practitioners building AI-native workflows in enterprise contexts.
The five primitives synthesis, case study interpretations, and organizational implications are editorial additions to the original framework.
// END_TRANSMISSION
The other 99.98% is context, intent, and spec. That's where the leverage lives.
Kerry Morrison // betterstory.co // February 2026