Combat Writing: Expressing Bold Ideas in a Complex Business World

Combat Writing is a conceptual tool for authors to uncover insights and publish outputs using those emerging discoveries. It is a framework for professionals to build quality pieces through iterating, feedback loops, and implementing a variety of perspectives.

This approach systematically uses multiple artificial intelligence to reveal previously unforeseen results and angles. It also explores the hidden tension between the emerging dynamics of human learning and deep learning.

In other words, we understand learning is not what you know but how you move. Insights cannot be engineered nor designed, they must come about naturally through experience, practice, discussion and other unknown variables.

If you’re not using AI tools, try this with a committed group of friends or teammates.The human is the creator and decision maker building around the following questions:

• How does AI feedback complement human feedback in refining ideas?

• When evaluating the quality of rough drafts, where do we agree and disagree with AI?

• How does the Combat Writing approach engage with multiple AI to reveal hidden insights?

[Without AI]

• How does feedback refine our ideas?

• When evaluating the quality of rough drafts, where do we agree and disagree with one another?

• How does the Combat Writing approach foster the conditions for insights to emerge?

THE COMBAT WRITING FRAMEWORK

Key Terms:

• SM: Source Material

• C: Context Brief

• R1/R2: Rounds of analysis (R = Round)

• FQ: Focus Question - Guiding reference

• S1/S2: Synthesis rounds (S = Synthesis)

Strategy Stage

Step 1. Select a meaningful project unique to your work or business. If it’s not high stakes enough to require action, scratch it.

Step 2. [SM - Source Material] After reflecting on the desired outcome of the piece, type out your first draft. Created entirely by you, the human(s). This becomes your "source material" and the foundation for all subsequent analysis.

Step 3. [C - Context Brief] Describe and establish clear context: Who you are (or your team), your purpose for writing this piece, what you're attempting to accomplish, and the stakes involved. Share this context with multiple AI models. We use Anthropic's Claude, xAI's Grok, and our customized ChatGPT agent "Learning Producer."

Sparring Stage

Step 4. [R1 - Independent Analysis] Upload your rough draft or “source material” to an AI crew of your choice. We suggest at least three LLMs for identifying potential signals and patterns. 

Prompt them identically with the following: “Read this rough draft and rate it on a scale from 1–10, you cannot use 7. Explain your reasoning with evidence.”

Step 5. Process the feedback from each AI model separately. Consider how the different LLMs evaluated your first iteration. Most rough drafts are usually well, rough! If this is done without AI, consider the biases each person has when sharing their interpretations.

Step 6. Discuss specific points with human teammates or reflect on where you agree and disagree with AI. For example, if the critique involves topics uniquely human, like emotional responses or physical sensations, remember that artificial intelligence can be excellent at explaining yet not always at understanding.

Step 7. Identify patterns among the multiple AI feedback and make revisions or edits. Or, if the topic is too controversial, discuss it with human collaborators or with an offline, uncensored AI model (we use Llama 3 for this using the Ollama app).

Battle Stage

Step 8. Upload revised draft and prompt: “Evaluate this piece and provide an honest review.” From here, you can ask specific follow-up questions: Would you recommend this piece? Purchase this service? Join this team? (AI has its own biases, responses can be subjective, and hallucinations do occur so take it with a grain of salt.)

Step 9. [FQ - Focus Question Injection] Create a focus question based on insights that have emerged. This might involve evaluating your work against specific criteria, research, outside references (books, articles, datasets, philosophies), or newly discovered frameworks.

Step 10. [R2 - Cross-Review Analysis] Ask your focus question to each AI separately. Then give each AI the feedback from the other two AI models, rotating until all models have analyzed each other's responses.

You can guide this move by prompting: “Everything I have shared with you in this discussion as far as my contexts, prompts and source materials, are identical with my interactions with the other two AI models. I am going to share their perspectives with you. Provide any additional insights after considering both their responses. Wait until both AI feedback has been submitted before responding.”

Step 11. [S1 - First Synthesis] Each AI creates their own synthesis, considering their blind spots and how their interpretations overlap and diverge with their AI peers. You now have three "First Syntheses."

Step 12. [S2 - Second Synthesis] Share each AI's First Synthesis with the other AI models. For example: Grok's and Claude's First Syntheses go to Learning Producer GPT, who creates a synthesis of those two syntheses. Repeat until you have three "Second Syntheses."

Step 13. Consider important details and results you may have previously been unaware of. Process the Second Syntheses and apply signaling feedback (patterns, latent structures) to reiterate your piece once more. If necessary, take any action you must to address any emerging insights unique to your circumstances.

Step 14. Prepare final draft, decide on the outlets to distribute your piece, and prompt your AI crew (or friends IRL) with the following:

“Read this final draft, is this piece grammatically correct and ready for publication?”

Step 15. Review feedback and make last minute adjustments if needed.

Champion Stage

Step 16. Publish your piece. Share it with your intended audience across chosen platforms.

Step 17. Analyze metrics. Impressions, comments, business outcomes.

Step 18. Acknowledge results, whether engagement is high or low.

Step 19. Celebrate, you didn’t just talk about free speech; you lived it.

This represents the first major iteration of Combat Writing since Learning Producers, Inc was founded in the summer of 2023. After extensive internal testing, we’re ready for users to join our pilot program: The Writing Production.

Apply here: https://www.learningproducers.com/services

[Free 10 min discovery call for interested testers!]

You can also try out Combat Writing on your own and share your thoughts or published pieces with us. This isn’t for the faint of heart. It’s just for those with heart. Our motto: Reading is peace; writing is war!

COMBAT WRITING FRAMEWORK VISUAL OUTLINE

STRATEGY STAGE (Steps 1-3)

├─ SM: Source Material (Human-created first draft)

├─ C: Context Brief (Stakes, Goals, Constraints)

SPARRING STAGE (Steps 4-7)

├─ R1: Independent Analysis (3+ AI models rate & critique)

├─ Human Processing (Identify patterns, make revisions)

BATTLE STAGE (Steps 8-15)

├─ FQ: Focus Question Injection (Based on emerging insights)

├─ R2: Cross-Review Analysis (AI models analyze each other's R1 feedback)

├─ S1: First Synthesis (Each AI synthesizes other AIs' perspectives)

├─ S2: Second Synthesis (Each AI synthesizes other AIs' First Syntheses)

├─ Human Integration & Final Draft

CHAMPION STAGE (Steps 16-19)

├─ Publication

├─ Metrics Analysis

├─ Results Acknowledgment

└─ Celebration