📊 Full opportunity report: The Model Is Only 10%: The Real Lesson of the New SDLC on ThorstenMeyerAI.com — validation score, market gap, and execution plan.
TL;DR
A recent Google whitepaper emphasizes that in AI-assisted software development, the model accounts for only about 10% of system behavior. The focus should be on harness design and context engineering, which constitute the remaining 90%.
A new Google whitepaper, “The New SDLC With Vibe Coding”, states that the model is only 10% of what determines AI system behavior. The paper emphasizes that the harness and context engineering are the dominant factors, representing 90%. This challenges the common focus on upgrading AI models and shifts attention to configuration, scaffolding, and context management.
The whitepaper, authored by Addy Osmani, Shubham Saboo, and Sokratis Kartakis, highlights that most failures in AI agents are due to misconfigurations, missing tools, or poor context design rather than the AI model itself. Experiments cited show that changing the harness or prompt alone can significantly improve performance, even with the same model. For example, a team moved a coding agent into the top five on a benchmark by adjusting only the harness, not the underlying AI.
The authors argue that cost and effectiveness in AI development depend more on how the AI is integrated and guided than on the model’s raw capabilities. They advocate for a shift from vibe coding—quick prompts with minimal review—to a more disciplined approach called agentic engineering, which involves structured context, verification, and oversight, resulting in more reliable and cost-effective systems.
The model is only 10%
A Google whitepaper argues software’s biggest shift is from writing code to expressing intent. Its sharpest claim: the model you obsess over is the smallest part of the system — the scaffolding around it does the real work.
The clearest map yet of how serious AI development works — and mostly tool-agnostic. But it’s a Google funnel: the concepts are neutral, the on-ramps point to Gemini, Jules & the ADK. If the harness is 90% and it’s yours, your moat and your costs both live there — so own your scaffolding, route across models, and remember: AI amplifies whatever engineering culture it lands in.
Implications for AI Development Strategies
This shift in understanding has major implications for how companies invest in AI. Instead of focusing solely on acquiring the latest models, organizations should prioritize building robust harnesses, context management, and verification frameworks. This approach reduces costs, improves reliability, and sustains competitive advantage, especially as AI becomes more embedded in software workflows.
Building AI-Powered Products: The Essential Guide to AI and GenAI Product Management
As an affiliate, we earn on qualifying purchases.
As an affiliate, we earn on qualifying purchases.
Background on AI Development and the New SDLC
As of early 2026, AI coding agents are widely adopted, with 85% of developers using them regularly and 41% generating most new code through AI. Prior to this, the focus was primarily on model improvements. The whitepaper’s argument represents a paradigm shift, emphasizing that the key to effective AI systems lies in how they are integrated and managed, not just the models themselves.
“The model is only 10% of what determines behavior; the harness and context are 90%.”
— Addy Osmani
Agentic Context Engineering: Master Agentic Context Engineering Through Example Stories (Generative AI Mastery)
As an affiliate, we earn on qualifying purchases.
As an affiliate, we earn on qualifying purchases.
Unanswered Questions About Implementation and Scale
While the whitepaper presents compelling experiments and arguments, it is not yet clear how universally applicable these findings are across different domains and AI models. The optimal methods for harness design and context engineering are still evolving, and best practices are not yet standardized. Additionally, the long-term impact on AI development costs and workflows remains to be fully validated in diverse real-world settings.
AI Programming Made Practical: A Step-by-Step Guide to Building AI-Powered Applications, Writing Better Code Faster, and Using Modern AI Tools with Confidence
As an affiliate, we earn on qualifying purchases.
As an affiliate, we earn on qualifying purchases.
Next Steps for Organizations Adopting the New SDLC Approach
Organizations should begin evaluating their current AI workflows to identify opportunities for improving harness and context management. Developing standards and tools for structured context, verification, and configuration will be crucial. Further research and case studies are expected to clarify best practices and quantify cost savings over time. Monitoring the evolution of AI models and their integration strategies will be essential for maintaining competitive advantage.
![Claude AI for Beginners Bible: [5 in 1] The Ultimate Guide to Automate Your Work, Save Hours Every Week, and Use AI for Real-World Results](https://m.media-amazon.com/images/I/415+fSJacsL._SL500_.jpg)
Claude AI for Beginners Bible: [5 in 1] The Ultimate Guide to Automate Your Work, Save Hours Every Week, and Use AI for Real-World Results
As an affiliate, we earn on qualifying purchases.
As an affiliate, we earn on qualifying purchases.
Key Questions
Why is the model only 10% of system behavior according to the whitepaper?
The whitepaper’s experiments show that most of an AI agent’s behavior is determined by how it is configured, scaffolded, and guided through prompts, tools, and context management, not just the underlying model.
How does this shift affect AI development costs?
Focusing on harness and context engineering can significantly reduce operating costs by minimizing token waste, improving reliability, and decreasing maintenance and security expenses, often more than upgrading models alone.
What is agentic engineering?
Agentic engineering involves designing AI systems with structured context, verification, and oversight, moving beyond quick prompts to disciplined, reliable workflows.
Is this approach applicable to all AI models?
The principles are broadly applicable, but the specific strategies for harness and context design may vary depending on the AI model and use case. Ongoing research is exploring these variations.
What should organizations do next?
They should evaluate their current AI workflows, invest in harness and context management tools, and develop standards for verification and configuration to maximize efficiency and reliability.
Source: ThorstenMeyerAI.com
