> ## Content Index
> Fetch the complete content index at: https://www.antoinebuteau.com/llms.txt
> Use this file to discover other available public pages before exploring further.

# Lessons from Drew Breunig
- URL: https://www.antoinebuteau.com/lessons-from-drew-breunig/
- Published: 2026-06-06T03:00:30.000Z
- Updated: 2026-09-05T03:06:16.000Z
- Description: Drew Breunig presents Part 1 of the Gods, Interns, and Cogs Framework. Its contrasting labels establish the central question worth studying: what separates these three categories, and what does their relationship reveal within the framework’s own terms?
- Author: Antoine Buteau
- Tags: Profile, AI & Machine Learning Profiles

![Visual summary of operating lessons from Drew Breunig.](https://www.antoinebuteau.com/content/images/2026/06/lessons-from-drew-breunig-profile-infographic.webp)

## Part 1: The Gods, Interns, and Cogs Framework

1. **On the Taxonomy of AI:** "AI use cases can be simplified into three distinct buckets: Gods, Interns, and Cogs." — [*Source: dbreunig.com*](https://www.dbreunig.com/2024/02/05/the-3-ai-use-cases-gods-interns-and-cogs.html?ref=antoinebuteau.com)
2. **On Defining Gods:** "Gods are super-intelligent, artificial entities that do things autonomously and represent the human replacement use case." — [*Source: dbreunig.com*](https://www.dbreunig.com/2024/02/05/the-3-ai-use-cases-gods-interns-and-cogs.html?ref=antoinebuteau.com)
3. **On the Capital Barrier:** "Building AI Gods requires ungodly amounts of capital—billions or trillions of dollars—making it a game only for the largest labs." — [*Source: dbreunig.com*](https://www.dbreunig.com/2024/02/05/the-3-ai-use-cases-gods-interns-and-cogs.html?ref=antoinebuteau.com)
4. **On Defining Interns:** "Interns are supervised copilots that collaborate with experts, focusing on the grunt work of drafting, brainstorming, and summarizing." — [*Source: dbreunig.com*](https://www.dbreunig.com/2024/02/05/the-3-ai-use-cases-gods-interns-and-cogs.html?ref=antoinebuteau.com)
5. **On Expert Oversight:** "The defining quality of an Intern is that it is used and supervised by an expert who can catch its inevitable mistakes." — [*Source: dbreunig.com*](https://www.dbreunig.com/2024/02/05/the-3-ai-use-cases-gods-interns-and-cogs.html?ref=antoinebuteau.com)
6. **On Error Tolerance:** "Interns have a high tolerance for errors because a human expert reviews their output before it is ever used in a final product." — [*Source: dbreunig.com*](https://www.dbreunig.com/2024/02/05/the-3-ai-use-cases-gods-interns-and-cogs.html?ref=antoinebuteau.com)
7. **On Realized Value:** "Today, Interns are delivering the lion's share of the realized value from AI because they augment existing human workflows." — [*Source: dbreunig.com*](https://www.dbreunig.com/2024/02/05/the-3-ai-use-cases-gods-interns-and-cogs.html?ref=antoinebuteau.com)
8. **On Defining Cogs:** "Cogs are functions optimized to perform a single task extremely well, usually as part of a larger, automated software pipeline." — [*Source: dbreunig.com*](https://www.dbreunig.com/2024/02/05/the-3-ai-use-cases-gods-interns-and-cogs.html?ref=antoinebuteau.com)
9. **On Low Error Tolerance:** "Cogs have a low tolerance for errors because they run unsupervised; if a Cog fails, the entire pipeline often fails with it." — [*Source: dbreunig.com*](https://www.dbreunig.com/2024/02/05/the-3-ai-use-cases-gods-interns-and-cogs.html?ref=antoinebuteau.com)
10. **On Sorting for Bottlenecks:** "Sorting AI into these buckets helps identify the specific technical and capital bottlenecks holding back each category of application." — [*Source: dbreunig.com*](https://www.dbreunig.com/2024/02/05/the-3-ai-use-cases-gods-interns-and-cogs.html?ref=antoinebuteau.com)

## Part 2: Context Engineering Fundamentals

1. **On the Core Definition:** "Context Engineering is the systematic discipline of designing, organizing, and optimizing the complete informational payload provided to an LLM at inference time." — [*Source: dbreunig.com*](https://www.dbreunig.com/2024/05/13/context-engineering.html?ref=antoinebuteau.com)
2. **On the RAM Metaphor:** "If the LLM is the CPU, the context window is the RAM—the model’s limited, high-speed working memory that must be managed." — [*Source: dbreunig.com*](https://www.dbreunig.com/2024/05/13/context-engineering.html?ref=antoinebuteau.com)
3. **On Architecture vs. Text:** "Context is no longer just a string of text; it is a compilation pipeline that assembles data, tools, and state." — [*Source: dbreunig.com*](https://www.dbreunig.com/2024/05/13/context-engineering.html?ref=antoinebuteau.com)
4. **On the 80/20 Rule:** "In production AI, the prompt is 20% of the work; the other 80% is the engineering of the environment and context around it." — [*Source: dbreunig.com*](https://www.dbreunig.com/2024/05/13/context-engineering.html?ref=antoinebuteau.com)
5. **On Context as a Product:** "Your knowledge base and context assembly logic should be treated as a living product, not a static asset." — [*Source: dbreunig.com*](https://www.dbreunig.com/2024/05/13/context-engineering.html?ref=antoinebuteau.com)
6. **On the Iceberg Insight:** "Prompt engineering focuses on the tip, the instruction; context engineering focuses on the massive submerged portion, the data environment." — [*Source: dbreunig.com*](https://www.dbreunig.com/2024/05/13/context-engineering.html?ref=antoinebuteau.com)
7. **On Pure Functionality:** "LLMs are essentially pure functions; the quality of the output depends entirely on the structure and relevance of the input context." — [*Source: dbreunig.com*](https://www.dbreunig.com/2024/05/13/context-engineering.html?ref=antoinebuteau.com)
8. **On Situational Awareness:** "Context engineering gives AI the situational awareness needed to act with relevance and precision in a specific business domain." — [*Source: dbreunig.com*](https://www.dbreunig.com/2024/05/13/context-engineering.html?ref=antoinebuteau.com)
9. **On Stateless to Stateful:** "Prompting is for stateless tasks; context engineering is for stateful, multi-turn agentic workflows that require memory." — [*Source: dbreunig.com*](https://www.dbreunig.com/2024/05/13/context-engineering.html?ref=antoinebuteau.com)
10. **On the Karpathy Effect:** "The term 'Context Engineering' identified a common technical experience that had been felt but not yet named by the community." — [*Source: dbreunig.com*](https://www.dbreunig.com/2024/05/13/context-engineering.html?ref=antoinebuteau.com)

## Part 3: The Mechanics of Context Rot

1. **On Context Poisoning:** "Context poisoning occurs when a hallucination enters the context window and the model repeatedly references it as truth in future turns." — [*Source: dbreunig.com*](https://www.dbreunig.com/2024/04/23/context-rot.html?ref=antoinebuteau.com)
2. **On Context Distraction:** "When the context grows too large, the model may over-focus on provided text and neglect the logic of its underlying training." — [*Source: dbreunig.com*](https://www.dbreunig.com/2024/04/23/context-rot.html?ref=antoinebuteau.com)
3. **On Context Confusion:** "Superfluous or irrelevant information in the window causes context confusion, leading the model to generate low-quality, noisy responses." — [*Source: dbreunig.com*](https://www.dbreunig.com/2024/04/23/context-rot.html?ref=antoinebuteau.com)
4. **On Context Clash:** "Context clash happens when new tool outputs or user inputs conflict with earlier instructions or established conversation facts." — [*Source: dbreunig.com*](https://www.dbreunig.com/2024/04/23/context-rot.html?ref=antoinebuteau.com)
5. **On Lost in the Middle:** "Accuracy drops significantly when the decisive fact is buried in the middle of a long context window rather than the ends." — [*Source: dbreunig.com*](https://www.dbreunig.com/2024/04/23/context-rot.html?ref=antoinebuteau.com)
6. **On Context Rot:** "Context rot is the systematic degradation of AI performance as a session grows longer and the signal-to-noise ratio drops." — [*Source: dbreunig.com*](https://www.dbreunig.com/2024/04/23/context-rot.html?ref=antoinebuteau.com)
7. **On Token Pressure:** "As the window fills, models start cutting corners, leading to shorter, less nuanced, or logically incomplete reasoning." — [*Source: dbreunig.com*](https://www.dbreunig.com/2024/04/23/context-rot.html?ref=antoinebuteau.com)
8. **On Instruction Drift:** "Models tend to stop honoring initial system constraints as the volume of conversation history accumulates in the window." — [*Source: dbreunig.com*](https://www.dbreunig.com/2024/04/23/context-rot.html?ref=antoinebuteau.com)
9. **On the U-Shaped Curve:** "Retrieval performance follows a U-shaped curve; models remember the beginning and the end but fail at the center." — [*Source: dbreunig.com*](https://www.dbreunig.com/2024/04/23/context-rot.html?ref=antoinebuteau.com)
10. **On the Attention Tax:** "If you put something in the context, the model has to pay attention to it, whether it is relevant or not." — [*Source: dbreunig.com*](https://www.dbreunig.com/2024/04/23/context-rot.html?ref=antoinebuteau.com)

## Part 4: AI Product Strategy and Subsumption

1. **On the Subsumption Window:** "The subsumption window is the time between a product's launch and when a future foundation model replicates its core functionality." — [*Source: dbreunig.com*](https://www.dbreunig.com/2024/01/22/the-subsumption-window.html?ref=antoinebuteau.com)
2. **On What to Build Today:** "The haunting question for every AI product team is: what can you build today that won't be subsumed by tomorrow's model?" — [*Source: dbreunig.com*](https://www.dbreunig.com/2024/01/22/the-subsumption-window.html?ref=antoinebuteau.com)
3. **On Resistance to Subsumption:** "Features resistant to subsumption include unique user interfaces, proprietary data access, and complex multi-step workflow integration." — [*Source: dbreunig.com*](https://www.dbreunig.com/2024/01/22/the-subsumption-window.html?ref=antoinebuteau.com)
4. **On Spec-Driven Development:** "In spec-driven development, the specification is the actual product, and the code is merely a generated artifact." — [*Source: GitHub*](https://github.com/dbreunig/wenwords?ref=antoinebuteau.com)
5. **On the Spec-Tests-Code Triangle:** "Reliable AI systems require a Spec-Tests-Code triangle where the model's output is constantly validated against rigid specifications." — [*Source: GitHub*](https://github.com/dbreunig/wenwords?ref=antoinebuteau.com)
6. **On AI as a Commodity:** "The model itself is becoming a commodity; the value lies in the specialized context and the workflow it enables." — [*Source: dbreunig.com*](https://www.dbreunig.com/2024/01/22/the-subsumption-window.html?ref=antoinebuteau.com)
7. **On Unique UI as Defense:** "A specialized UI that solves a specific user problem remains a defensive moat even when the underlying model gets smarter." — [*Source: dbreunig.com*](https://www.dbreunig.com/2024/01/22/the-subsumption-window.html?ref=antoinebuteau.com)
8. **On Proprietary Data as Defense:** "Proprietary data that the model hasn't seen during training is the most robust defense against being subsumed." — [*Source: dbreunig.com*](https://www.dbreunig.com/2024/01/22/the-subsumption-window.html?ref=antoinebuteau.com)
9. **On the Year of Context:** "2026 will be the year where context engineering officially replaces prompt engineering as the dominant technical discipline." — [*Source: dbreunig.com*](https://www.dbreunig.com/2024/05/13/context-engineering.html?ref=antoinebuteau.com)
10. **On the Communication Tax:** "Emergent fields pay a communication tax; we must agree on the meaning of words before we can do productive work." — [*Source: dbreunig.com*](https://www.dbreunig.com/2024/05/13/context-engineering.html?ref=antoinebuteau.com)

## Part 5: Location Intelligence and Geospatial Standards

1. **On Making Place as Easy as Time:** "The goal of modern geospatial engineering is to make place as easy to work with as time is in software." — [*Source: dbreunig.com*](https://www.dbreunig.com/2023/10/24/making-place-easy.html?ref=antoinebuteau.com)
2. **On Standardizing the Built Environment:** "Standardizing the human-made world—stores, offices, and infrastructure—is far more complex than mapping natural geography." — [*Source: dbreunig.com*](https://www.dbreunig.com/2023/10/24/making-place-easy.html?ref=antoinebuteau.com)
3. **On the Join Problem:** "The hardest part of geospatial data is the 'join'—trying to combine disparate datasets that refer to the same physical location." — [*Source: dbreunig.com*](https://www.dbreunig.com/2023/10/24/making-place-easy.html?ref=antoinebuteau.com)
4. **On Placekey Utility:** "Placekey provides a universal identifier for physical places, solving the joining problem without sharing sensitive latitude/longitude data." — [*Source: Placekey Blog*](https://www.placekey.io/blog?ref=antoinebuteau.com)
5. **On Overture Maps and GERS:** "The Global Entity Reference System (GERS) is the industry's attempt to create a common ID for every building on Earth." — [*Source: Overture Maps Foundation*](https://overturemaps.org/news/?ref=antoinebuteau.com)
6. **On Location-Aware Insights:** "Location intelligence is really about understanding journeys and brand affinities, not just seeing pings on a map." — [*Source: dbreunig.com*](https://www.dbreunig.com/2023/10/24/making-place-easy.html?ref=antoinebuteau.com)
7. **On Mapping the Human-Made World:** "We spend 90% of our lives inside the human-made world, yet our maps are still largely focused on the natural one." — [*Source: dbreunig.com*](https://www.dbreunig.com/2023/10/24/making-place-easy.html?ref=antoinebuteau.com)
8. **On Data Interoperability:** "Geospatial data interoperability is the prerequisite for building truly intelligent local service agents." — [*Source: Overture Maps Foundation*](https://overturemaps.org/news/?ref=antoinebuteau.com)
9. **On the GERS Importance:** "GERS isn't just a database; it's a shared language that allows different organizations to speak about the same physical entities." — [*Source: Overture Maps Foundation*](https://overturemaps.org/news/?ref=antoinebuteau.com)

## Part 6: Data Integrity and Information Environments

1. **On Information Environment vs. Model:** "The model is not the bottleneck; the information environment you construct around the model determines its reliability." — [*Source: dbreunig.com*](https://www.dbreunig.com/2024/05/13/context-engineering.html?ref=antoinebuteau.com)
2. **On Data Integrity as Strategy:** "Data integrity is a strategic positioning problem; if you can't trust the data, you can't build a product around it." — [*Source: Precisely Blog*](https://www.precisely.com/blog?ref=antoinebuteau.com)
3. **On Reliability over Optimization:** "In the current era of LLMs, reliability is a much bigger bottleneck for adoption than speed or cost optimization." — [*Source: dbreunig.com*](https://www.dbreunig.com/2024/05/13/context-engineering.html?ref=antoinebuteau.com)
4. **On Context as Infrastructure:** "Enterprise context is shifting from a per-call variable to a governed, unified infrastructure layer shared by many agents." — [*Source: dbreunig.com*](https://www.dbreunig.com/2024/05/13/context-engineering.html?ref=antoinebuteau.com)
5. **On Context Caching:** "Context caching is the primary technical lever for making large, static background information affordable at scale." — [*Source: dbreunig.com*](https://www.dbreunig.com/2024/05/13/context-engineering.html?ref=antoinebuteau.com)
6. **On Stable Prefixes:** "Keep prompt prefixes stable and predictable to maximize cache reuse and significantly lower overall system latency." — [*Source: dbreunig.com*](https://www.dbreunig.com/2024/05/13/context-engineering.html?ref=antoinebuteau.com)
7. **On Deterministic Serialization:** "Serialize your context, actions, and observations in a predictable, repeatable order to ensure model consistency." — [*Source: dbreunig.com*](https://www.dbreunig.com/2024/05/13/context-engineering.html?ref=antoinebuteau.com)
8. **On Noise Filtering:** "The science of context engineering is often more about what you systematically exclude than what you choose to include." — [*Source: dbreunig.com*](https://www.dbreunig.com/2024/05/13/context-engineering.html?ref=antoinebuteau.com)
9. **On the Wiki Sweet Spot:** "For many corporate agents, a curated wiki of 1,000 high-signal documents is more valuable than an unmanaged lake of 1,000,000." — [*Source: dbreunig.com*](https://www.dbreunig.com/2024/05/13/context-engineering.html?ref=antoinebuteau.com)

## Part 7: Engineering Reliability and Tool Harnesses

1. **On Compound AI Systems:** "Modern AI systems are compound architectures built from multiple models, specialized tools, and state management logic." — [*Source: dbreunig.com*](https://www.dbreunig.com/2024/05/13/context-engineering.html?ref=antoinebuteau.com)
2. **On the Agent Harness:** "The agent harness is the software wrapper that manages the flow of context, memory, and tool-calling in and out of the model." — [*Source: dbreunig.com*](https://www.dbreunig.com/2024/05/13/context-engineering.html?ref=antoinebuteau.com)
3. **On Software Engineering Best Practices:** "Software engineering remains the discipline of managing complexity and reliability, even when models do the coding." — [*Source: dbreunig.com*](https://www.dbreunig.com/2024/05/13/context-engineering.html?ref=antoinebuteau.com)
4. **On Evals as Backbone:** "Rigorous, automated evaluations are the backbone of any successful context engineering project." — [*Source: dbreunig.com*](https://www.dbreunig.com/2024/05/13/context-engineering.html?ref=antoinebuteau.com)
5. **On the Reliability Bottleneck:** "Employees won't use AI if it's wrong even 10% of the time, because then it becomes more work to supervise than to do manually." — [*Source: dbreunig.com*](https://www.dbreunig.com/2024/02/05/the-3-ai-use-cases-gods-interns-and-cogs.html?ref=antoinebuteau.com)
6. **On Tool Loadout:** "Actively selecting only the subset of tools relevant to a specific task phase prevents the model from becoming confused by tool sprawl." — [*Source: dbreunig.com*](https://www.dbreunig.com/2024/05/13/context-engineering.html?ref=antoinebuteau.com)
7. **On Context Quarantine:** "Isolate specific sub-tasks into their own dedicated threads to prevent early errors from poisoning the entire project context." — [*Source: dbreunig.com*](https://www.dbreunig.com/2024/04/23/context-rot.html?ref=antoinebuteau.com)
8. **On Agentic RAG:** "We are moving from fixed RAG pipelines to reasoning loops where the agent proactively decides what information it needs to retrieve." — [*Source: dbreunig.com*](https://www.dbreunig.com/2024/05/13/context-engineering.html?ref=antoinebuteau.com)
9. **On Black Box Memory Warning:** "Avoid black box memory systems; agents need transparent, auditable, and steerable memory to be safe for production." — [*Source: dbreunig.com*](https://www.dbreunig.com/2024/05/13/context-engineering.html?ref=antoinebuteau.com)

## Part 8: The Cultural and Linguistic Shift of AI

1. **On Language Defining Reality:** "Language does not just describe reality; it defines reality and puts hard limits on the conversations we can have." — [*Source: dbreunig.com*](https://www.dbreunig.com/2024/05/13/context-engineering.html?ref=antoinebuteau.com)
2. **On Knighting Buzzwords:** "The term 'context engineering' gained traction because it was knighted by industry leaders, crystallizing a shared technical experience." — [*Source: dbreunig.com*](https://www.dbreunig.com/2024/05/13/context-engineering.html?ref=antoinebuteau.com)
3. **On AI Fluency as Leadership:** "AI fluency is no longer a technical nice-to-have; it is a mandatory leadership skill for anyone managing a modern workforce." — [*Source: dbreunig.com*](https://www.dbreunig.com/2024/02/05/the-3-ai-use-cases-gods-interns-and-cogs.html?ref=antoinebuteau.com)
4. **On Transforming Thought:** "AI isn't just transforming the work we produce; it is transforming how we think through problems together in teams." — [*Source: dbreunig.com*](https://www.dbreunig.com/2024/02/05/the-3-ai-use-cases-gods-interns-and-cogs.html?ref=antoinebuteau.com)
5. **On AI Security as Proof of Work:** "Cybersecurity increasingly looks like proof of work; you don't win by being clever, you win by out-spending the attacker in tokens." — [*Source: dbreunig.com*](https://www.dbreunig.com/2024/05/13/context-engineering.html?ref=antoinebuteau.com)
6. **On Tokens as Proof of Stake:** "Tokens are the new units of digital verification; the cost of compute is becoming the ultimate barrier to entry for malicious actors." — [*Source: dbreunig.com*](https://www.dbreunig.com/2024/05/13/context-engineering.html?ref=antoinebuteau.com)
7. **On the Cathedral and the Bazaar:** "The future of AI is a battle between the Cathedral of closed labs and the Bazaar of open-source context engineers." — [*Source: dbreunig.com*](https://www.dbreunig.com/2024/02/05/the-3-ai-use-cases-gods-interns-and-cogs.html?ref=antoinebuteau.com)
8. **On the Winchester Mystery House Warning:** "Avoid building AI systems that grow haphazardly like the Winchester Mystery House; they need a central, intentional architecture." — [*Source: dbreunig.com*](https://www.dbreunig.com/2024/05/13/context-engineering.html?ref=antoinebuteau.com)