Definition
Constitutional Layer
The rules, values, and ethical principles baked into each agent at instantiation. The foundational constraint set that shapes all downstream behavior before any prompt is processed.
From the episode “Your Next Co-Founder Should Be AI”Hear it on the podcast1 episode
Learn the language of AI-native founders
Every week: the new terms, tools, and workflows founders are using, straight from the podcast.
Related terms in AI Fundamentals
Citation-Based RetrievalReturning answers tied to specific document sources.Closed sourceProprietary software whose code is kept private, so the public can't see, modify, or reuse it.Computer visionThe branch of AI that lets computers interpret images and video, like recognizing objects, faces, or text.ConfabulationA human psychology term for the way memory reconstructs rather than records — people create plausible narratives around incomplete memories with no intent to deceive. Geoff draws the parallel to AI hallucinations: both are a system constructing a coherent story from incomplete information. The observation cuts both ways: AI hallucinations aren't as alien as they seem (human memory does the same thing), and human testimony is far less reliable than assumed (well-established in criminal justice research). Working closely with AI has become a useful mirror on human cognition.Context ArchetypeA named configuration of rules governing how an AI generation system behaves in a specific mode — for example, 'creative exploration' vs. 'compliance review.' The same underlying model produces reliably different outputs depending on which archetype is active. In Knapsack's Intelligent Product Engine, archetypes are one of three components (alongside real-time artifact monitoring and a rules engine) that make AI generation predictable and enterprise-appropriate rather than open-ended and unpredictable.Context engineeringStructuring the inputs and memory an LLM receives. Ross Barnes's position is that the difference between reliable and hallucinatory output is almost always context, not model choice.Context GroundingThe practice of providing an AI coding agent with accurate documentation of the existing codebase before asking it to generate or modify code. Without grounding, agents operate on generic code patterns and produce architecturally inconsistent output that may be technically correct in isolation but incompatible with the existing system. BrainGrid generates five grounding documents from the actual repository — architecture overview, key workflows, data structures, directory structure, API patterns — so the agent extends what's there rather than inventing new patterns.Context HallucinationA hallucination that occurs not from false information, but from failure to account for relationships between documents, where one document modifies, contradicts, or conditionally applies to another.