Overview: COAST and SINK
A Complementary Methodology for Knowledge Work in an AI Forward World
Artificial intelligence does not merely accelerate existing ways of working with ideas. It changes the structure of intellectual labor itself. When explanation, critique, and synthesis are always available on demand, the limiting factor is no longer access to information, but how thinking is organized, tested, and shared.
COAST and SINK are two complementary methodologies designed to address this shift. Together, they form a complete practice for knowledge work in an AI forward environment: one governing how ideas are produced, the other governing how they are distributed without loss of agency or rigor.
Neither method is a tool, a platform, or a belief system. They are practicesways of engaging with AI that preserve human judgment while taking advantage of AIs unique strengths.
The Problem They Address
Most current approaches to working with AI focus on tactics: better prompts, faster outputs, or automation of tasks. These approaches tend to collapse thinking into generation and evaluation into trust. The result is often speed without accountability and fluency without understanding.
COAST and SINK begin from a different premise:
AI should extend human thinking, not replace it.
That requires two things:
A disciplined way to think with AI without surrendering authorship.
A disciplined way to share ideas in an AI-mediated world without turning them into persuasion or performance.
COAST addresses the first. SINK addresses the second.
COAST: The Production Side
COAST is a methodology for producing ideas with AI while retaining intellectual sovereignty. It treats AI as a thinking partner that can synthesize, critique, and challenge, but never as an authority.
At its core, COAST emphasizes:
deliberate use of AI for synthesis and exploration, adversarial engagement using multiple models, explicit separation between AI output and human judgment, and the preservation of transcripts as a record of how conclusions were reached.
COAST is slow by design. It resists the temptation to move directly from question to answer. Instead, it creates space for error, revision, and reflection, recognizing that insight often emerges through friction rather than fluency.
The outcome of COAST is not a polished answer, but a conclusion the human author can genuinely stand behindbecause they have seen how it was formed.
SINK: The Distribution Side
SINK is a methodology for sharing ideas once they exist. It assumes that readers now approach material with AI at their side, and that this changes how knowledge should be packaged.
Instead of asking readers to consume long papers linearly, SINK distributes ideas as structured summaries designed for interrogation. These summaries function like source code: bounded, readable, and intended to be executed through questioning rather than absorbed passively.
Under SINK, readers are encouraged to:
feed entire bundles of related summaries into their AI, interrogate claims at their own pace and depth, follow conceptual threads across documents, and form their own understanding without pressure to agree.
SINK is not a teaching method and not a persuasion strategy. It is a navigation layer that makes complex ideas resilient under questioning.
Why They Are Designed as Complements
COAST and SINK address different phases of the same problem.
COAST governs creation: how ideas are generated, tested, and stabilized in the presence of AI.
SINK governs distribution: how those ideas move into other minds without being flattened, distorted, or weaponized.
Used together, they form a closed loop:
COAST minimizes error and self-deception during production.
SINK minimizes misunderstanding and dilution during transmission.
Neither method requires the other to function, but each becomes more powerful when paired. COAST produces material worth interrogating. SINK ensures that interrogation remains possible for others without recreating the entire process.
What This Methodology Isand Is Not
COAST and SINK are intentionally modest in scope.
They are not:
A productivity system, a collaboration platform, a governance framework, or a replacement for primary research.
They are a way of working that assumes curiosity, good faith, and personal responsibility. They do not prevent misuse or guarantee consensus. What they offer instead is a better default: one that favors understanding over speed and interrogation over persuasion.
The Central Claim
As AI becomes ubiquitous, the quality of our thinking will depend less on what tools we use and more on the structures we adopt around them.
COAST and SINK propose such a structure.
They do not tell you what to think.
They give you a way to thinkand a way to let others think with youwithout losing yourself in the process.