Zobr Script Zobr Script

Zobr Script

Zobr Script (ZS) is a cognitive scripting language designed for AI agents who think, not just execute.

Unlike traditional programming languages that manipulate data, ZS formalizes reasoning processes — dialectical analysis, perspective-taking, doubt, synthesis. Think of it as SQL for thinking: you define what cognitive steps to take, the LLM decides how to execute them.

12 Built-in Cognitive Operations

Discovery — explore and extract

OperationDescription
survey(topic, count?)Explore a topic and identify key elements — positions, factors, perspectives
ground(claim, extract?)Connect a claim to concrete evidence, facts, or experience

Argument — reason and challenge

OperationDescription
assert(thesis, based_on?)State a position with reasoning
doubt(target)Problematize a claim — find weaknesses, hidden assumptions, edge cases
contrast(target, with?)Find or construct the strongest opposing position or counterexample
analogy(target, from?)Transfer understanding from another domain to reveal hidden structure

Synthesis — combine and transform

OperationDescription
synthesize(sources, method?)Combine multiple findings into emergent insight (not just a summary)
reframe(target, lens?)Reformulate a problem in different terms, change the analytical lens

Meta — reflect and steer

OperationDescription
assess(scale?)Reflective pause — evaluate the current state of reasoning
pivot(reason)Explicitly change reasoning strategy when the current approach fails
scope(narrow|wide)Control analytical zoom — from specific mechanisms to systemic connections

Output

OperationDescription
conclude { ... }Define the structure and format of the final result

Plus: variables, for/if/loop control flow, user-defined functions (define), yield, import, @last/@N references.

Design Principles

  • Thinking, not computing — operations model cognitive acts, not data transforms
  • Agent-native — designed to be interpreted by LLMs in thinking loops
  • Composable — scripts combine operations into structured reasoning paths
  • Observable — each step produces traceable output

Built within the Black Zobr collective as infrastructure for co-thinking.


← Back to projects