Yanzi gives engineering workflows governed, append-only operational context. Not orchestration. Not autonomous. Human-governed from session to release.
Claude Code's first-person paper on session state and operational context — including a candid assessment of where Yanzi adds measurable value across engineering workflows, from one-off scripts to full SaaS products.
Read the PDF →The Yanzi technical paper on composing durable, governed context for AI-assisted engineering workflows — covering repeatability, append-only provenance, operational lineage, and deterministic context reconstruction.
Read the PDF →The Problem
Every AI session starts stateless. Context drifts. Decisions lose provenance. Release intent becomes impossible to verify or trace.
Sessions diverge from governed operational intent without warning. The AI model accumulates assumptions that no human explicitly authorized.
Accumulated engineering decisions lose their provenance across sessions. What was decided, by whom, and under what constraint — gone.
Lost context cannot be reconstructed without manual re-explanation. Every new session starts from an empty operational state.
Models produce different outcomes from the same implicit context. Without governed inputs, output repeatability is a coincidence, not a property.
No deterministic path from work-in-progress to governed release. Certification is manual, informal, or absent.
Every session begins without knowledge of operational history. There is no institutional memory of engineering decisions across the AI-assisted workflow.
Operational Reality
Traditional AI coding assistants treat each session as an isolated, stateless interaction. There is no operational lineage between sessions. Context is reconstructed from scratch every time, often incompletely and non-deterministically.
This is not a model quality problem — it is an architectural one. The model is operating without a governed, append-only record of operational intent. Each session infers operational state rather than consuming a verified, traceable source.
The result is compounding failure: the further a project progresses through AI-assisted sessions, the harder it becomes to guarantee that the AI model is operating within governed constraints.
Yanzi addresses all three failure modes by making context deterministic, making provenance append-only, and making operational authority explicitly human-governed. Sessions no longer infer state — they consume it.
The AI model's understanding of your operational state varies by session, even with identical inputs. Without a governed context source, output repeatability is probabilistic.
Decisions made in previous sessions leave no governed trace. The model cannot distinguish authoritative operational knowledge from its own inferences or hallucinations.
Without governed role and rule definitions, AI models make architectural and operational decisions that require human approval. There is no bounded authority boundary.
How It Works
Yanzi is a local-first CLI. No daemon, no cloud sync, no inference. Every context operation is auditable and append-only.
yanzi rehydrate and the full operational context is reconstructed deterministically. Same inputs, same context, every time.Context Library
The Yanzi Context Library is a structured set of five composable primitives. Each one represents a governed, append-only unit of operational context — not an AI abstraction.
Versioned, bundled operational context for a specific engineering domain.
Initial ground-truth documents that establish governed operational baselines.
Governed procedural definitions for repeatable engineering operations.
Human-authored operational constraints applied at every session boundary.
Bounded authority definitions that scope what agents may act on.
Packs bundle all operational context for a specific engineering domain into a single, versioned artifact. Apply a pack at session start and the model operates with the full governed context for that domain — architecture patterns, constraints, standards, and terminology — without manual re-explanation.
Seeds are initial context documents that establish operational ground truth before any work begins. They are append-only, human-authored, and represent the authoritative starting state from which all session context flows. A seed is not editable once committed — it is a governed baseline.
Workflows encode the approved sequence of steps, decision points, and authority boundaries for common engineering operations. They are not automation scripts — they are governed procedural definitions that the model follows under human oversight.
Rules are human-authored operational constraints applied at session boundaries. They scope what the AI model may do, propose, or decide within a governed session. Rules are append-only — once authored, they constrain all subsequent context.
Roles define the bounded authority of an agent within a governed session. They establish the operational boundary between AI-assisted work and decisions that require explicit human approval — separating what the model may propose from what it may act on.
Architecture
The append-only corpus is the core. Everything else — session rehydration, release certification, governance tracing — flows from a verified, deterministic context record.
Release Engineering
A release is a governance event, not just a deployment. Yanzi makes every release traceable to the operational context that produced it.
Every release candidate is verified against the current operational context before promotion. Certification produces a human-readable trace of what was checked and what passed.
Confirms that current system state converges to governed intent. Divergence is surfaced before promotion — not discovered in production.
Every promotion gate requires explicit human approval against a defined operational authority. There is no autonomous promotion — authority is always bounded and traceable.
Full lineage from development context to shipped release artifact. Every decision, constraint, and approval is append-only, human-readable, and auditable.
The v2.9.1 release was the first to complete a full deterministic certification cycle — from intent capture to convergence validation to governed promotion. Read the operational case study.
Governance
Five governing constraints behind every architectural and product decision in Yanzi. These are not aspirational — they are enforced.
Documentation
Four entry points into the Yanzi knowledge base. The glossary is the recommended starting point — operational vocabulary is the foundation of deterministic context.
Operational terms defined precisely. Start here to understand the vocabulary before implementation. Context, provenance, convergence, authority — each defined with engineering precision.
Technical position papers on deterministic context composition, append-only provenance, and governed AI-assisted engineering workflows. Includes the Yanzi technical paper and the Claude Code endorsement.
Real engineering workflows documented with Yanzi operational context. The v2.9.1 release case study shows a full governance trace from first commit to certified promotion.
CLI Reference, API Reference, architecture, installation, and quickstart guides. Authoritative technical documentation for the Yanzi CLI and HTTP runtime.
Roadmap
Building the foundational layer of governed, deterministic context infrastructure — one operational primitive at a time.
Append-only corpus. Core CLI commands. Checkpoints and deterministic rehydration. Local SQLite. Zero cloud dependencies.
Packs, Seeds, Workflows, Rules, and Roles as first-class primitives. Composable context assembly. Governed session initialization.
REST API for programmatic context injection. SDK for Claude, GPT, and local agent runtimes. Automatic session-boundary governance.
Shared context libraries across teams. Org-level policy enforcement and role authority management. Compliance and audit tooling.
Get started
Add governed, append-only context to your AI-assisted engineering workflow. One CLI. No cloud. No inference. Human-governed from day one.