# Verification Design > Sourced principles and executable, stdlib-only Python pattern cards for verifying agent work: designing evals, checking tool-use output, and replacing self-review with external signals. Use when an agent must check its own or another agent's work. Content is licensed under CC BY 4.0. Markdown links provide reference documents and generated indexes for the corresponding HTML pages. ## Available representations - [llms.txt](https://verificationdesign.com/llms.txt): This index. Fetch first. - [llms-full.txt](https://verificationdesign.com/llms-full.txt): The full corpus in one plain-text file: principles, all cards in reading order, references. Fetch when you need everything. - [catalog.json](https://verificationdesign.com/catalog.json): Versioned routing manifest with revision and content hashes; per-card title, intent, URLs, related cards, first-paragraph determinism move, observable signal report fields, use_when and do_not_use_when lists, pattern_example and evidence_count coverage, plus the failure map. Coverage records are not research approval. Fetch to pick one card without loading the corpus. - [patterns.md](https://verificationdesign.com/patterns.md): Pattern index with the failure map. Fetch to choose a pattern from a symptom. - [context-and-state.md](https://verificationdesign.com/patterns/context-and-state.md): Index of the Context and State cards. - [verification.md](https://verificationdesign.com/patterns/verification.md): Index of the Verification cards. - [orchestration.md](https://verificationdesign.com/patterns/orchestration.md): Index of the Orchestration cards. - [principles.md](https://verificationdesign.com/principles.md): The complete reference document; the HTML Principles page is a shorter, illustrated overview. - [references.md](https://verificationdesign.com/references.md): Deduplicated sources. ## Principles - [Verification Design Principles](https://verificationdesign.com/principles.md): The complete reference document; the HTML Principles page is a shorter, illustrated overview. - [Raw principles source](https://raw.githubusercontent.com/verificationdesign/verificationdesign/3b649727271ca7fb20e88b2aa0837feb35859e1e/verification_design.md): The repository source file, raw markdown. ## Context and State Patterns - [Constitution](https://verificationdesign.com/patterns/context-and-state/constitution.md): Represent the system’s verification criteria as explicit, versioned, machine-readable data, rather than as scattered prompt prose. - [Guardrail Decorator](https://verificationdesign.com/patterns/context-and-state/guardrail-decorator.md): Wrap a model call, tool call, or other model-output boundary in a policy decorator that can deny, replace, sanitize, or convert errors, so policy lives in code at the boundary the model crosses instead of in prompt prose the model is asked to obey. - [Causal Tag](https://verificationdesign.com/patterns/context-and-state/causal-tag.md): Stamp emitted events with stable joinable identifiers and parent links, then join destination observations to recorded actions; causal attribution depends on trustworthy tag generation and propagation. - [Trajectory Cursor](https://verificationdesign.com/patterns/context-and-state/trajectory-cursor.md): Maintain an explicit, structured record of where the agent is in its multi-step process and what happened at each boundary, so the verifier and the next turn can read the trajectory instead of inferring it from chat history or model recall. - [State Baseline](https://verificationdesign.com/patterns/context-and-state/state-baseline.md): Capture the relevant environment or process state before an action under verification, so the verifier can establish that observed state did not already exist before the action; causal attribution requires isolation or a Causal Tag. ## Verification Patterns - [Executable Analog](https://verificationdesign.com/patterns/verification/executable-analog.md): Translate a subjective, language-based verification step into a deterministic, programmatic execution step that yields a binary pass/fail signal independent of the agent's judgment. - [Blind Oracle](https://verificationdesign.com/patterns/verification/blind-oracle.md): Derive expected evidence from the spec, the question, or independent re-execution without conditioning that derivation on the agent's draft, reasoning trace, or shortcut history. - [Comparator](https://verificationdesign.com/patterns/verification/comparator.md): Express verification comparison as a named operator from a finite family, so the verdict is a deterministic function of (expected, observed, operator, threshold, normalization) rather than a model's interpretation of "does this look right?" - [Delta](https://verificationdesign.com/patterns/verification/delta.md): Check whether the observed change in environment state satisfies an action's expected postcondition; attribution to that action requires isolation or a propagated causal tag. - [Judge Harness](https://verificationdesign.com/patterns/verification/judge-harness.md): Wrap an LLM judge in a structural harness of perturbation, repetition, calibration, and reporting so that one judge verdict becomes a measured signal with visible consistency and bias controls. - [Admissibility Gate](https://verificationdesign.com/patterns/verification/admissibility-gate.md): Replace tone-level skepticism instructions with admissibility rules that define what counts as proof, name common shortcut paths to reject, and invert the verifier's default from "accept if plausible" to "fail unless backed by trusted evidence." ## Orchestration Patterns - [Cross-Family](https://verificationdesign.com/patterns/orchestration/cross-family.md): Run high-leverage generation and high-leverage assessment on deliberately different model families, and record both identities, so exposure to shared training-data biases and shared latent priors is reduced rather than assumed away, and any residual correlated error is attributable to named models. - [Adversary](https://verificationdesign.com/patterns/orchestration/adversary.md): Assign a structurally separate role whose only job is to find failures in another role's output, and require that role to emit a negative channel the orchestrator can inspect. - [Debate](https://verificationdesign.com/patterns/orchestration/debate.md): Run bounded disagreement among multiple roles before a decision, with turn order, round count, phase, and consensus threshold held in orchestration state instead of model discretion. - [Escalation Chain](https://verificationdesign.com/patterns/orchestration/escalation-chain.md): Route work to a higher-authority or different-capability handler through a typed, validated handoff, so the next owner is code-level state instead of a model's memory of who to call. - [Backpressure](https://verificationdesign.com/patterns/orchestration/backpressure.md): When a downstream check fails, route the failure back upstream as structured rerun context within a bounded retry budget, instead of swallowing the failure or retrying blindly. - [Tool Adapter](https://verificationdesign.com/patterns/orchestration/tool-adapter.md): Normalize model-emitted tool calls at a typed boundary: derive or fetch a schema, validate arguments before invocation, call the tool with typed arguments, and return a typed observation. ## References - [References](https://verificationdesign.com/references.md): Deduplicated sources and the pages that cite them. ## Source - [Repository](https://github.com/verificationdesign/verificationdesign): Source repository. - [License](https://creativecommons.org/licenses/by/4.0/): CC BY 4.0. ## Optional - [About](https://verificationdesign.com/about/): A human-facing introduction for operators.