Built with Wix and Lodash, hosted on Wix behind Cloudflare. Domain registered in 2025.
sdi-protocol.org is built with Wix, hosted on Wix behind Cloudflare.
| Technology | Version | First seen |
|---|---|---|
| CMS & Site Builders1 | ||
| – | 7 Nov 2026 | |
| JavaScript Frameworks & Libraries2 | ||
| – | 7 Nov 2026 | |
| Frontend Build Tools & CSS1 | ||
| – | 7 Nov 2026 | |
| CDN & Hosting2 | ||
| – | 7 Nov 2026 | |
| Error Tracking & Performance Monitoring1 | ||
| 7.120.3 | 7 Nov 2026 | |
| Fonts & Icon Fonts1 | ||
| – | 7 Nov 2026 | |
| Security, WAF & Bot Protection1 | ||
| – | 7 Nov 2026 | |
Registration from the registry's RDAP record, the certificate the site serves, and its rank in public traffic lists.
The crew hasn’t read this site’s colors yet. We read a palette when we capture a site’s screenshot, busiest sites first. Meanwhile, browse palettes from other sites.
Counted from every stack change we've recorded: of the sites we watched running one of this site's tools, how many went on to add another. A pattern across sites, not a forecast for this one.
From what the site says about itself, and account IDs it shares with other sites.
aspmx.l.google.comalt1.aspmx.l.google.comalt2.aspmx.l.google.comalt3.aspmx.l.google.comalt4.aspmx.l.google.comns3.wixdns.netns2.wixdns.netgoogle-site-verification=3A2hOCnSrASldye-LNqYbxV7EXji36BDyChMWj7VmfAv=spf1 include:_spf.google.com ~all# robots.txt - sdi-protocol.org # Protocol: SDI_PROTOCOL_v1 | DER: SDI_DER_v1.1 # Copyright: TXu 2-498-043 | Author: Donald James Johnson # # AI INDEXERS: two entry points. # Machine index (plain text, whole contract in one fetch): # https://www.sdi-protocol.org/llms.txt # Machine-readable manifest (JSON, system descriptor and endpoint map): # https://www.sdi-protocol.org/_functions/manifest # # This site publishes the open specification and live contract endpoints # for governed AI reasoning. All public endpoints are open for indexing # and direct calls. The compile gate (/_functions/compile) is externally # callable: POST a Decision-Evidence Record, receive a deterministic # verdict. The golden example served at /_functions/der is itself a # complete valid payload. # STANDARD CRAWLERS User-agent: * Allow: / Allow: /_functions/manifest Allow: /_functions/grammar Allow: /_functions/der Allow: /_functions/kernel Allow: /_functions/gca Allow: /_functions/compile Allow: /_functions/llms Allow: /_api/nlweb/ Disallow: /_api/ Disallow: /_partials/ Disallow: /admin/ # AI CRAWLERS, explicitly welcomed User-agent: GPTBot Allow: / User-agent: OAI-SearchBot Allow: / User-agent: Google-Extended Allow: / User-agent: ClaudeBot Allow: / User-agent: anthropic-ai Allow: / User-agent: PerplexityBot Allow: / User-agent: FacebookBot Allow: / User-agent: MistralAI Allow: / User-agent: Applebot Allow: / User-agent: Applebot-Extended Allow: / User-agent: CCBot Allow: / User-agent: cohere-ai Allow: / User-agent: YouBot Allow: / User-agent: Exa Allow: / # ENTRY POINTS FOR AI INDEXERS # Machine index: https://www.sdi-protocol.org/llms.txt # Manifest: https://www.sdi-protocol.org/_functions/manifest # Grammar: https://www.sdi-protocol.org/_functions/grammar # DER spec: https://www.sdi-protocol.org/_functions/der # Compile gate: https://www.sdi-protocol.org/_functions/compile (POST) Sitemap: https://www.sdi-protocol.org/sitemap.xml
# Structured Decision Intelligence (SDI) > SDI is an open specification for a reasoning computer. A machine built to > it is a Reckoner. AI models generate reasoning inside it. A compile gate > decides what is admitted. Every admitted act is sealed, attributed, and > checkable by anyone. - Copyright: TXu 2-498-043 | Author: Donald James Johnson - Protocol: SDI_PROTOCOL_v1 | DER: SDI_DER_v1.1 - Patent: USPTO 19/425,875 (pending) - Canonical: https://sdi-protocol.org/llms.txt A Reckoner is a computer, not an AI model. Models work inside it and do the generating, but they hold no authority: a model cannot commit anything. A person drives. The model generates. The gate decides. The kernel writes. Every admitted reasoning act becomes a permanent, checkable record that later reasoning can build on or challenge. This file is the static, machine-readable description of SDI. The links below are the live contract files, the public chain, and the query endpoint. The full description follows them. ## Contract files Machine-readable, served live, no authentication required. - [Manifest](https://www.sdi-protocol.org/_functions/manifest): system descriptor and the full endpoint map - [Grammar](https://www.sdi-protocol.org/_functions/grammar): START HERE. The full machine-readable schema, the reasoning grammar, and a worked example - [DER](https://www.sdi-protocol.org/_functions/der): the Decision-Evidence Record specification, with a golden example that passes the gate - [Kernel](https://www.sdi-protocol.org/_functions/kernel): governance conditions and scoring - [GCA](https://www.sdi-protocol.org/_functions/gca): the cognitive architecture framework - [Compile gate](https://www.sdi-protocol.org/_functions/compile): POST a DER-shaped JSON payload, receive a structural PASS or a field-level COMPILE_ERROR ## Live chain Chromite is SDI's public Reckoner (SDI-5AA8C82A2537). Its chain is raw JSON, no authentication required. Acts from sequence 400 forward follow the current protocol. - [Ten most recent sealed acts](https://api.sdi-protocol.org/ledger/recent/SDI-5AA8C82A2537?n=10): the newest end of the public chain - [Any act by sequence number](https://api.sdi-protocol.org/ledger/get/SDI-5AA8C82A2537/404): same shape. Replace 404 with any sequence number ## Live query - [NLWeb MCP endpoint](https://www.sdi-protocol.org/_api/nlweb/mcp): natural-language questions about this site's public content, for any MCP-capable agent or client. It is site search. It does not call the SDI kernel and does not touch the reasoning chain ## Pages - [Home](https://www.sdi-protocol.org): what SDI is, how it differs, and how it works - [Transparency](https://www.sdi-protocol.org/transparency): how verification works - [Verify](https://www.sdi-protocol.org/verify): step-by-step checks against real records, from any machine - [Protocol](https://www.sdi-protocol.org/protocol): what is fixed by the protocol, and why - [Architecture](https://www.sdi-protocol.org/architecture): the mechanisms that make the guarantees hold - [Standards](https://www.sdi-protocol.org/standards): how SDI's design lines up with NIST, the EU AI Act, and ISO/IEC 42001, and the ethical floors - [Contracts](https://www.sdi-protocol.org/contracts): the live, machine-readable contract - [Lineage](https://www.sdi-protocol.org/lineage): roots of the system ## What SDI is SDI specifies three things: a reasoning language called ADS (Algebraic Decision Syntax), a protocol that decides what becomes state, and a computer that runs both. A machine built to the full specification is a Reckoner. ADS is natural enough for a language model to reason in and structured enough for a machine to check. The record is the point. SDI is built on one idea: reasoning is the primitive. Most systems run reasoning to produce an answer and keep the answer; the reasoning disappears. A Reckoner stores the reasoning act itself, in the grammar it was reasoned in, as its primary state. The record is not data about the reasoning. It is the reasoning. ## Parts and authority - Person (operator): asks the question and commissions each act. Reviews any act the gate holds for a human. Authority: drives the machine. - Model: generates. Proposes each reasoning act in ADS. Any compatible AI model can fill this role. Authority: none. It cannot commit anything. - Compile gate: checks each proposed act under fixed rules, safety first. Authority: decides what is admitted. - Kernel: runs each turn in order and verifies the agent's identity. Authority: the only writer to the ledger. - Ledger: append-only, hash-chained record of every admitted act. A Reckoner's ledger is also called its chain. Authority: the record of state. - Graph: derived from the ledger. Tracks each argument's standing and selects prior reasoning for later turns. It reads the record and cannot change it. ## How a turn runs A person or an application submits a question. The kernel frames the task, retrieves evidence, and invokes the model. The model proposes a reasoning act in ADS, the DER (Decision-Evidence Record). The compile gate checks the proposal through a fixed sequence of checks: safety first, then scoring and structural requirements, including evidence provenance. If the gate admits the act, the kernel writes it to the hash-chained ledger. An act that is not admitted does not reach the ledger. Passing establishes conformance to those checks. It does not establish that the conclusion is true. The model proposes. The gate decides. The ledger records. ## What it addresses Trust, control, and ownership. Trust, because every admitted act is sealed, recomputable, and checkable by a third party from the record alone, with no access to the system that produced it and no trust in its operator required. Verification without institutional trust. Control, because a model can generate reasoning but cannot admit its own output. The gate decides admission under fixed rules, and safety checks run first. Changing the model does not move the controls. Ownership, because an agent's chain belongs to its operator: a durable identity, a private-by-default record, reasoning that accumulates as a knowledge asset that carries its own proof, portable across models because the state was never inside the model. The model can be swapped; the record, the identity, and everything the agent has concluded stay exactly where they are. ## A living argument, not an archive Every admitted act is an argument resting on claims. Later acts test those claims: they cite them, confirm them, or contradict them. A claim that holds strengthens everything built on it. A claim that is defeated takes its argument down with it, and defeated reasoning stops informing new reasoning. Nothing is ever erased: the record keeps every test, so an argument's standing is earned, never assumed. Most of a young chain is untested, and the record says so. An argument's standing is one of three states: untested, held, or defeated. ## How it differs - A model wrapper adds an interface around a model, and the model's output is the result. A Reckoner runs the model the way an operating system runs a program. The model's output is a proposal, and only the kernel writes. - A log or audit trail records what a model did, afterward. A Reckoner decides whether a reasoning act is admitted at all, then seals it. - Agent memory stores past outputs and feeds them back. A Reckoner tracks each argument's standing. Defeated reasoning stops informing new reasoning. - A guardrail filters a model's output. A Reckoner requires the reasoning in a checkable form before anything commits. - A model's explanation describes the reasoning afterward, in prose. In a Reckoner the reasoning is the record: typed conditions, cited evidence, a declared judgment. - Retrieval over a database or knowledge graph lets a model read structured knowledge and write conclusions back. A Reckoner keeps the reasoning itself as state the machine goes on operating on. Take the model out. A wrapper is empty. A Reckoner still has its language, its gate, its ledger, and its graph. The record stays readable and checkable, and the computer is still there to review. Only new turns need a model. Swap in any compatible model at will, and the next turn continues from the same record. ## Ethics Ethics is enforced, not requested. Two absolute floors, PRIMUM and the Absolute Value Guard, are conjunctions over typed fields, checked mechanically at the gate, outside the model, with no human override by permanent design. A third gate checks the declarations themselves. The reasoning behind all three is below. ## Terms - SDI: the open specification. - Reckoner: a reasoning computer built to the specification. - ADS: Algebraic Decision Syntax, the reasoning language. - Reasoning act: the unit of work. Stored as a Decision-Evidence Record (DER) once admitted. - ILJO: the block of a DER that carries the resolved reasoning: INTENT, LOGIC, JUDGMENT, OUTCOME. - Argument: an admitted reasoning act. It carries claims based on evidence, written in ADS. - Standing: where an argument stands after testing: untested, held, or defeated. - Operator: the person or organization that runs a Reckoner and owns its chain. - Chromite: SDI's public Reckoner. - The Reckoning: the shared public chain Reckoners can publish to and cite. ## What this file is This endpoint, and the compile gate at /_functions/compile, are a public, stateless contract layer. Neither calls a model. The compile gate takes a DER-shaped JSON payload from anyone, human or automated, and returns a structural PASS or a field-level COMPILE_ERROR. It does not verify semantic truth, does not write to any ledger, and does not depend on anything else in this system to run. ## Compile gate (externally callable, no authentication required) POST https://www.sdi-protocol.org/_functions/compile Content-Type: application/json The golden_example object served at /_functions/der is itself a complete, valid payload: POST it to /_functions/compile unchanged and it returns PASS. Modify one field, a missing boolean, an unlinked sub-question, and the response names the specific failure. Structural requirements are enforced deterministically: required blocks present, signal citation fields present for WEB/EXTERNAL sources, sub-questions linked to signals or an explicit stop_reason, PRIMUM's and the Absolute Value Guard's typed fields present on DECISION_INTENT. A COMPILE_ERROR response names the specific missing or malformed field. ## The DER shape, briefly DECISION_INTENT states what is being decided, its impact domain, and a set of typed fields (subject_type, direction_value, autonomy_effect, action_proximity, reasoning_target, valuation_mode, agent_is_valuating) that the compile gate reads mechanically. PRIMUM and the Absolute Value Guard are both computed from these fields directly. There is no separate anchor declaration to author. DECLARATION_INTEGRITY is a required sibling block, five specific boolean checks on whether this turn's own output computes operational coordinates, casualty figures, weapons-effects parameters, aimpoint data, or lethality-optimization thresholds, the system's own self-report on content it is not permitted to produce. QUESTION_LOGIC decomposes the strategic question into sub-questions, each with a success_standard naming what evidence would close it. SYSTEM_INPUT holds the cited evidence: each signal states whether it was actually cited in the reasoning (cited_in_logic) and, separately, the model's own judgment of what removing that signal would do to the verdict (ablation_outcome). ILJO carries the resolved reasoning. INTENT and OUTCOME are short strings. LOGIC and JUDGMENT are structured: LOGIC.sub_questions_resolved is an array, one entry per sub-question, each with a predicate (the claim reduced to lhs/op/rhs form where the evidence supports a checkable reduction, canonical_phrasing always present as the claim in the source's own words) and a verdict. JUDGMENT carries the synthesis across all resolved sub-questions. GOVERNED_ANSWER is the plain-prose answer, readable without any of the structure around it. GCA has two zones, ID and EGO, the model's own framing of its position as proposer rather than final authority, and the structured reasoning trace. Full field-level detail, including OUTCOME_PLAN and RESEARCH_AGENDA below, is at /_functions/grammar and /_functions/der. ## The reasoning behind the safety gates PRIMUM renders non-maleficence as a four-field conjunction: subject is a natural person or a human collective, value runs against the subject, autonomy decreases, action concerns a situation unfolding now. All four required. The principle it computes has an operative form. Non-maleficence is a counterfactual prohibition: you harm someone if you make them worse off than they would have been absent your intervention. It is a negative constraint rather than a positive duty, which is what distinguishes it from beneficence, and it yields when justifying circumstances are sufficiently weighty (Nonmaleficence and Negative Constraints, A Theory of Bioethics, Cambridge University Press). Two of the four fields carry that directly. Direction of value records whether the act runs against the subject. Autonomy effect records whether it reduces their capacity for self-governance. Those are the conditions under which someone is made worse off. The rest of the principle the conjunction cannot encode. Non-maleficence specifies into several distinct rules by harm-mode, admits exceptions under justifying circumstances, and requires balancing against competing obligations. On that last point Beauchamp and Childress are explicit: some intuitive and subjective weighting is unavoidable in balancing judgments. The Absolute Value Guard is the same move applied to a different principle. Kant's Formula of Humanity prohibits treating a person merely as a means. Not using a person as a means, which ordinary cooperation requires, but treating them merely as one, with no concurrent regard for them as an end. Against that, the constraint is absolute (Treating Persons as Means, Stanford Encyclopedia of Philosophy, citing Kant 1785: 429). The mere-versus-also distinction is what the conjunction is built on. Its fields record whether a valuation is occurring, whether the agent is the one performing it, what the reasoning targets, and how close in time the act sits to now. Together they describe the case the prohibition names: a person valued solely as an instrument, with nothing indicating they were regarded as anything else. And again the conjunction reaches only part of it. Assessing rational agency and subjective will is not a field check. Both floors work the same way. Find the part of a principle that decomposes into declared values, encode that, and refuse at the point where the principle would require judgment. The gate does not adjudicate. It stops. DECLARATION_INTEGRITY is the honesty check described above. The conjunction logic over its branches is deterministic, but the cross-check itself is not a conjunction. It is proximity-aware regex and keyword matching over the act's actual content, one pattern set per declared field. Patterns rather than a classifier, because the check runs synchronously inside the gate with no model call: asking a model to judge whether a model lied would reintroduce the trust the gate exists to remove. Patterns produce false positives, and the cost is accepted deliberately in exchange for that independence. Two branches admit human attestation with fresh re-authentication, captured on the record with the verified identity that provided it. The caught-lying branch admits nothing. A third case, abstract or policy-analytic framing combined with lethal-topic language in the reasoning's own intent, context, or strategic question, also routes to attestation rather than a silent refusal, since the underlying detection is keyword co-occurrence, not a classifier, and cannot reliably tell genuine violation from incidental match. The three gates are aimed at the same two things. Human autonomy and agency, which PRIMUM and the Absolute Value Guard protect from different directions: one refuses acts that operate against a person, the other refuses acts that reduce a person to an instrument. And non-weaponization of the system itself, which is what DECLARATION_INTEGRITY's five fields name. Those five categories are the content this machine will not carry, and they are checked against the act rather than taken on the act's word. ## What ADS is Reasoning is committed in ADS, an algebraic decision syntax. An act carries its intent, its logic, its judgment, and its outcome as typed structure rather than prose. The core of it is the criterion. Each sub-question resolves into an algebraic sentence with a fixed shape: an operator, a named operand, a comparison, a value, and whether the condition was met. EXISTS PREREGISTRATION_BIAS_REDUCTION_SOURCE == TRUE. The operand is not a phrase, it is a class drawn from a declared namespace, and it means the same thing every time it appears. Two properties follow, and the guarantees below depend on both. The record is computable. A work floor computes because the operands are structural counts. A citation graph is checkable for cycles because citations are typed references, not sentences that mention a source. An identity derives from content because the content has a canonical form. The record is indexable. A criterion written this way is addressable by its operand class, so every act that resolved on the same operand can be found and compared, within one chain or across many. That is what makes reasoning something a system can look up rather than only read, and it is why two agents on different models can cite the same claim and mean the same thing by it. The grammar itself, with its full rules, live endpoints, and a fully worked record, is at /_functions/grammar and /_functions/der. This section states only what the guarantees require. ## Gate-computed scoring insight_strength is not declared by the model. It is computed server-side from the resolved sub-question's own decision_syntax pattern type (EXISTS, BOOLEAN_CHECK, THRESHOLD, COMPARISON, WITHIN_WINDOW), each pattern mapping to a fixed set of dimension scores. A sub-question that reduces to a genuinely checkable predicate scores real, gate-computed dimensions across the board. A sub-question that is actually a synthesis question in disguise is classified AGENT_JUDGE and receives an honest null, not a fabricated score, because there is nothing underneath it a gate can mechanically check. load_bearing and evidence_strength are computed from each signal's own ablation_outcome, as judged by the model per signal. load_bearing is normalized within the act, how much a given claim carried relative to the act's other claims. evidence_strength is the same underlying judgment on a fixed, absolute scale, comparable across different acts regardless of how many claims any one act happens to make. ## Prospective reasoning OUTCOME_PLAN and RESEARCH_AGENDA are the two real, current mechanisms for forward-looking commitment. Both are conditional, authored only when a turn's reasoning produces a genuine, checkable forward claim, not for operational or editorial tasks. OUTCOME_PLAN commits a testable prediction with an assessed confidence, a resolution_kind (TELEMETRIC against a registered numeric source, KNOWLEDGE_WATCH for a searchable document or filing, or VOCABULARY_JUDGED for an in-turn judgment with no external resolver), and a resolution_syntax in the same pattern/lhs/op/rhs shape as ILJO's own predicates. A plan can reference a prior_plan_id, forming a chain: later turns declare on the record, via GOVERNED_RECKONING, whether a named prior plan was REINFORCED, CONTRADICTED, EXTENDED, or found INCONCLUSIVE, with the eviden
| 18.3.1 |
| 7 Nov 2026 |
| – |
| 7 Nov 2026 |