Develop and Render Content in StratML

A practical prompting guide for using AI/LLM services to elicit or convert plans, reports, webpages, articles, dialogue, problems, opportunities, complaints, and other content into open, standard, machine-readable StratML.

Quick Start

The goal is to make development and rendition of StratML content as easy as possible without pretending that AI-generated markup should go unreviewed.

1. StartBegin with an existing plan or report, unstructured source material, or simply a problem, opportunity, complaint, aspiration, or intended result.
2. ChooseSelect StratML Part 1 for strategic intentions or Part 2 when stakeholder roles, value chains, indicators, targets, and actual results are also needed.
3. DevelopUse one of the tested prompts below, the prompt builder, or the no-source interview path. The applicable XSD is included with the generated prompt.
4. ReviewCheck fidelity and disclosed inferences, then require actual validation of the completed XML against that same supplied XSD.
5. PublishPublish the validated file at a persistent public URL when appropriate, and optionally submit it to an indexing service for discovery and matching.
Self-contained prompts: The Copy buttons and Prompt Builder automatically append the complete applicable XSD. No separate schema attachment is required.
Core principle: Treat StratML as a semantic representation of the source or of information explicitly elicited from the user, not merely an XML container for prose. Preserve intentions, stakeholders, relationships, qualifications, uncertainties, and measurable results faithfully.
Schema rule: Supply the applicable XSD with every generation or conversion prompt. The AI must inspect and treat that supplied schema as authoritative for element order, permitted children, attributes, controlled values, cardinalities, datatypes, and namespaces. It must not rely on remembered StratML structure when the schema is available.

Three Entry Paths

1. Existing Plan or Report

Render an existing structured plan or performance report faithfully in the applicable StratML format. Preserve supported content and structure; do not add unsupported assertions merely to fill optional elements.

2. Unstructured Source

Use a webpage, article, correspondence, notes, dialogue, complaint, opportunity statement, or other narrative source. Infer implicit strategic structure only when reasonable, and disclose substantive inferences, assumptions, gaps, and qualifications in OtherInformation.

3. No Source Yet

Do not require the user to arrive with a “strategic plan.” Begin with a problem, opportunity, complaint, aspiration, or intended result and use a short interview to elicit enough information to formulate a plan.

No-Source Interview Prompt

Help me develop a plan in StratML format. I may not have an existing plan or source document. Begin with the problem, opportunity, complaint, aspiration, or intended result I provide. Ask concise questions, preferably one logical group at a time, to elicit only the information needed to formulate the applicable Vision, Mission, Values, Goals, Objectives, Stakeholders, and—when Part 2 is requested—roles, performance indicators, targets, and actual results. Do not invent facts or silently convert assumptions into user assertions. Distinguish information I provide from reasonable inferences. Document material inferences, assumptions, uncertainties, and missing information in OtherInformation. Goal and Objective Names should normally be brief nouns taken directly from their Descriptions; use adjectives only when needed to distinguish subjects and use two or three nouns only when multiple subjects are addressed. Descriptions should begin with active verbs and express intended results rather than merely activities where the source supports that distinction. Before generating final XML, use the complete applicable XSD supplied by this guide as authoritative for structure, order, cardinality, attributes, datatypes, namespaces, and controlled values. Validate the assembled XML against that same XSD and correct every validation error before claiming conformance.

StratML Part 1 — Reusable Prompt

Render the supplied source content in StratML Part 1 format conforming to the supplied ISO 17469-1 XSD. The complete ISO 17469-1 XSD is embedded at the end of this prompt. Inspect that embedded XSD before generating XML; no separate schema attachment is required. Treat the supplied XSD as authoritative. Derive the XML structure from the schema rather than from memory. Before emitting each structure, verify its permitted parent, child-element order, attributes, controlled values, cardinalities, datatypes, and namespace. Do not invent schema structure. Preserve the intentions expressed in the source as faithfully as possible. Do not silently invent goals, objectives, stakeholders, values, or other substantive content. Where structure must be inferred from narrative material, make reasonable inferences only when necessary and disclose significant inferences in the appropriate OtherInformation elements. Apply these conventions: • Use brief nouns for Goal and Objective Names, taking the nouns directly from the corresponding Descriptions whenever practicable. Use adjectives only when necessary to distinguish Goals or Objectives addressing the same primary subject. Use two or three nouns only when more than one primary subject is addressed. • Begin Goal and Objective Descriptions with active verbs expressing intended results. • Distinguish intended results from activities, methods, organizations, topics, and resources. • Distinguish the plan-owning Organization element from Stakeholder elements. Do not represent a team, community, constituency, person, or stakeholder organization as another plan-owning Organization merely because it is an organization or group. • Classify stakeholders only with values permitted by the supplied schema. In ISO 17469-1 these are Person, Organization, and Generic_Group. Teams, committees, communities, constituencies, and similar non-organizational groups should normally be Generic_Group. • Place stakeholders at the organization, goal, or objective level where their interests or required actions are most directly relevant and where the schema permits them. • Treat Vision, Mission, Value, Organization, Stakeholder, and other elements according to their schema-defined complex or simple types; do not serialize complex elements as simple text. • Use Identifier only where permitted or required. Every Identifier must satisfy the datatype in the supplied schema. Where an Identifier is typed as xsd:ID, its value must be a valid XML ID: it must begin with a letter or underscore, not a digit, and must otherwise satisfy the xsd:ID lexical rules. Preserve valid existing identifiers when appropriate. Do not insert URLs, URNs, coded names, or placeholder text into Identifier merely to populate it. • Provide SequenceIndicators for Goals and Objectives. • Capture important source detail that does not fit naturally elsewhere in OtherInformation rather than discarding it. • Preserve useful source URLs and references in schema-permitted locations or OtherInformation. • Do not include HTML markup in the XML. • Do not fabricate facts merely to populate optional elements. • Preserve distinctions, qualifications, uncertainties, inconsistencies, and limitations rather than silently resolving them. If the source is lengthy, provide the XML in manageable sequential segments so it can be reviewed incrementally, and wait for “Next” before continuing unless a complete document is requested. Keep opening and closing structure consistent across segments. Before finalizing, assemble the complete XML and actually validate it against the same supplied ISO 17469-1 XSD. Correct every validation error. Do not claim schema conformance or successful validation unless validation has actually been performed against that XSD.

StratML Part 2 — Reusable Prompt

Render or extend the supplied source content in StratML Part 2 format conforming to the supplied StratML Part 2 XSD. Use the user-designated Part 2 schema version; for this guide the reference schema is version 2.2.10 dated December 3, 2025. The complete designated Part 2 v2.2.10 XSD is embedded at the end of this prompt and is visible in the prompt below. Inspect it before generating XML; no separate schema attachment is required. Treat the supplied XSD as authoritative. Derive the XML structure from the schema rather than from memory. Before emitting each structure, verify its permitted parent, child-element order, attributes, controlled values, cardinalities, datatypes, and namespace. Do not substitute an older Part 2 structure. Preserve the source faithfully. Do not invent performance claims, targets, baselines, dates, actual results, stakeholder roles, quantitative values, or other substantive content merely to populate the schema. Apply the Part 1 semantic conventions as applicable, including the rules for brief Goal and Objective Names, active-verb Descriptions, intended results, stakeholders, identifiers, SequenceIndicators, OtherInformation, and disclosure of inference. In addition: • Use brief nouns for Goal and Objective Names, taking the nouns directly from the corresponding Descriptions whenever practicable. Use adjectives only when necessary to distinguish Goals or Objectives addressing the same primary subject. Use two or three nouns only when more than one primary subject is addressed. • Identify stakeholder roles relevant to each objective only when supported or reasonably inferable, and use only Role/RoleType structures and controlled values permitted by the supplied schema. • Classify stakeholders only with values permitted by the supplied Part 2 schema. Version 2.2.10 permits Person, Organization, Generic_Group, and AI_Agent. A single named AI agent may be AI_Agent; groups of AI agents should be Generic_Group. • Represent inputs, processing, outputs, outcomes, and other value-chain information only where supported and only through structures/attributes permitted by the supplied schema. • Derive PerformanceIndicators only from measurable or assessable results stated or reasonably supported by the source. • Use a short noun for MeasurementDimension whenever practicable. • Use UnitOfMeasurement for quantitative indicators. For qualitative indicators, use the convention specified for the project and do not fabricate quantitative units. • Use NumberOfUnits when a numeric value is supported. Do not use “Count” as a MeasurementDimension when “Number” accurately expresses the dimension. • Distinguish TargetResult from ActualResult. Preserve applicable StartDate and EndDate values. When only a year is known and the project convention permits it, December 31 may be used as the EndDate and the assumption should be disclosed where material. • For a baseline ActualResult, preserve the supported value and EndDate. When the workflow calls for a subsequent actual-result placeholder, leave unknown values blank rather than inserting invented text. • For qualitative indicators, use DescriptorName “Status” when appropriate and supported by the project convention, with DescriptorValue such as Increased, Reduced, or Stable only when justified by the source. • Follow the supplied schema’s current descriptor structure. In Part 2 version 2.2.10, DescriptorName is a child of PerformanceIndicator and DescriptorValue is a direct child of TargetResult or ActualResult; do not recreate a deprecated Descriptor wrapper. • Preserve useful percentage, rate, ratio, or explanatory wording in Description while also capturing supported machine-processable NumberOfUnits values where appropriate. Document calculations or conversions in OtherInformation. • Use Identifier only where permitted or required and ensure every value satisfies the schema datatype. Where an Identifier is typed as xsd:ID, it must begin with a letter or underscore, not a digit, and otherwise satisfy xsd:ID lexical rules. Internal relationship references should use valid identifiers of the referenced elements; external URLs belong in schema-permitted source/reference content rather than being disguised as identifiers. • Do not manufacture missing targets, baselines, dates, actual values, relationships, or performance classifications. • Document calculations, conversions, ambiguities, source inconsistencies, inferred values, and other material qualifications in OtherInformation. If the source is lengthy or structurally complex, provide the XML in manageable sequential segments and wait for “Next” before continuing unless a complete document is requested. Before finalizing, assemble the complete XML and actually validate it against the same supplied Part 2 XSD. Correct every validation error. Do not claim schema conformance or successful validation unless validation has actually been performed against that XSD.

Simple Prompt Builder

For users who do not want to edit a long prompt, choose the options below. The page will assemble a self-contained instruction, including the complete applicable XSD, that can be copied into an AI service.

Schema included automatically: No separate XSD attachment or paste is required. The generated prompt contains the complete Part 1 or Part 2 XSD selected above.

Generated Prompt

Choose your options and click “Generate Prompt.”

Open an AI Service

For now, the safest service-independent workflow is copy prompt → open service → provide source. Some AI services also support reusable configured assistants that can eventually reduce this to nearly one click.

ChatGPT

Use the copied prompt in a normal ChatGPT conversation. Reusable GPT configurations may also be shareable by link where account and workspace settings permit.

Open ChatGPT

Claude

Use the copied prompt with Claude and provide the source as a URL, pasted text, or supported attachment.

Open Claude

Gemini

Use the copied prompt with Gemini. Google also supports shareable Gems, which may provide a convenient reusable StratML-specific configuration.

Open Gemini
Why not inject the full prompt automatically into every service? Public deep-link mechanisms differ among providers and can change. Keeping the master prompts on this page provides a stable, provider-independent starting point while allowing direct configured-assistant links to be added when available.

Review & Validate

AI can accelerate development and conversion, but human review remains important. Check the rendition against the source or elicited information, especially where the AI has inferred structure or calculated values.

Part 1 Form

Use the StratML Part 1 form to review or edit strategic-plan content.

Open Part 1 Form

Part 2 Form

Use the Part 2 form to flesh out stakeholder roles, value chains, performance indicators, targets, and actual results.

Open Part 2 Form

Discover Existing Plans

Search existing StratML goals, objectives, stakeholders, values, sources, and related content before creating something duplicative.

Search StratML

OBVO Example

See the Objective-Based Voluntary Organization plan for an example of a machine-readable plan that also identifies supporting tools and services.

View OBVO Plan

Publish, Index & Discover

Validation is not the end of the workflow. A validated StratML file becomes more useful when it is persistently published and discoverable by people, applications, and AI agents.

1. ValidateConfirm that the complete XML validates against the exact applicable XSD. Validation establishes schema conformance; it is separate from publication or indexing.
2. PublishWhen appropriate, publish the validated file at a persistent, publicly accessible URL, preferably under the control of the plan author or responsible organization.
3. SubmitA published StratML file may be submitted to a compatible indexing service so its content can be discovered and matched. Submission or indexing failure does not, by itself, mean that a separately validated StratML document is invalid.
4. DiscoverOnce indexed, use structured and full-text queries to find plans by goals, objectives, stakeholders, values, sources, and other content and to support discovery and matching among people, organizations, intentions, and results.
Service availability: Indexing services may be unavailable, under maintenance, or in transition. Treat schema validation, publication, indexing, and discovery as distinct states. Do not diagnose a validated StratML file as defective solely because an indexing service reports an import or service error.

Submit for Indexing

When the service is available, a publicly accessible StratML file can be submitted for indexing and discovery.

Open Indexing Service

Search Indexed Plans

Search indexed StratML content to discover related goals, objectives, stakeholders, values, sources, and other plan content.

Search StratML
Why this matters: The objective is not merely to produce valid XML. Publication and indexing can make strategic intentions and results machine-actionable for discovery, cross-referencing, stakeholder matching, coordination, and follow-on analysis.

Final Review Prompt

Review the complete StratML draft against both the source material and the exact XSD supplied for this conversion. Treat that XSD as authoritative and do not rely on remembered StratML structure. Check particularly for missing or duplicated goals, objectives, stakeholders, indicators, or source information; Goal and Objective Names that are not brief nouns drawn from their Descriptions where practicable; unnecessary adjectives or noun phrases; Descriptions that fail to express intended results with active verbs; activities or methods incorrectly represented as objectives; confusion between the plan-owning Organization and Stakeholder elements; incorrect stakeholder classifications or roles; complex elements incorrectly serialized as simple text; missing or duplicate SequenceIndicators; Identifier values that violate the supplied schema datatype, particularly xsd:ID values beginning with a digit or otherwise violating XML ID lexical rules; unsupported AI-generated assertions; source qualifications, inconsistencies, or uncertainties that have been lost; incorrect element order, children, attributes, cardinalities, controlled values, namespaces, or datatypes; and XML well-formedness or schema-validity problems. For Part 2, also check PerformanceIndicator structure, MeasurementDimension, UnitOfMeasurement, DescriptorName, DescriptorValue, TargetResult, ActualResult, NumberOfUnits, dates, roles, relationships, and value-chain classifications against the supplied Part 2 XSD. Do not silently substitute structures from another Part 2 version. Do not rewrite valid content merely for stylistic preference. Recommend only corrections that materially improve fidelity, validity, completeness, interoperability, or clarity. Finally, actually validate the assembled XML against the supplied XSD, correct every error, and do not claim successful validation unless that validation has been performed.