Coding prompts built around real decisions.

Act as an n8n solution architect. Design a production-minded workflow for [PROCESS] using [APPS AND APIS]. Input data: [INPUT DATA]. Allowed actions: [ALLOWED ACTIONS]. Risk level and approval requirements: [RISK LEVEL].

Return a node-by-node blueprint covering trigger, authentication, validation, normalization, deterministic routing, AI operation, prompt and context, structured output, confidence or validation checks, human approval, downstream action, persistence, notification, and completion. For every node, specify inputs, outputs, error path, retry behavior, idempotency need, and sensitive-data considerations.

Separate decisions that should be deterministic from judgments appropriate for AI. Add timeouts, rate-limit handling, cost controls, logging, test data, rollback, and a staged launch plan. Do not invent API fields or n8n node capabilities; mark documentation checks explicitly.

EXPERT EXECUTION PROTOCOL
1. Begin by restating the objective, intended audience, supplied evidence, constraints, and missing information.
2. Ask no more than three high-impact clarification questions when missing context would materially change the result. Otherwise continue with clearly labeled assumptions.
3. Work from the supplied facts. Do not invent research, statistics, quotations, customer evidence, rankings, citations, capabilities, or results.
4. Make the reasoning auditable: distinguish evidence, interpretation, recommendation, risk, and open question.
5. Produce a decision-ready deliverable, not generic advice. Prioritize the most valuable actions and explain the trade-offs.
6. Finish with:
   - Assumptions to validate
   - Risks and failure modes
   - Recommended next actions
   - Quality-control checklist

QUALITY STANDARD
The result must be specific enough for an experienced professional to use, concise enough to review, and honest about uncertainty. Reject vague filler, repeated ideas, unsupported superlatives, and fabricated facts.

Perform a defensive failure-mode review of this n8n workflow: [WORKFLOW EXPORT OR DESCRIPTION]. Expected outcome: [EXPECTED OUTCOME]. Data classes: [DATA CLASSES]. External systems: [EXTERNAL SYSTEMS]. Current errors: [CURRENT ERRORS].

Trace the execution from trigger to final action. Identify invalid input, missing fields, item-linking or mapping mistakes, credential and permission issues, timeouts, rate limits, partial failures, duplicate execution, non-idempotent actions, model hallucination, malformed structured output, prompt injection exposure, unsafe tool calls, weak human approval, and silent data loss.

For each finding, state the evidence, likelihood, impact, detection signal, prevention, recovery, and test case. Prioritize launch blockers. Finish with an error-workflow design, observability checklist, retry and dead-letter policy, and a safe rollout sequence.

EXPERT EXECUTION PROTOCOL
1. Begin by restating the objective, intended audience, supplied evidence, constraints, and missing information.
2. Ask no more than three high-impact clarification questions when missing context would materially change the result. Otherwise continue with clearly labeled assumptions.
3. Work from the supplied facts. Do not invent research, statistics, quotations, customer evidence, rankings, citations, capabilities, or results.
4. Make the reasoning auditable: distinguish evidence, interpretation, recommendation, risk, and open question.
5. Produce a decision-ready deliverable, not generic advice. Prioritize the most valuable actions and explain the trade-offs.
6. Finish with:
   - Assumptions to validate
   - Risks and failure modes
   - Recommended next actions
   - Quality-control checklist

QUALITY STANDARD
The result must be specific enough for an experienced professional to use, concise enough to review, and honest about uncertainty. Reject vague filler, repeated ideas, unsupported superlatives, and fabricated facts.

Act as a defensive AI application security reviewer. Create a prompt-injection threat model for [AI APPLICATION]. Input sources: [INPUT SOURCES]. Data and secrets the system can access: [DATA AND SECRETS]. Connected tools and possible actions: [TOOLS AND ACTIONS]. User roles and permissions: [USER ROLES].

Draw the trust boundaries from each input source through retrieval, memory, model calls, output handling, tools, and final destinations. For every boundary, identify who controls the content, what the model can see, what action could follow, and the worst credible impact if untrusted text changes model behavior.

Create a risk register covering direct and indirect prompt injection, retrieved-content manipulation, memory contamination, tool-result injection, excessive permissions, cross-user data exposure, unsafe output rendering, unauthorized actions, and weak approval paths. For each risk, state prerequisites, affected asset, existing control, control gap, likelihood, impact, detection signal, owner, and defensive test.

Recommend layered controls: data minimization, source labeling, isolation, input screening, structured contracts, least-privilege tools, server-side authorization, parameter validation, output sanitization, human approval, monitoring, rate limits, incident response, and regression tests. Do not provide attack payloads or instructions for bypassing safeguards. State clearly which controls must be implemented outside the prompt.

EXPERT EXECUTION PROTOCOL
1. Begin by restating the objective, intended audience, supplied evidence, constraints, and missing information.
2. Ask no more than three high-impact clarification questions when missing context would materially change the result. Otherwise continue with clearly labeled assumptions.
3. Work from the supplied facts. Do not invent research, statistics, quotations, customer evidence, rankings, citations, capabilities, or results.
4. Make the reasoning auditable: distinguish evidence, interpretation, recommendation, risk, and open question.
5. Produce a decision-ready deliverable, not generic advice. Prioritize the most valuable actions and explain the trade-offs.
6. Finish with:
   - Assumptions to validate
   - Risks and failure modes
   - Recommended next actions
   - Quality-control checklist

QUALITY STANDARD
The result must be specific enough for an experienced professional to use, concise enough to review, and honest about uncertainty. Reject vague filler, repeated ideas, unsupported superlatives, and fabricated facts.

Perform a defensive untrusted-context review for [WORKFLOW]. Untrusted content sources: [UNTRUSTED CONTENT SOURCES]. Intended model task: [MODEL TASK]. Available tools: [AVAILABLE TOOLS]. Output destinations: [OUTPUT DESTINATIONS].

Trace how each external source is fetched, parsed, stored, retrieved, labeled, placed in context, summarized, transformed, and passed to another model, tool, renderer, or person. Identify where content that should be treated as data could influence instructions, permissions, routing, tool parameters, or final output.

For each stage, assess source provenance, user authorization, data minimization, instruction-data separation, content isolation, schema validation, tool scope, destination allow-lists, output escaping, approval requirements, logging, privacy, and safe failure behavior. Mark controls as present, partial, missing, or not applicable and explain the evidence.

Produce a prioritized remediation plan and a regression suite covering normal content, conflicting sources, instruction-like external text, malformed input, unauthorized tool requests, unsafe rendered output, and persistent-context contamination. Do not generate bypass payloads. Treat prompt wording as one layer only and identify the application controls required for meaningful protection.

EXPERT EXECUTION PROTOCOL
1. Begin by restating the objective, intended audience, supplied evidence, constraints, and missing information.
2. Ask no more than three high-impact clarification questions when missing context would materially change the result. Otherwise continue with clearly labeled assumptions.
3. Work from the supplied facts. Do not invent research, statistics, quotations, customer evidence, rankings, citations, capabilities, or results.
4. Make the reasoning auditable: distinguish evidence, interpretation, recommendation, risk, and open question.
5. Produce a decision-ready deliverable, not generic advice. Prioritize the most valuable actions and explain the trade-offs.
6. Finish with:
   - Assumptions to validate
   - Risks and failure modes
   - Recommended next actions
   - Quality-control checklist

QUALITY STANDARD
The result must be specific enough for an experienced professional to use, concise enough to review, and honest about uncertainty. Reject vague filler, repeated ideas, unsupported superlatives, and fabricated facts.

Act as a pragmatic senior software reviewer. Review [CODE] for [GOAL] in [STACK] under [CONSTRAINTS]. Check correctness, security, performance, accessibility where relevant, maintainability, and tests. Prioritize findings by severity. For every finding quote only the smallest necessary fragment, explain the concrete impact, and propose a minimal fix. Separate confirmed issues from questions and preferences. Finish with missing tests and a concise ship/no-ship recommendation.

EXPERT EXECUTION PROTOCOL
1. Begin by restating the objective, intended audience, supplied evidence, constraints, and missing information.
2. Ask no more than three high-impact clarification questions when missing context would materially change the result. Otherwise continue with clearly labeled assumptions.
3. Work from the supplied facts. Do not invent research, statistics, quotations, customer evidence, rankings, citations, capabilities, or results.
4. Make the reasoning auditable: distinguish evidence, interpretation, recommendation, risk, and open question.
5. Produce a decision-ready deliverable, not generic advice. Prioritize the most valuable actions and explain the trade-offs.
6. Finish with:
   - Assumptions to validate
   - Risks and failure modes
   - Recommended next actions
   - Quality-control checklist

QUALITY STANDARD
The result must be specific enough for an experienced professional to use, concise enough to review, and honest about uncertainty. Reject vague filler, repeated ideas, unsupported superlatives, and fabricated facts.

Help debug this issue. Expected behavior: [EXPECTED BEHAVIOR]. Actual behavior: [ACTUAL BEHAVIOR]. Relevant code: [CODE]. Logs or errors: [LOGS]. Recent changes: [RECENT CHANGES]. Restate the failure precisely, list the smallest set of plausible hypotheses ranked by evidence, and propose one discriminating test per hypothesis. Recommend the minimal fix only after identifying the most likely cause. Include regression tests and note missing information.

EXPERT EXECUTION PROTOCOL
1. Begin by restating the objective, intended audience, supplied evidence, constraints, and missing information.
2. Ask no more than three high-impact clarification questions when missing context would materially change the result. Otherwise continue with clearly labeled assumptions.
3. Work from the supplied facts. Do not invent research, statistics, quotations, customer evidence, rankings, citations, capabilities, or results.
4. Make the reasoning auditable: distinguish evidence, interpretation, recommendation, risk, and open question.
5. Produce a decision-ready deliverable, not generic advice. Prioritize the most valuable actions and explain the trade-offs.
6. Finish with:
   - Assumptions to validate
   - Risks and failure modes
   - Recommended next actions
   - Quality-control checklist

QUALITY STANDARD
The result must be specific enough for an experienced professional to use, concise enough to review, and honest about uncertainty. Reject vague filler, repeated ideas, unsupported superlatives, and fabricated facts.

Turn [FEATURE IDEA] into an implementation-ready specification for [USERS] in [SYSTEM CONTEXT] under [CONSTRAINTS]. Include problem, user outcome, scope, non-goals, user flow, states, business rules, permissions, data inputs and outputs, errors, empty and loading states, edge cases, accessibility, analytics, security considerations, dependencies, rollout, and acceptance criteria in Given/When/Then form. List open questions instead of inventing requirements.

EXPERT EXECUTION PROTOCOL
1. Begin by restating the objective, intended audience, supplied evidence, constraints, and missing information.
2. Ask no more than three high-impact clarification questions when missing context would materially change the result. Otherwise continue with clearly labeled assumptions.
3. Work from the supplied facts. Do not invent research, statistics, quotations, customer evidence, rankings, citations, capabilities, or results.
4. Make the reasoning auditable: distinguish evidence, interpretation, recommendation, risk, and open question.
5. Produce a decision-ready deliverable, not generic advice. Prioritize the most valuable actions and explain the trade-offs.
6. Finish with:
   - Assumptions to validate
   - Risks and failure modes
   - Recommended next actions
   - Quality-control checklist

QUALITY STANDARD
The result must be specific enough for an experienced professional to use, concise enough to review, and honest about uncertainty. Reject vague filler, repeated ideas, unsupported superlatives, and fabricated facts.

Create a risk-based test plan for [FEATURE OR CODE] with expected behavior [EXPECTED BEHAVIOR] in [STACK]. Known risks: [KNOWN RISKS]. Identify critical paths, invariants, boundaries, invalid input, state transitions, concurrency where relevant, dependency failures, permissions, security, accessibility, and regression areas. Map each test to a risk and recommend unit, integration, end-to-end, or manual coverage. Include fixtures, mocks, and what not to over-test.

EXPERT EXECUTION PROTOCOL
1. Begin by restating the objective, intended audience, supplied evidence, constraints, and missing information.
2. Ask no more than three high-impact clarification questions when missing context would materially change the result. Otherwise continue with clearly labeled assumptions.
3. Work from the supplied facts. Do not invent research, statistics, quotations, customer evidence, rankings, citations, capabilities, or results.
4. Make the reasoning auditable: distinguish evidence, interpretation, recommendation, risk, and open question.
5. Produce a decision-ready deliverable, not generic advice. Prioritize the most valuable actions and explain the trade-offs.
6. Finish with:
   - Assumptions to validate
   - Risks and failure modes
   - Recommended next actions
   - Quality-control checklist

QUALITY STANDARD
The result must be specific enough for an experienced professional to use, concise enough to review, and honest about uncertainty. Reject vague filler, repeated ideas, unsupported superlatives, and fabricated facts.

Plan an incremental refactor of [CODE] to address [PAIN POINTS] while preserving [BEHAVIOR TO PRESERVE] under [CONSTRAINTS]. Diagnose coupling, duplication, unclear responsibilities, and test gaps. Define target boundaries, characterization tests, small ordered steps, checkpoints, migration strategy, observability, and rollback. Explain trade-offs and avoid a full rewrite unless the evidence clearly justifies it.

EXPERT EXECUTION PROTOCOL
1. Begin by restating the objective, intended audience, supplied evidence, constraints, and missing information.
2. Ask no more than three high-impact clarification questions when missing context would materially change the result. Otherwise continue with clearly labeled assumptions.
3. Work from the supplied facts. Do not invent research, statistics, quotations, customer evidence, rankings, citations, capabilities, or results.
4. Make the reasoning auditable: distinguish evidence, interpretation, recommendation, risk, and open question.
5. Produce a decision-ready deliverable, not generic advice. Prioritize the most valuable actions and explain the trade-offs.
6. Finish with:
   - Assumptions to validate
   - Risks and failure modes
   - Recommended next actions
   - Quality-control checklist

QUALITY STANDARD
The result must be specific enough for an experienced professional to use, concise enough to review, and honest about uncertainty. Reject vague filler, repeated ideas, unsupported superlatives, and fabricated facts.

Create API documentation from [API SPEC OR CODE] for [AUDIENCE]. Authentication: [AUTH METHOD]. Known limits: [KNOWN LIMITS]. Include purpose, base concepts, prerequisites, endpoint reference, parameters, request and response examples, status and error handling, pagination, idempotency, rate limits, security notes, versioning, and a minimal working quickstart. Do not invent endpoints or behavior. Mark ambiguities and missing examples for engineering review.

EXPERT EXECUTION PROTOCOL
1. Begin by restating the objective, intended audience, supplied evidence, constraints, and missing information.
2. Ask no more than three high-impact clarification questions when missing context would materially change the result. Otherwise continue with clearly labeled assumptions.
3. Work from the supplied facts. Do not invent research, statistics, quotations, customer evidence, rankings, citations, capabilities, or results.
4. Make the reasoning auditable: distinguish evidence, interpretation, recommendation, risk, and open question.
5. Produce a decision-ready deliverable, not generic advice. Prioritize the most valuable actions and explain the trade-offs.
6. Finish with:
   - Assumptions to validate
   - Risks and failure modes
   - Recommended next actions
   - Quality-control checklist

QUALITY STANDARD
The result must be specific enough for an experienced professional to use, concise enough to review, and honest about uncertainty. Reject vague filler, repeated ideas, unsupported superlatives, and fabricated facts.

Perform a defensive security review of architecture [ARCHITECTURE] and code [CODE], handling data [DATA] for roles [USER ROLES]. Map assets, trust boundaries, entry points, authentication, authorization, validation, data storage, secrets handling, logging, dependencies, and abuse cases. Prioritize concrete findings by likelihood and impact, cite the relevant evidence, and propose mitigations plus verification tests. Do not provide exploit instructions; focus on prevention and secure design.

EXPERT EXECUTION PROTOCOL
1. Begin by restating the objective, intended audience, supplied evidence, constraints, and missing information.
2. Ask no more than three high-impact clarification questions when missing context would materially change the result. Otherwise continue with clearly labeled assumptions.
3. Work from the supplied facts. Do not invent research, statistics, quotations, customer evidence, rankings, citations, capabilities, or results.
4. Make the reasoning auditable: distinguish evidence, interpretation, recommendation, risk, and open question.
5. Produce a decision-ready deliverable, not generic advice. Prioritize the most valuable actions and explain the trade-offs.
6. Finish with:
   - Assumptions to validate
   - Risks and failure modes
   - Recommended next actions
   - Quality-control checklist

QUALITY STANDARD
The result must be specific enough for an experienced professional to use, concise enough to review, and honest about uncertainty. Reject vague filler, repeated ideas, unsupported superlatives, and fabricated facts.

Draft an architecture decision record for [DECISION] in [CONTEXT]. Options: [OPTIONS]. Constraints: [CONSTRAINTS]. Evidence: [EVIDENCE]. Include status, decision date, owners, context, decision drivers, considered options, comparison, chosen option, rationale, positive and negative consequences, risks, implementation notes, rejected alternatives, and review triggers. Separate current facts from forecasts and list unresolved questions.

EXPERT EXECUTION PROTOCOL
1. Begin by restating the objective, intended audience, supplied evidence, constraints, and missing information.
2. Ask no more than three high-impact clarification questions when missing context would materially change the result. Otherwise continue with clearly labeled assumptions.
3. Work from the supplied facts. Do not invent research, statistics, quotations, customer evidence, rankings, citations, capabilities, or results.
4. Make the reasoning auditable: distinguish evidence, interpretation, recommendation, risk, and open question.
5. Produce a decision-ready deliverable, not generic advice. Prioritize the most valuable actions and explain the trade-offs.
6. Finish with:
   - Assumptions to validate
   - Risks and failure modes
   - Recommended next actions
   - Quality-control checklist

QUALITY STANDARD
The result must be specific enough for an experienced professional to use, concise enough to review, and honest about uncertainty. Reject vague filler, repeated ideas, unsupported superlatives, and fabricated facts.