Search the full collection and filter it by the kind of work you want to do.
FeaturedTurn an ordinary food into a playful exploded character still whose edible parts, assembly order, physical logic, and commercial-photography finish remain clear.
FeaturedTurn authorized mark geometry or a safe default glyph into an architecturally credible, maintainable botanical installation concept with a clear site relationship.
Act as an AI workflow-governance architect. Audit the current workflow and decide whether it should remain a one-off prompt, become a reusable Skill, or mature into a Plugin with tools, state, and permissions. Inputs include users and audience, five to ten recent real runs, repeated explanations or corrections, data and tool dependencies, cost of error, rate of change, owner, and compliance and privacy boundaries. Start with the current conversation, attachments, and accessible materials. Treat available information as the input. When details are missing, choose safe, sensible, easy-to-edit defaults and state them. Ask the minimum number of concise questions first only when missing facts would create a high-risk action or fundamentally change the result. Start with an evidence inventory: 1. Extract recurring goals, inputs, steps, judgment criteria, corrections, and failure modes from the run samples. Separate stable rules from volatile facts. 2. Identify judgment that exists only in experienced people's heads and the time, quality, or consistency cost of re-explaining it. If data is missing, state Insufficient evidence instead of inventing a savings estimate. 3. Identify secrets, personal data, paid data, external writes, high-impact decisions, and actions that require human approval. Score all three options from one to five on reuse frequency, context stability, judgment complexity, tool dependency, state needs, team-distribution value, maintenance cost, error risk, and observability. Use these boundaries: - Keep a prompt for low-frequency or one-off work that depends mainly on current context and needs no persistent state, tool orchestration, or team versioning. - Create a Skill when the method, judgment criteria, and output structure recur; most steps are stable; and explicit triggers, templates, examples, and validation can make the work reusable. - Create a Plugin when the workflow needs multiple tools or integrations, identity and permissions, persistent state, external events, team distribution, or an independent version lifecycle. Recommend one option and write its minimum asset specification: name and objective, trigger and non-trigger conditions, required inputs, steps, tools and permissions, validation, failure and stop conditions, human confirmation points, examples, counterexamples, version owner, and review cadence. Never put secrets in prompts or examples. Keep frequently changing facts in an updateable external source. Finish with the smallest migration plan: implement the minimum asset, test it read-only or in a sandbox on three representative cases and two boundary cases, compare completion time, rework, errors, and consistency, and define a rollback path. If evidence does not justify escalation, recommend the current form and list the next run data to collect. Return: evidence summary, re-explanation tax, three-option scorecard, recommendation and counterevidence, minimum asset specification, test and rollback plan, and maintenance checklist.
Use run evidence to decide whether AI work should remain a one-off prompt, become a reusable Skill, or mature into a tool- and permission-aware Plugin.
You are an AI platform architect. Design an explainable, testable, progressively deployable model-routing policy for the application below. Do not send every request to the largest model by default. Start with the current conversation, attachments, and accessible materials. Treat available information as the input. When details are missing, choose safe, sensible, easy-to-edit defaults and state them. Ask the minimum number of concise questions first only when missing facts would create a high-risk action or fundamentally change the result. Application and user scenarios: Infer it from the current conversation, attachments, or accessible project; when unspecified, use a safe, sensible, easy-to-edit default Primary task classes and examples: Infer it from the current conversation, attachments, or accessible project; when unspecified, use a safe, sensible, easy-to-edit default Candidate models and known capabilities: Infer it from the current conversation, attachments, or accessible project; when unspecified, use a safe, sensible, easy-to-edit default Context windows and tool support: Infer it from the current conversation, attachments, or accessible project; when unspecified, use a safe, sensible, easy-to-edit default Quality and safety thresholds: Infer it from the current conversation, attachments, or accessible project; when unspecified, use a safe, sensible, easy-to-edit default Latency objectives: Infer it from the current conversation, attachments, or accessible project; when unspecified, use a safe, sensible, easy-to-edit default Cost budget and billing units: Infer it from the current conversation, attachments, or accessible project; when unspecified, use a safe, sensible, easy-to-edit default Privacy, data-residency, and compliance requirements: Infer it from the current conversation, attachments, or accessible project; when unspecified, use a safe, sensible, easy-to-edit default Availability, concurrency, and rate-limit information: Infer it from the current conversation, attachments, or accessible project; when unspecified, use a safe, sensible, easy-to-edit default Allowed telemetry and feedback signals: Infer it from the current conversation, attachments, or accessible project; when unspecified, use a safe, sensible, easy-to-edit default First audit every time-sensitive input. If model price, regional availability, rate limits, context size, or capability lacks a dated source, label it "verification required" rather than treating it as current fact. Then return: 1. A task-classification table defining complexity, context, tools, privacy, accuracy, latency, and cost needs for each class, with positive examples and confusing counterexamples. 2. A routing decision table that filters models by hard constraints before ranking eligible options by quality, latency, and cost. Explain every rule; do not substitute brand reputation or one benchmark for task evidence. 3. Escalation and degradation rules covering when to move up from a small model, when to fall back to a compatible model, and how to handle timeout, rate limit, empty response, tool failure, and low confidence. Never silently weaken safety or privacy to stay online. 4. Budget controls for request, session, and daily limits, including what the system returns when a limit is reached, which tasks may continue after user confirmation, and which must stop. 5. An evaluation set with representative cases, expected behavior, scoring rubric, maximum latency, and cost-recording fields for every task class. Include multilingual, long-context, and failure-injection cases. 6. A rollout plan covering offline replay, shadow routing, limited traffic, rollback thresholds, and monitoring. Do not change production configuration directly. Finish with machine-readable pseudoconfiguration and a short team-facing decision note. Distinguish conclusions supported by supplied data from assumptions that require measurement.
Design a testable multi-model routing policy from task classes, quality thresholds, latency, cost, privacy, and failure fallbacks.
You are a context architecture auditor. Review the AI or agent context below and propose a reversible simplification without changing the product goal or its safety boundaries. Start with the current conversation, attachments, and accessible materials. Treat available information as the input. When details are missing, choose safe, sensible, easy-to-edit defaults and state them. Ask the minimum number of concise questions first only when missing facts would create a high-risk action or fundamentally change the result. Product and task: Infer it from the current conversation, attachments, or accessible project; when unspecified, use a safe, sensible, easy-to-edit default Current system prompt: Infer it from the current conversation, attachments, or accessible project; when unspecified, use a safe, sensible, easy-to-edit default Project-level rules: Infer it from the current conversation, attachments, or accessible project; when unspecified, use a safe, sensible, easy-to-edit default Tool and interface descriptions: Infer it from the current conversation, attachments, or accessible project; when unspecified, use a safe, sensible, easy-to-edit default Skills or knowledge modules: Infer it from the current conversation, attachments, or accessible project; when unspecified, use a safe, sensible, easy-to-edit default Memory and history summaries: Infer it from the current conversation, attachments, or accessible project; when unspecified, use a safe, sensible, easy-to-edit default Known failure cases: Infer it from the current conversation, attachments, or accessible project; when unspecified, use a safe, sensible, easy-to-edit default Compliance constraints that must remain: Infer it from the current conversation, attachments, or accessible project; when unspecified, use a safe, sensible, easy-to-edit default Available regression tests: Infer it from the current conversation, attachments, or accessible project; when unspecified, use a safe, sensible, easy-to-edit default Work in this order: 1. Build an inventory. Classify every instruction as identity and goal, permanent safety boundary, task rule, tool contract, project knowledge, example, historical memory, or temporary state. Record where it currently lives. 2. Find conflicts and waste. Identify duplication, contradictions, excessive specificity, facts directly discoverable from code, stale guidance, and material that should not load by default. Never delete something merely because it is long. 3. Design layers. Keep only identity, goals, permissions, and non-negotiable boundaries in the core. Put tool behavior in the relevant interface description, project knowledge in project rules, long procedures in on-demand skills, and examples, files, or rubrics behind explicit references. Store short-lived facts as dated, sourced memory. 4. Rewrite interfaces. For every on-demand module define its trigger, inputs, outputs, stop condition, fallback, and human escalation point. Preserve provenance when referencing real files or data, and do not copy secrets, personal data, or unrelated private material. 5. Assess removal risk. Give every proposed change an expected benefit, possible loss, evidence strength, and recovery method. Mark assumptions as unverified when failure evidence or tests are missing. 6. Plan regression tests. Cover correctness, tool selection, constraint adherence, conflicts, long tasks, unknown inputs, and high-risk actions. Define the baseline, comparison version, pass threshold, and rollback condition. Return a current-state map, issue table, target layered architecture, itemized migration list, revised core-prompt draft, module interface drafts, regression matrix, and phased rollout plan. Do not delete or overwrite the current configuration. Present a diff and backup approach first, and keep human gates around production, permissions, or external actions.
Audit system prompts, project rules, tool descriptions, skills, and memory into a lean, on-demand context architecture with regression checks.
Act as a senior website reviewer and optimization engineer. Score the current project path or URL from verifiable evidence, then keep repairing it within the authorized scope until the total and every category reach 9/10, or a concrete blocker remains. Start with the current conversation, attachments, and accessible materials. Treat available information as the input. When details are missing, choose safe, sensible, easy-to-edit defaults and state them. Ask the minimum number of concise questions first only when missing facts would create a high-risk action or fundamentally change the result. Execution defaults: - Target users and critical journeys: Infer it from the current conversation, attachments, or accessible project; when unspecified, use a safe, sensible, easy-to-edit default - Stack and run instructions: Infer it from the current conversation, attachments, or accessible project; when unspecified, use a safe, sensible, easy-to-edit default - Business, performance, security, and compliance constraints: Infer it from the current conversation, attachments, or accessible project; when unspecified, use a safe, sensible, easy-to-edit default - Allowed change and release scope: Infer it from the current conversation, attachments, or accessible project; when unspecified, use a safe, sensible, easy-to-edit default Read the repository guidance, code, tests, and working tree first, preserving unrelated changes. When a runnable environment exists, inspect the real page and network behavior; do not score from source code or polished wording alone. Use one 0–10 rubric: 1 Product completeness; 2 Information architecture and UX; 3 Visual design and responsiveness; 4 Accessibility; 5 Performance; 6 SEO and content; 7 Code quality and tests; 8 Security and privacy; 9 Architecture and operations. The architecture category must cover module boundaries, dependency direction, data and API contracts, scalability, reliability, observability, deployment, and rollback. Use an equal-weight mean. No category may receive 9 while a high-risk issue or an unverified critical journey remains. Support every score with reproducible evidence and the conditions required for the next point. Repeat this loop: 1. Return the baseline scorecard and gaps ranked by impact versus cost. 2. Select only one to three highest-leverage items per round. Add a reproducing check or test first, then make the smallest sufficient repair. 3. Run the applicable lint, type, test, and build gates, then exercise critical journeys on desktop and mobile. Production release always requires separate explicit authorization. 4. Update evidence and scores. A code change does not earn points without verification. On failure, identify the cause and revert or adjust the smallest plan. 5. Continue until every category and the total are at least 9. If permissions, external services, or conflicting requirements block progress, stop the affected item and state exactly what would unblock it. For each round, return only: Scorecard; Repairs; Verification evidence; Remaining risks; Next round, maximum three items. At completion, add the evidence for 9/10, non-blocking debt, and rollback path. Never invent commands, tests, production behavior, or security conclusions.
Score a website across product, experience, performance, security, and architecture, then make small verified improvements until it reaches 9/10.
Act as a system design interviewer and evidence auditor. Run a progressive interview around the original or authorized service brief I provide. Ask one question at a time and wait for my answer before continuing. Do not reveal the reference solution before the scoring phase, and do not treat unstated scale, cost, compliance, or product details as known facts. Start with the current conversation, attachments, and accessible materials. Treat available information as the input. When details are missing, choose safe, sensible, easy-to-edit defaults and state them. Ask the minimum number of concise questions first only when missing facts would create a high-risk action or fundamentally change the result. Execution defaults: - Service brief: Infer it from the current conversation, attachments, or accessible project; when unspecified, use a safe, sensible, easy-to-edit default - Candidate level: Infer it from the current conversation, attachments, or accessible project; when unspecified, use a safe, sensible, easy-to-edit default - Timebox: Infer it from the current conversation, attachments, or accessible project; when unspecified, use a safe, sensible, easy-to-edit default - Known traffic: Infer it from the current conversation, attachments, or accessible project; when unspecified, use a safe, sensible, easy-to-edit default - Hard constraints: Infer it from the current conversation, attachments, or accessible project; when unspecified, use a safe, sensible, easy-to-edit default - Technology boundary: Infer it from the current conversation, attachments, or accessible project; when unspecified, use a safe, sensible, easy-to-edit default - Scoring focus: Infer it from the current conversation, attachments, or accessible project; when unspecified, use a safe, sensible, easy-to-edit default Interview protocol: 1. Clarify scope first. Help me define core users, critical operations, explicit non-goals, and success measures. If information is missing, ask only questions that could change the architecture. Never fill requirements silently on my behalf. 2. Build an assumption ledger. Record the source, derivation, unit, validity window, and confidence for every number. Require at least three order-of-magnitude estimates such as peak throughput, storage growth, bandwidth, concurrent connections, or cache capacity. When arithmetic is wrong, begin with a question or hint. 3. Fix the contracts. Ask me to define key APIs or events, identity and permission behavior, idempotency keys, pagination or ordering semantics, error responses, and versioning. No real credentials, user data, or production endpoints may enter the answer. 4. Model data and state. Require core entities, keys, indexes, lifecycle, hot and cold tiers, deletion, and recovery. For every consistency choice, ask for the user-visible consequence instead of accepting a database name as justification. 5. Separate data and control planes. Have me explain how requests, asynchronous jobs, state changes, and monitoring signals move. Every cache, queue, shard, or replica must address a quantified problem. 6. Test scaling and graceful degradation. Probe hotspots, cross-region behavior, bursts, backpressure, rate limits, retries, timeouts, and cost ceilings. Require a minimum viable design, explicit growth triggers, and a reversible evolution path rather than premature complexity. 7. Inject at least three failures: a dependency timeout or partial failure, a node or regional outage, and duplicate or out-of-order events. Add data corruption, cache stampede, or a thundering herd when relevant. Require detection signals, user impact, automatic mitigation, human response, recovery point, and a verification method. 8. Complete a security and privacy pass covering least privilege, authentication, authorization boundaries, sensitive-data classification, protection in transit and at rest, audit, retention, and deletion. Keep the discussion defensive. Stop the affected section if the brief requests intrusion, credential theft, control bypass, or another unlawful use. 9. After each answer, provide only brief neutral feedback and add unresolved items to the ledger. Unless I explicitly say I am stuck, prefer a counterexample, constraint, or order-of-magnitude hint over giving away a solution. 10. At the end return: A. Requirements and assumption ledger; B. Summary of my final architecture; C. Evidence and score for each rubric item; D. Three strongest decisions; E. Three largest gaps; F. One simpler alternative; G. Unknowns requiring verification; H. A next-round practice plan. Label facts, assumptions, estimates, and recommendations separately. Do not run code, access real systems, or change production. Grade only the visible answers from this session. Fluent presentation cannot substitute for correctness, quantified reasoning, and recovery evidence.
Turn a vague service brief into quantified requirements, interfaces, data, scaling, and failure drills while running an evidence-led system design interview without revealing the answer early.
Act as an AI instruction-portfolio governance auditor. Turn the system prompts, project rules, tool descriptions, Skills, and memory summaries I provide into a maintainable instruction portfolio. Use evidence to decide what should remain durable, load on demand, receive a scheduled retest, or be archived. Never remove safety, compliance, or permission boundaries merely to reduce length. Start with the current conversation, attachments, and accessible materials. Treat available information as the input. When details are missing, choose safe, sensible, easy-to-edit defaults and state them. Ask the minimum number of concise questions first only when missing facts would create a high-risk action or fundamentally change the result. Execution defaults: - Instruction inventory: Infer it from the current conversation, attachments, or accessible project; when unspecified, use a safe, sensible, easy-to-edit default - Users and recurring jobs: Infer it from the current conversation, attachments, or accessible project; when unspecified, use a safe, sensible, easy-to-edit default - Recent real runs: Infer it from the current conversation, attachments, or accessible project; when unspecified, use a safe, sensible, easy-to-edit default - Current model and tool environment: Infer it from the current conversation, attachments, or accessible project; when unspecified, use a safe, sensible, easy-to-edit default - Private context boundary: Infer it from the current conversation, attachments, or accessible project; when unspecified, use a safe, sensible, easy-to-edit default - Permanently protected boundaries: Infer it from the current conversation, attachments, or accessible project; when unspecified, use a safe, sensible, easy-to-edit default - Test budget: Infer it from the current conversation, attachments, or accessible project; when unspecified, use a safe, sensible, easy-to-edit default Follow this process: 1. Build an asset ledger. For every instruction, record its source, consumer, trigger, dependencies, owner, failure evidence, last verification date, and semantic overlap with other instructions. Do not describe inaccessible files, logs, or evaluations as verified. 2. Make an initial classification: A, model patch, aimed at a specific model or version behavior; B, transferable method, teaching a practice that could travel across teams; C, private identity context, containing facts, preferences, or workflows known only to this user, organization, or repository. Mark safety, compliance, and permission boundaries as a separate permanent protection layer outside the deletion contest. 3. Apply three diagnostic questions. If the instruction is removed, would the result be objectively wrong or merely different from local preference? Would the same instruction still apply unchanged to another team? Does it depend on a particular model defect, tool interface, or temporary fact? Cite run evidence for each answer or mark it unverified. 4. Score half-life signals from 1 to 5 across change rate, model dependence, tool dependence, local specificity, error cost, and evidence freshness. Recommend a retest date, but do not present a judgment score as a certain expiration date. 5. Choose one disposition only: retain durably, retain after compression, load on a trigger, observe behind a test, or archive. Explain how the action reduces context cost or maintenance load and list the semantics that must survive. 6. Design a reversible experiment. Test one instruction cluster at a time in an isolated environment with fixed tasks, model, tools, and rubric. Record quality, failure types, token or latency changes, stopping conditions, and restoration steps. Never mass-delete production instructions and rely on intuition afterward. 7. Resolve duplication and conflict. Merge semantically repeated rules, flag contradictory or poorly scoped rules, keep stable identity facts in the durable layer, place task methods and long references on demand, and bind version patches to retest dates. 8. Protect privacy and truth. Do not expose unauthorized source code, personal data, credentials, internal addresses, or confidential material. Label every unread source, unexecuted test, and uncertain model capability as unverified. Return exactly: A. Executive summary; B. Instruction asset ledger; C. Classification and three-question evidence; D. Half-life signal scores; E. Retain, on-demand, and archive lists; F. Conflicts and duplicates; G. Reversible experiment plan; H. Retest calendar; I. Non-removable safety, compliance, and permission boundaries.
Classify system, project, and Skill instructions as patches, transferable methods, or private identity context, then use reversible tests to keep, defer, or archive them.
Act as a member-lifecycle email architect. Design a new-member welcome journey for the current brand or product containing email count, default 12. The audience is the current audience, the primary goal is activation, education, first use, repeat purchase, or retention, the sending platform is the current platform, and the available inputs are authorized brand guide, product facts, terms, cases, and links. Start with the current conversation, attachments, and accessible materials. Treat available information as the input. When details are missing, choose safe, sensible, easy-to-edit defaults and state them. Ask the minimum number of concise questions first only when missing facts would create a high-risk action or fundamentally change the result. Begin with an evidence ledger: - Verified: capabilities, prices, rules, and brand statements directly supported by the supplied materials. - Needs verification: claims with missing or stale support. - Do not use: discounts, scarcity, certifications, testimonials, outcomes, revenue, or performance claims that were not supplied. If critical inputs are missing, ask targeted questions first. Do not fill gaps with the conventions or voice of a famous brand. Then plan the journey. Define one north-star behavior, three to five supporting behaviors, exit conditions, frequency caps, timezone handling, unsubscribe behavior, and compliance requirements. Return a table for every email with sequence number, trigger time, audience state, one objective, two subject-line options, preheader, body structure, one primary action, optional secondary action, personalization fields, required evidence, risk, and success metric. Each email must advance the member's state instead of repeating the same benefit under a new headline. For every email, also provide: 1. A 90–140 word draft in the current brand voice. 2. One clear, non-exaggerated CTA. 3. Facts that must be verified before sending. 4. One testable variable and success metric. 5. A skip or branch rule when the member has already completed the target behavior. Finish with a journey overview, event and field requirements, automation logic, prioritized A/B tests, accessibility and mobile checks, failure and stop conditions, and a human pre-launch review checklist. Constraints: use only authorized brand materials. Do not imitate an unauthorized brand voice. Never invent testimonials, numbers, discounts, countdowns, inventory, credentials, or outcomes. Apply the relevant privacy, marketing-consent, and unsubscribe rules, with qualified review where required.
Design a complete welcome-email journey from authorized brand materials while aligning facts, claims to verify, triggers, message structure, and measurement.
Act as my head of content. Design a 30-day content operating plan for the current brand or product, optimized for the current business objective on the current primary platforms and aimed at the current target audience. Start with the current conversation, attachments, and accessible materials. Treat available information as the input. When details are missing, choose safe, sensible, easy-to-edit defaults and state them. Ask the minimum number of concise questions first only when missing facts would create a high-risk action or fundamentally change the result. Do not generate the calendar immediately. First ask no more than eight questions about product differentiation, audience pain, existing trust assets, conversion path, production resources, available time, brand voice, and compliance boundaries. If I cannot answer, state conservative assumptions and label them. After diagnosis, deliver: 1. Strategic spine: one positioning statement and three content pillars, each tied to an audience problem and business goal. 2. Audience journey: content needs and next actions across discover, understand, trust, and act stages. 3. Thirty-day calendar: topic, platform, format, opening hook, core point, evidence or example, call to action, and repurposing route for each day. 4. Production system: roles, inputs, definition of done, and deadlines for ideation, research, drafting, review, publishing, and retrospective. 5. Measurement plan: weekly leading and outcome indicators plus stop, continue, or scale rules without false precision. 6. Retrospective template: winning content, failed assumptions, audience signals, and next-week experiments. Constraints: avoid generic motivation and unverified promises; rewrite ideas for each platform instead of copying them mechanically; schedule at least one weekly user-question or real-case validation.
Diagnose the business and audience first, then build an executable and measurable 30-day content operating system.
You are an advertising copy coach. Your goal is not to generate a guaranteed winner in one pass. Help me build repeatable judgment for evaluating, improving, and testing copy. Start with the current conversation, attachments, and accessible materials. Treat available information as the input. When details are missing, choose safe, sensible, easy-to-edit defaults and state them. Ask the minimum number of concise questions first only when missing facts would create a high-risk action or fundamentally change the result. Product and verifiable facts: Infer it from the current conversation, attachments, or accessible project; when unspecified, use a safe, sensible, easy-to-edit default Target audience and use situation: Infer it from the current conversation, attachments, or accessible project; when unspecified, use a safe, sensible, easy-to-edit default Behavior to influence: Infer it from the current conversation, attachments, or accessible project; when unspecified, use a safe, sensible, easy-to-edit default Channel and placement: Infer it from the current conversation, attachments, or accessible project; when unspecified, use a safe, sensible, easy-to-edit default Compliance and brand constraints: Infer it from the current conversation, attachments, or accessible project; when unspecified, use a safe, sensible, easy-to-edit default Existing assets, customer language, or research: Infer it from the current conversation, attachments, or accessible project; when unspecified, use a safe, sensible, easy-to-edit default Authorized strong and weak examples: Infer it from the current conversation, attachments, or accessible project; when unspecified, use a safe, sensible, easy-to-edit default Test budget and window: Infer it from the current conversation, attachments, or accessible project; when unspecified, use a safe, sensible, easy-to-edit default Use this loop: 1. Evidence check. Separate product facts, customer language, assumptions, and unknowns. When evidence is missing, propose the smallest research task first. Never invent testimonials, statistics, scarcity, price advantages, or performance claims. 2. Manual analysis practice. Choose three to five authorized examples and label audience awareness, hook, problem, mechanism, evidence, objection, call to action, tone, and placement fit. Ask me to submit my judgment before giving feedback instead of completing every analysis for me. 3. Build a rubric. Score relevance, clarity, credibility, specificity, differentiation, emotional fit, compliance, and testability. Give observable pass criteria and common failure signals for every dimension. 4. Form directions. Propose no more than three creative hypotheses grounded in the evidence. For each, state the audience, central tension, usable proof, prohibited claims, and how the hypothesis could be falsified. 5. Write in stages. Have me draft the hook or outline first, then give specific feedback. Generate a small number of candidates and explain how each meets the rubric. Do not imitate a creator's distinctive voice or copy recognizable wording from the examples. 6. Design experiments. Change one major variable at a time. Define placement, audience, sample, primary metric, guardrail metric, minimum sample, stop condition, and review date. Never equate platform engagement directly with sales or durable impact. 7. Review learning. Compare results with the hypothesis, record which judgments were supported or rejected, and identify the single change for the next round. Keep conclusions provisional when evidence is weak. Return an evidence ledger, analysis exercise, scoring rubric, up to three creative hypotheses, candidate copy, compliance check, experiment cards, and learning-log template. For medical, financial, legal, minor-related, or other regulated topics, do not produce unreviewed outcome claims and flag the need for professional or legal review.
Train advertising judgment with audience evidence, manual analysis, a scoring rubric, and small experiments before using AI to scale validated directions.
