9 min readStart Building Your Company With an Evidence-First Launch Brief
Produce a decision-ready company launch brief and a verified handoff for designing the first website.
You know the basics. These articles give you practical skills you can apply at work tomorrow.
93 results
Nothing matches these filtersTry a different category or level, or clear the filters to see everything.
9 min readProduce a decision-ready company launch brief and a verified handoff for designing the first website.
9 min readProduce three comparable webpage directions and a documented, evidence-based decision for the first company website.
10 min readBuild and verify a deployable static company website from an approved content model and design direction.
9 min readDeploy a static company website through a verified preview-to-production workflow with a tested rollback path.
4 min readBuild a private disclosure comparison and identify missing assumptions without asking AI to select a financial product.
4 min readRun a claim-trace checklist that routes investment pitches through official verification steps instead of AI product picks.
4 min readProduce a dispute-prep packet of mismatched lines and evidence notes without engaging score-hack or guaranteed-deletion advice.
4 min readWrite a six-field home project brief before any generative prompt so constraints stay human-owned and life-safety trades stay off DIY rails.
4 min readRun a line-by-line materials verification pass from manufacturer specs and reader constraints so AI lists cannot silently become unsafe purchases.
4 min readBuild a scope-aligned comparison grid from reader-supplied written quotes and list clarifying questions without letting AI select the contractor.
4 min readApply hard-stop rules so electrical, gas, structural, roof-load, and asbestos prompts stay in question-pack mode instead of DIY instruction mode.
4 min readRecognize FTC home-improvement scam patterns and use AI only to rehearse verification questions and organize notes - never to trust an unverified doorstep quote.
6 min readRun a draft-then-critique loop where human drafting comes first and model feedback stays criteria-bound.
6 min readRun direction-locked variant iteration so exploration does not erase the creative thesis.
6 min readBuild a visual reference practice that uses genre and technique cues instead of cloning a living artist's style.
5 min readDecide when AI assistance needs a creative credit and write an honest, proportionate disclosure line.
6 min readRun a consent-and-scope checklist before using synthetic voice or likeness in any creative project.
5 min readRun a proposal-drafting workflow where AI formats structure while you retain exclusive control of price, scope, and commitments.
5 min readMaintain a scope change log that blocks AI-invented delivery promises and captures client acceptance.
4 min readProduce portfolio case writeups grounded in permissioned evidence without AI-invented results.
6 min readBuild a private clause-and-invoice field checklist with exact source quotes and questions for a qualified professional, without sharing client documents with a chatbot.
6 min readBuild a source-linked question list and uncertainty log for the next clinical conversation, without asking AI to interpret a prognosis.
5 min readPrepare precise questions from a medical document while preserving the original wording, protecting the document and leaving interpretation to the care team.
6 min readPrepare a consent-aware handoff covering preferences, routines, and open tasks, with the cared-for person's own voice preserved.
6 min readBuild and check private what-if budget scenarios from verified household figures, and identify which decisions need a qualified adviser.
5 min readReview real transactions privately for recurring charges and produce a checked cancellation list without connecting an AI tool to a bank account or sharing transaction lines.
5 min readTranslate a government form's instructions into a source-linked checklist and identify questions for the responsible authority, without inventing entitlements.
3 min readExtract obligations, dates, fees, and change terms from a contract into a clause ledger with questions for a qualified professional, preserving exact wording without drawing legal conclusions.
4 min readBuild a private itinerary with source checks, feasible connections, access confirmations and verified fallback options.
3 min readDescribe a functional barrier, requested change, alternative, and follow-up plan without disclosing more health data than needed.
6 min readSummarize a public proposal from primary documents, surface disputed claims, and prepare questions for human participation.
5 min readDraft a factual complaint letter from receipts, dates, and a requested remedy, without legal threats or invented consumer-rights claims.
6 min readIdentify tasks where productive difficulty builds judgement and redesign AI use to preserve an unaided attempt.
6 min readDistinguish accessibility or practice benefits of AI companionship from dependency and displacement of human contact.
5 min readCompare a decision against self-authored values and document the conflicts that remain.
4 min readApply a practical disclosure norm for AI-assisted deliverables that keeps accountability with a named human.
4 min readUse AI to draft apology wording while keeping the repair, delivery, and follow-through with the person who caused harm.
5 min readRefuse to use AI to score, rank, or grade people in daily life or work without an accountable human process.
7 min readRun a two-part consent-and-disclosure check on any AI-generated or AI-edited media of a real person before posting or sharing it.
4 min readRecognize the specific limits of AI-generated and AI-edited images, and avoid trusting a detector tool's verdict on any single image.
6 min readValidate material claims in an AI-generated news summary against the original article and underlying primary documents before sharing or acting on them.
5 min readRead a Content Credentials badge or AI-content watermark correctly - know what it proves, what it doesn't, and why its absence proves nothing either.
6 min readRun a consent check before uploading, AI-editing, or sharing a photo that includes another identifiable person.
5 min readInterrupt a false or unverified claim spreading in a group chat using a low-confrontation script and a quick AI-assisted verification step, without derailing into a personal conflict.
4 min readPrepare a self-assessment for a performance review using AI to organize verified evidence, without fabricating or exaggerating claims.
6 min readVerify AI-generated meeting notes for accuracy, correct attribution, and decided-versus-open status before distributing them.
5 min readDraft peer or direct-report feedback with AI while keeping every example evidence-based and the tone accurate to your actual intent.
4 min readDraft async status updates with AI that accurately reflect blocked, behind-schedule, or uncertain status rather than defaulting to upbeat language.
5 min readVerify any AI-generated claim about a specific employer's HR or company policy against the actual handbook or HR contact before acting on it.
5 min readRun a structured AI drill routine for vocabulary, grammar correction, and roleplay practice, while scheduling the human conversation practice that AI cannot substitute for.
6 min readBuild a return-to-study plan that uses AI to organize a syllabus-grounded catch-up schedule while preserving the actual assessment rules, allowed supports and evidence of the skills being practised.
6 min readUse AI for practice questions and explanations during exam preparation, and identify the specific point where use becomes a policy violation rather than study help.
8 min readRead an academic paper's actual claim, method, and stated limitations accurately as a non-expert, using AI to define jargon and check comprehension without letting it upgrade a hedge into a fact.
7 min readBuild a cumulative lecture-question bank with source pointers, uncertainty labels, unaided attempts, and a resolution log for gaps across the course.
6 min readUse measured run times and quoted transcript evidence to compare rehearsals. Check the recording for pauses and filler words that transcription may remove, and ask a listener about delivery. The workflow does not verify the talk's facts.
7 min readBuild a certification study plan from the certifying body's own exam content outline, allocating time by its actual domain weightings and tracking evidence of competence per domain rather than chapters read.
3 min readPrepare a private brief that separates your reported observations, interpretation, request, uncertainty and opening sentence.
3 min readBuild a private household constraint map and choose a freely agreed change with a suitable review date.
5 min readBuild a consent-aware care-coordination record that separates emergency information from routine admin, with minimum necessary disclosure and your parent's own preferences recorded in their words.
5 min readApply a four-question screen that separates policy compliance, disclosure, learning support, and independent demonstration, then take ambiguous or accommodation-sensitive cases to the responsible educator.
5 min readObserve a child's AI use across five concrete prompts (activity, attachment, displacement, privacy or concealment, and after-effects) and know when to involve a qualified person, without treating the prompts as a diagnostic screen.
6 min readRun a preliminary seven-point privacy screen, document unanswered questions, and escalate the final child-product decision to the responsible adult or qualified privacy reviewer.
5 min readEvaluate one teacher-approved AI-assisted access adaptation for a specific barrier while preserving the learning goal, privacy, and the learner's existing accommodations.
5 min readDraft a household AI agreement with the child as a participant, record it in an accessible form and choose when to review it; signing is optional.
9 min readA first-response plan for harmful synthetic images involving a child: protect the child, avoid copying suspected sexual material, preserve non-content details, and use official platform and national reporting routes.
8 min readCheck candidate themes against low-risk source notes, distinguish missing follow-up from unfinished work, and choose a next step without treating a model's interpretation as fact.
4 min readSeparate a felt reaction from the story attached to it and prepare one grounded next step.
4 min readUse a reversible/irreversible decision check, evidence ledger, and delay rule before acting under stress.
9 min readRecognize repeated reassurance-seeking from a chatbot and replace it with a pre-committed human or offline action.
4 min readTurn a vague goal into a testable two-week experiment with named constraints, leading actions, and a review date.
4 min readBuild a practice loop with a specific subskill, explicit criteria, checked feedback, a retry and an independent transfer check.
4 min readUse preview, active questions, unaided recall, and source-checked synthesis to retain one important text, with quotes, paraphrases, and model inferences clearly labeled.
3 min readChoose an AI assistance boundary for one creative stage and inspect a revision against that boundary.
8 min readBuild a capability-evidence matrix and use it to choose two realistic, low-cost experiments for a possible career transition.
7 min readIdentify sycophancy, framing lock-in, fluency bias, and outsourced judgement in an AI-assisted decision, then apply one concrete countermeasure to each.
7 min readApply five repeatable prompting patterns that expose weak assumptions and produce independent counterarguments without treating model disagreement as proof.
7 min readBuild a one-week study loop that uses AI to prepare source-grounded questions while preserving retrieval effort, spaced review, and useful interleaving.
4 min readCreate a stage-by-stage delegation card for one workflow, preserving authority, relational participation and required skills.
4 min readBuild prompts with role, context, task, constraints, and format, plus a validation check, instead of relying on one-off wording tricks.
8 min readTurn a weak first answer into usable output through critique, narrowing, pivots, and stress tests.
4 min readPick a model by task type and mode (fast vs reasoning) using decision criteria, not a timeless ranking.
3 min readBuild a factual input-output example set and test its style, missing-data behavior and transfer to a new case.
4 min readConfigure reusable assistant context while avoiding stale memory and accidental disclosure of sensitive details.
4 min readCapture meetings with one tool and a quote-grounded cleanup prompt that surfaces decisions, owners, and open items.
4 min readDraft from your own bullets or voice, then remove generic patterns while checking facts, authorship, and required disclosure.
4 min readBuild a focused NotebookLM notebook for low-risk research and validate its answers by opening the cited passages and recording coverage gaps.
4 min readFrame a research question and verify every decision-critical claim against applicable primary sources before using the report.
7 min readWrite an audio job card, choose the correct processing pipeline, and run a representative acceptance test before publishing or operational use.
4 min readBuild one Custom GPT or Claude Project with clear instructions and curated knowledge files, and choose the platform by sharing, tooling, and privacy needs.
4 min readChoose prompt patterns by job type and pair them with validation instead of memorizing prompt recipes.
3 min readRun a four-step Frame → Generate → Stress-test → Decide workflow that requests counterarguments before you commit.
4 min readApply practical workplace rules for sensitive data, tool choice, retention, and review before using AI.
4 min readBuild a small AI automation with filters, validation, fallback behavior, and clear ownership.