FREE WORKING TOOLKIT
Less blank page.
More useful work.
Seven worksheets to turn the guides into a brief, a test, a review or a clear offer.
Type into a worksheet and use your browser’s Print command to save a PDF. Entries stay on this page only: they are not submitted or saved and will be lost on refresh. Download the Markdown templates for a durable editable copy.
Download all seven templatesIdea validation ledger
Turn a promising idea into claims you can investigate.
Who experiences the problem, in what context, and what do they do today?
What would make this idea unworkable if it were false?
List sources, dates and contradictory observations. Separate facts from assumptions.
What will you do, with whom, for how long? What result would change your mind?
What happened? What can the evidence support, and what remains uncertain?
Research evidence log
Keep sources, observations and interpretations separate.
Which decision does the study inform? Who participated, and what are the limits?
Source ID | Observation or exact excerpt | Context | Interpretation | Contradiction
Which sources support it? Which sources challenge it? What is your confidence and why?
Who checked the original material? What changed during review?
What will change, who owns it and what must be tested next?
Design quality scorecard
Review eight dimensions and keep blockers outside the average.
Version, date, audience, primary task, intended fidelity and reviewers.
Task clarity; content integrity; interaction completeness; visual hierarchy; brand specificity; accessibility; responsive behavior; maintainability.
For each: 0 blocking/missing, 1 major revision, 2 minor revision, 3 meets brief, or not evaluated. Add the observation and source.
List serious defects independently of scores. Assign an owner and evidence needed to resolve each.
Inputs, model/tool, settings, revision budget, review effort and unresolved issues. This rubric is not a certification or scientific benchmark.
User testing plan
Prepare a study that helps a real decision.
What needs to be learned, and which method fits?
Relevant criteria, access needs, recruitment, consent, recording, approved processing and retention.
Write realistic scenarios without naming the controls. Define success, assistance and failure.
Check prototype limits. Log session ID, action, context, quotation and interpretation separately.
Attach sources, include contradictions, state sample limits and choose a next action.
Art direction brief
Create a specific visual point of view before generating.
What should the person understand or do? What content must remain exact?
Reference | Quality to study | What not to copy | Rights or permission status.
Type relationships, color roles, spacing, image treatment, composition and motion.
Propose three different concepts, not three color variations. Record why you chose one.
Check content, cropping, coherence, responsive behavior, accessibility and editability.
Automation and AI team contract
Define a bounded workflow the team can understand and stop.
What starts the job, and who is accountable?
Required fields, approved sources, allowed tools, permissions and data limits.
Artifact format, validation rules, reviewer and quality criteria.
Missing inputs, invalid output, retries, duplicate prevention, error reporting and stop control.
Assistant role | Input | Output | Reviewer | Stop condition. Model agreement is not independent user evidence.
Baseline time, processing cost, review time, accepted output, errors, rework and next review date.
Client offer canvas
Turn expertise into a clear, credible service.
Who can use this service, and what observable problem triggers the need?
What is included, excluded, required from the client, and reviewed together?
Sample artifact or permitted case study. Label fictional examples and avoid unsupported results.
Where does AI assist? Who reviews? Are real participants involved? How is data handled?
Fact-checked reason to connect, next step, qualified conversations, proposals and wins.