# AI product UX > Explore trust, transparency and user control in AI products. Canonical page: https://aixdesign.kens-toolbox.com/en/learn/design-for-ai ## Content generation Help users compare, edit and finish drafts instead of accepting a single generated result. Let users correct the output without regenerating everything. - Support stopping, editing and retrying while preserving useful output. - Make source passages available when citations matter and explain missing information. ## Claude Long-form generation and structured rewriting; ask it to flag uncertainty and suggest edits instead of final answers. [Claude](https://aixdesign.kens-toolbox.com/en/tools/claude) ## ChatGPT General-purpose generation and rewriting for fast iteration across multiple variants. [ChatGPT](https://aixdesign.kens-toolbox.com/en/tools/chatgpt) ## Gemini Multimodal generation when text and image need to work together. [Gemini](https://aixdesign.kens-toolbox.com/en/tools/google-gemini) ## Google Flow Prototype storyboards from references or start/end frames; review characters, motion and continuity before expanding. [Google Flow](https://aixdesign.kens-toolbox.com/en/tools/google-flow) ## Midjourney Visual direction exploration and high-quality image generation for moodboarding. [Midjourney](https://aixdesign.kens-toolbox.com/en/tools/midjourney) ## NN/g: AI Hallucinations Read before designing generated-output surfaces; covers citation mismatch risks and mitigation patterns. [NN/g: AI Hallucinations](https://www.nngroup.com/articles/ai-hallucinations/) ## IBM Carbon for AI Reference for labeling AI-generated content and communicating explainability in UI components. [IBM Carbon for AI](https://carbondesignsystem.com/guidelines/carbon-for-ai/) ## Google Flow: video creation guide Learn text, reference and frame-based generation, starting with one shot. [Google Flow: video creation guide](https://support.google.com/flow/answer/16353334?hl=en) ## Google Flow: model capabilities Check support for references, video editing and extensions before choosing a model. [Google Flow: model capabilities](https://support.google.com/flow/answer/16352836?hl=en) ## Figma Make Generate runnable prototypes through conversation for quick demos; verify third-party licenses before external sharing. [Figma Make](https://aixdesign.kens-toolbox.com/en/tools/figma-make) ## Google PAIR Guidebook Define what users can or can't edit and where AI involvement should be visible. [Google PAIR Guidebook](https://pair.withgoogle.com/guidebook/) ## Microsoft HAX Toolkit Map capability boundaries clearly: what the system can do, how well, and what happens when it is wrong. [Microsoft HAX Toolkit](https://www.microsoft.com/en-us/haxtoolkit/ai-guidelines/) ## Content generation template Template — prompt Claude directly to output draft, basis, uncertainty, and compliance flags. Prompt Claude: "Draft \[output type\] for \[audience\] given this context: \[paste context\]. Format response as: (1) editable draft, (2) sources or basis, (3) uncertain points and next steps. Flag anything needing copyright or compliance check." [Content generation template](#) ## Decision support Present options, evidence and tradeoffs together while letting users modify or reject advice. Keep reasons close to options and avoid unsupported precision in scores. - Explain assumptions and missing information behind a recommendation. - Show the consequences before an action affects an external system. ## ChatGPT Generate conservative/default/bold options with trade-off reasoning per option. [ChatGPT](https://aixdesign.kens-toolbox.com/en/tools/chatgpt) ## Claude Long-form review, risk flagging, and rewrite comparison for decisions with deep context. [Claude](https://aixdesign.kens-toolbox.com/en/tools/claude) ## Notion AI Structured suggestions inside team documents while preserving context and edit history. [Notion AI](https://www.notion.com/product/ai) ## Microsoft Copilot Suggestions, summaries, and decision support in Office workflows. [Microsoft Copilot](https://aixdesign.kens-toolbox.com/en/tools/microsoft-copilot) ## Grammarly Rewrite and tone suggestions with a clear suggest -\> accept/modify pattern. [Grammarly](https://www.grammarly.com/features) ## HAX Guideline 11 + Pattern 11A Surface local, just-in-time reasoning inline instead of long explanation modals. [HAX Guideline 11 + Pattern 11A](https://www.microsoft.com/en-us/haxtoolkit/guideline/make-clear-why-the-system-did-what-it-did/) ## IBM Carbon for AI Reference for confidence, provenance, and reasoning expression inside components. [IBM Carbon for AI](https://carbondesignsystem.com/guidelines/carbon-for-ai/) ## Ladder of inference Prevent teams from jumping to conclusions by separating observable facts from interpretation. [Ladder of inference](https://untools.co/ladder-of-inference/) ## HAX Guideline 9 Design how users override, edit, and recover when AI recommendations are off. [HAX Guideline 9](https://www.microsoft.com/en-us/haxtoolkit/guideline/support-efficient-correction/) ## HAX Pattern 16A Feedforward Show high-risk consequences before execution, especially for irreversible downstream steps. [HAX Pattern 16A Feedforward](https://www.microsoft.com/en-us/haxtoolkit/pattern/g16-a-feedforward-convey-the-consequences-of-user-actions-before-the-user-takes-action/) ## Decision proposal template Template — prompt Claude directly to generate options, risks, editability, and commit consequences. Prompt Claude: "Given this decision \[describe it\], present three options: conservative, default, and bold. For each include: why it is recommended, estimated benefit and risk, what is editable, and what happens if committed. Flag any high-risk consequences that require a confirmation step." [Decision proposal template](#) ## Data analysis Help users understand findings and inspect calculations, filters and limitations. Let users inspect sources, adjust filters and recalculate. - State data dates, metric definitions and treatment of missing values. - Make key figures reproducible and trace charts and conclusions to data. ## Amplitude Use for behavior analysis tied to funnel drop-offs, adoption, and retention signals. [Amplitude](https://amplitude.com/get-started) ## Power BI Copilot Use natural-language queries to generate visualizations and analysis summaries. [Power BI Copilot](https://learn.microsoft.com/en-us/power-bi/create-reports/copilot-introduction) ## Tableau Pulse Automatically surface key metric changes with plain-language explanations. [Tableau Pulse](https://www.tableau.com/products/tableau-pulse) ## Perplexity Use citation-tracked research for external benchmarks and evidence tracing. [Perplexity](https://aixdesign.kens-toolbox.com/en/tools/perplexity) ## Looker Metric management with permission controls and shareable views for single-source-of-truth teams. [Looker](https://docs.cloud.google.com/looker/docs) ## NIST AI RMF Align analysis outputs with trustworthy AI and auditability requirements. [NIST AI RMF](https://www.nist.gov/itl/ai-risk-management-framework) ## WCAG Overview Baseline for accessible data presentation: contrast, labeling, and keyboard navigation. [WCAG Overview](https://www.w3.org/WAI/standards-guidelines/wcag/) ## Google PAIR Guidebook Design how insights are framed: what is certain, inferred, and what users should do next. [Google PAIR Guidebook](https://pair.withgoogle.com/guidebook/) ## Concept map Visualize relationships between metrics, segments, and causes so insight narratives stay coherent. [Concept map](https://untools.co/concept-map/) ## Analysis summary template Template — prompt Claude or use as a Notion structure to keep findings reproducible. Prompt: "Summarize this analysis for \[audience\]. Include: (1) question answered, (2) metric definition and time window, (3) key finding with source, (4) what is uncertain, (5) reproducible query steps or link." [Analysis summary template](#) ## Task automation Use a defined workflow for predictable steps and an agent when tool choices need to adapt, keeping progress and outcomes visible. Make one task reliable before adding autonomy and more tools. - Support pausing and recovery and prevent duplicate actions. - Test outcomes for common tasks, missing context and tool failures. ## Zapier Lightweight cross-app automation for lower-risk flows where full agent orchestration is overkill. [Zapier](https://zapier.com/) ## n8n Visual workflow orchestration with self-hosting; check the license before offering it as a hosted service to clients. [n8n](https://n8n.io/) ## Dify Build LLM apps and agent flows visually to try prompts, retrieval and tool calls. [Dify](https://github.com/langgenius/dify) ## NIST AI RMF Define risk boundaries, permission tiers, and governance checkpoints before launch. [NIST AI RMF](https://www.nist.gov/itl/ai-risk-management-framework) ## promptfoo Red-team test injection, override, and unauthorized-access risks before go-live. [promptfoo](https://www.promptfoo.dev/docs/intro/) ## MCP security MCP authorization and security boundaries; connecting tools does not grant unlimited permissions. [MCP security](https://modelcontextprotocol.io/docs/2026-07-28/tutorials/security/security_best_practices) ## UiPath Enterprise orchestration reference for wiring human approval into multi-step agent execution. [UiPath](https://www.uipath.com/platform/agentic-automation) ## LangChain HITL Design pattern for manual approval before critical write/spend/send actions. [LangChain HITL](https://docs.langchain.com/oss/python/langchain/human-in-the-loop) ## Make Cross-SaaS automation when the workflow needs approvals but not full agent complexity. [Make](https://www.make.com/) ## Langfuse Trace execution, monitor cost, and review prompt/version drift to audit what the agent actually did. [Langfuse](https://langfuse.com/docs) ## OpenAI Evals Use for quality and regression testing so agent behavior does not silently drift after changes. [OpenAI Evals](https://github.com/openai/evals) ## UiPath Agentic Automation Reference for enterprise rollback strategy, audit logs, and human-robot collaboration patterns. [UiPath Agentic Automation](https://www.uipath.com/automation/agentic-automation) ## OODA loop Design faster observe-orient-decide-act response loops for incidents and runtime uncertainty. [OODA loop](https://untools.co/ooda-loop/) ## Evaluating agents Build evaluations from real tasks and assess outcomes, recovery, latency and cost. [Evaluating agents](https://www.anthropic.com/engineering/demystifying-evals-for-ai-agents) ## Automation execution template Template — review with your team first, then prompt Claude for approval/fallback/audit fields. Cover before build: execution scope \| step-by-step plan + risk level \| approval points (write/spend/send) \| failure fallback per step \| interruption conditions \| log fields (who/when/what/impact) \| cost budget cap. Then prompt Claude: "Given this agent flow \[paste steps\], identify which steps need human approval, what fallback each step needs, and what log fields are required for auditability." [Automation execution template](#) ## Cross-scenario foundations ## Google PAIR Guidebook Human-centered AI product design baseline for cross-team principle alignment. [Google PAIR Guidebook](https://pair.withgoogle.com/guidebook/) ## Microsoft HAX Toolkit Turns explainability, correction, and recovery into concrete review checkpoints. [Microsoft HAX Toolkit](https://www.microsoft.com/en-us/haxtoolkit/ai-guidelines/) ## IBM Carbon for AI Patterns for AI labeling, supporting evidence and user control. [IBM Carbon for AI](https://carbondesignsystem.com/guidelines/carbon-for-ai/) ## AIUXPatterns Browse AI-specific UX patterns and anti-patterns as a practical reference across all scenarios. [AIUXPatterns](https://aiuxpatterns.com/) ## NIST AI RMF Align trustworthy AI requirements with risk management and governance. [NIST AI RMF](https://www.nist.gov/itl/ai-risk-management-framework) ## WCAG Overview Accessibility baseline across all scenarios and interaction types. [WCAG Overview](https://www.w3.org/WAI/standards-guidelines/wcag/) ## Related resources - [Design with AI](https://aixdesign.kens-toolbox.com/en/learn/design-with-ai.md): Methods and references for research, ideas, prototypes and design delivery. - [AI product UX](https://aixdesign.kens-toolbox.com/en/learn/design-for-ai.md): Explore trust, transparency and user control in AI products. - [Vibe coding for designers](https://aixdesign.kens-toolbox.com/en/learn/vibe-coding.md): Practical paths and tools for designers building with AI. - [Build your portfolio with AI](https://aixdesign.kens-toolbox.com/en/learn/build-portfolio-with-ai.md): Use AI to frame your projects, develop case studies and publish your work. - [Community field notes](https://aixdesign.kens-toolbox.com/en/learn/community-field-notes.md): Field notes, exercises and resources from our community discussions. - [AI design tools](https://aixdesign.kens-toolbox.com/en/tools.md): Explore AI tools for design, research, visual creation and development. Part of [Ken's Toolbox](https://kens-toolbox.com/). Account and participant data are not included in this public summary.