methodology-process

Reusable screenshot-driven UI polish workflow for iterative visual refinement. Use when improving layout, hierarchy, spacing, feedback, or Tailwind-based presentation through repeated review-and-adjust passes. DO NOT USE FOR: functional bug fixing, accessibility-only audits, or…

Shared opening-phase protocol for upstream agents (Experience-Owner, Solution-Designer, Issue-Planner) and Code-Conductor when invoked on an existing GitHub issue. Renders a scaled context brief and runs a standards check on inherited work at each phase boundary. Use when a…

Reusable validation and review methodology for staged validation, failure triage, and prosecution-depth setup. Use when running validation ladders, triaging failures, or executing adversarial review passes. DO NOT USE FOR: CE Gate orchestration, specialist dispatch ownership, or…

Evidence-based verification checklist before marking work complete. Use before PRs, releases, marking tickets done, or any "I'm finished" declaration. DO NOT USE FOR: post-merge cleanup or archival (use post-pr-review) or processing GitHub review comments (use…

Structured multi-source research workflow. Use when thoroughly investigating a topic, comparing technologies, or gathering evidence for technical decisions.

Designing review workflows to surface and mitigate bias in AI outputs.

Designing for informed user consent, opt-out, and human override.

When and how AI should escalate to humans, refuse, or ask for clarification.

Defining behavioral boundaries — what the AI should and shouldn't do.

Proactively identifying failure modes, misuse, and unintended consequences.

Showing users what the AI knows, doesn't know, and how confident it is.

Helping users form warranted trust in the AI — neither overtrust nor undertrust — through deliberate confidence and source signalling.

Translating organisational values and user expectations into system constraints.

Defining what each agent does, knows, and owns in a multi-agent system.

What happens when an agent fails — retry, fallback, escalate, or graceful degradation.

Designing smooth transitions between agents and between AI and humans.

Designing intervention points where humans review, approve, or redirect agent work.

Making multi-agent workflows visible and debuggable for designers and developers.

Managing shared context, memory, and state across multiple agents.

Breaking complex user goals into subtasks that agents can handle.

A/B testing, side-by-side comparison, and preference ranking for AI outputs.

Classifying AI failures — hallucination, refusal, irrelevance, tone mismatch, latency.

Adapting Nielsen's heuristics and new AI-specific heuristics for AI interfaces.

Tracking AI product quality over time — drift, degradation, and improvement.

Defining what "good" looks like for AI outputs — accuracy, relevance, helpfulness.