Map the current-state user journey
Assemble fragmented research into a current-state journey map while labelling evidence, operational context, and assumptions separately.
Why
The workflow problem
Research findings remain fragmented across channels, moments, actions, and emotions, while a polished AI timeline can introduce uncited activity or silently become a future-state solution.
AI can order cited observations into a draft chronology and surface missing transitions. Journey mapping remains an interpretive, cross-functional method; the trade-off is faster assembly against the risk of invented continuity.
Concrete output
What you will produce
A current-state journey map with actor, stages, actions, evidence, pain points, operational context, assumption labels, and opportunity notes.
How
Run the workflow
Set the actor and evidence boundary
The journey owner specifies one actor, one current-state objective, start and end boundaries, and a source pack with stable evidence IDs. Separate observed actions, reported feelings, operational facts, and assumptions before mapping.
Draft a cited chronology
Use AI to order only supplied evidence into possible stages and to flag missing transitions. Preserve competing sequences rather than forcing a single tidy path.
Arrange a current-state evidence timeline
Use only the supplied evidence pack to draft a current-state journey. Actor and objective: [insert] Start and end boundary: [insert] Evidence IDs, excerpts, and operational notes: [insert] Return: proposed stage | action or observation | evidence ID | confidence | operational dependency | gap or alternative sequence. Mark any inference as ASSUMPTION. Do not add emotions, touchpoints, or future-state improvements without supplied evidence.Correct the map with operational knowledge
Service, product, and frontline owners inspect the draft against real hand-offs, policies, and channels. Add operational context with its source, correct sequence errors, and keep gaps visible rather than resolving them by guesswork.
Validate assumptions and frame opportunities
The research lead plans targeted checks for assumption-labelled entries. Only after the current state is stable should the team add opportunity notes; do not redraw the map as a proposed future experience.
Human–AI partnership
Who contributes what
AI contribution
Evidence retrieval, provisional chronology drafting, and gap detection from the supplied source pack. It does not know the actual journey beyond that pack.
Human responsibility
Choose scope; distinguish evidence from assumption; provide operational truth; include relevant service perspectives; validate with users; and approve the map's use in decisions.
Stop rule
Stop AI use and return to research when any action, emotion, or stage is uncited; when alternative routes are collapsed without evidence; or when the map begins to contain future-state solutions.
Check before use
Watch out
A single journey can erase variation in access needs, channels, and exceptional routes. Make the actor definition explicit, show confidence and exclusions, and do not imply that service-owner knowledge is equivalent to user evidence.
Evidence base
What supports this workflow
Journey mapping is an established synthesis method supported by canonical design guidance. No direct harvested study tests the proposed AI chronology contribution, so this is a method-led design hypothesis that should be piloted against a human-built map.
- Sarah Gibbons · Journey Mapping 101
Provides established journey-map components and cautions that maps must be based on research rather than assumptions.
- IDEO.org · Journey Map
Supplies a canonical human-centered method reference for visualising an experience over time.
- Maddie Brown and Kate Moran · Accelerating Research with AI
Provides adjacent guidance that AI can draft research deliverables but requires human review for accuracy and relevance.