Skip to main content
The AI Pathway Builder proposes structural changes to a participant pathway as inline “ghost” suggestion cards — faded previews that appear in the pathway editor alongside your existing content. You accept, reject, or accept-and-continue each suggestion; the AI updates the underlying CRF version only on acceptance.

​
What It Does

Three AI tools are available when you are editing a CRF version (participant pathway): The AI decides which tool to call based on your prompt and the current state of the pathway. A typical flow is outline → detail-per-section → targeted edits to refine individual question groups.

​
Where It Runs

Open the AI Agent side panel anywhere in the study and ask the AI to help build or modify a pathway. For example: “Draft a pathway for a 12-week safety follow-up with screening, baseline, week 4, week 8, and end-of-study visits.” You don’t need to open a specific CRF version first:
  • If you are already viewing a CRF version, the AI edits that one by default.
  • If you aren’t, the AI looks for a Draft CRF version to edit. When there is exactly one draft, it uses that one; when there are several, it asks you which to use before making changes.
Suggestions render inline in the pathway editor — not in the chat panel — so open the CRF version when you’re ready to review them.
Only Draft CRF versions are editable. Testing, Approved, and Retired versions are locked, so suggestions cannot be applied to them — copy them as a new draft first. See Pathway Versioning.

​
Large Pathways

The AI reads pathways in chunks: first the outline (sections and a lightweight index of question groups), then the specific question groups it needs to inspect or edit. This means you can point it at a mature, multi-hundred-question pathway and ask for targeted edits — for example, “add a PHQ-9 to the Week 8 visit” — without truncation. Very large edits may take several tool steps. If the AI runs out of steps mid-task, it will pause and ask you to send a short follow-up like “continue”.

​
Ghost Suggestion Cards

Suggestions appear as dashed-border cards positioned where they will be inserted:
  • Green cards — new sections, question groups, or activities to add
  • Orange cards — edits to existing content, shown as a diff with added, removed, and unchanged lines highlighted
Each card carries three buttons: When suggestions are off-screen, a sticky “N suggestion(s) above/below” button appears in the editor so you can scroll to them.

​
Auto-Continuation

Accept and continue is the fastest way to build a pathway end-to-end: accept an outline, then let the AI populate each section one suggestion at a time, reviewing as you go. Behind the scenes the editor sends the AI a short “continue where you left off” prompt so you do not have to re-describe what you want on every step.

​
PDF-Driven Extraction

You can seed the AI with a protocol PDF:
1

Upload the Protocol

Upload the PDF to Study Documents.
2

Attach to the Chat

Open the AI Agent side panel in the pathway editor and attach the PDF.
3

Ask for a Pathway

Prompt the AI to draft a pathway based on the schedule of activities in the document.
4

Review Suggestions

The AI extracts the PDF contents (preserving tables, lists, and section structure) and proposes matching pathway structure as ghost cards.
Extracted PDF content is cached. Re-attaching the same document in a later conversation is instant.

​
Permissions

Using the AI Pathway Builder requires the Study AI Prompts permission. Roles that carry it by default:
  • Chief Coordinating Investigator
  • Deputy Coordinating Investigator
  • Study Administrator
Users without this permission still see the CRF version they are viewing, but the AI tools do not appear in their chat panel. If you ask the AI for something outside its current capabilities (for example, editing a study pathway or workflow), it drafts a feature request email to support@carelane.io that you can send in one click.

​
Best Practices

Ask for the outline first, review and adjust, then ask for section detail. It is easier to course-correct at the outline level than after a hundred questions are proposed.
Rejecting a bad suggestion teaches the AI faster than editing it post-acceptance. Use Reject generously.
Always build or refactor pathways inside a Draft CRF version. You can promote to Testing and then Approved when you are confident — see Pathway Versioning.
Attach the protocol PDF so the AI can ground suggestions in your actual study design rather than general clinical convention.

​
Limitations

  • AI Pathway Builder operates only on CRF versions (participant pathways), not study pathways or site workflows.
  • Suggestions are best-effort. Always review clinical logic (eligibility, conditional branching, scoring) before approving a version.
  • The AI cannot modify locked versions directly — Testing, Approved, and Retired CRF versions are immutable by design.

Pathway Versioning

Draft, Testing, Approved, and Retired lifecycle.

Conversational AI

The AI Agent side panel and model selection.