feat: explore facilitated investigation workspace

Phase 4 UX exploration — workshop desk metaphor.

Workspace layout changes:
- Investigation Map promoted from preview to workspace artefact
- Understanding card given wider surface (lg:col-span-2)
- Grid shifts from equal-column to cognitive-weighted widths (lg:grid-cols-5)
- Mobile remains stacked; tablet simplifies naturally
- Desktop exploits wider working canvas

Layout structured by cognitive activity:
  Active workspace zone (Question + Response)
  Supporting workspace (Understanding, Map)
  Reference row (Situation, History)

components/investigation-map.jsx

@@ -84,10 +84,10 @@ export default function InvestigationMap({ turnCount = 0 }) {
   return (
     <div className="rounded-lg border border-gray-100 bg-gray-50/50 p-4" role="region" aria-label="Investigation map preview">
       <h2 className="mb-1 text-sm font-semibold tracking-tight text-gray-400">
-        Investigation Map Preview
+        Investigation Map
       </h2>
       <p className="mb-3 text-xs text-gray-400">
-        This preview shows where a future reasoning map may appear. Its final shape will emerge from the reasoning engine.
+        Active investigation topics and their status.
       </p>
 
       <div className="space-y-px border-t border-gray-100 pt-3" role="list" aria-label="Investigation topics">

components/reasoning-workspace.jsx

@@ -669,11 +669,23 @@ export default function ReasoningWorkspace({
           {/* Post-update acknowledgement — only after success, never during loading */}
           {updateStatus === "success" && !isUpdating && <UpdateAcknowledgement updateResult={result} />}
 
-          {/* ── Active workspace (left) + Working memory (right) ─────── */}
+          {/* ══════════════════════════════════════════════════════════
-          <div className="grid grid-cols-1 gap-6 md:grid-cols-2">
+              FACILITATED INVESTIGATION WORKSPACE — PHASE 4 EXPLORATION
-            {/* Left column — active workspace */}
+              ══════════════════════════════════════════════════════════
+
+              Layout metaphor: a workshop desk, not a document.
+
+              Desktop: wide work surfaces organised by cognitive activity.
+              Tablet: simplified two-zone layout.
+              Mobile: naturally stacked.
+              ══════════════════════════════════════════════════════════ */}
+
+          {hasSelectedQuestion ? (
+
+            <>
+              {/* ── Active workspace zone (Question + Response) ───────── */}
               <div className="space-y-6">
-              {/* ── Local update loading (always visible when updating) ─ */}
+
                 {isUpdating && (
                   <LoadingOverlay
                     isLoading={true}
@@ -683,7 +695,6 @@ export default function ReasoningWorkspace({
                   />
                 )}
 
-              {/* ── Response form — hidden during update loading ─ */}
                 {!isUpdating && canAnswer && (
                   <form onSubmit={handleUpdateCaptureAndSubmit} className="space-y-4 rounded-lg border border-gray-200 bg-white p-5">
                     <div>
@@ -715,27 +726,44 @@ export default function ReasoningWorkspace({
                   </form>
                 )}
 
-              {/* ── Terminal state: outcome card — hidden during update loading ─ */}
-              {!isUpdating && status === "success" && !hasSelectedQuestion && graph && genuineCompletion && (
-                <CompletionCard summary={resolveCurrentSummary(propUnderstanding || graph?.currentSummary || result?.updatedSituationGraph?.currentSummary)} />
-              )}
-              {!isUpdating && status === "success" && !hasSelectedQuestion && graph && !genuineCompletion && (
-                <EvidenceLimitCard summary={resolveCurrentSummary(propUnderstanding || graph?.currentSummary || result?.updatedSituationGraph?.currentSummary)} />
-              )}
-
               </div>
 
-            {/* Right column — working memory: Understanding + Map */}
+              {/* ── Supporting workspace (Understanding, Map, Situation) ─ */}
-            {hasSelectedQuestion && (
+              <div className="grid grid-cols-1 gap-6 lg:grid-cols-5">
-              <div className="space-y-6">
+
+                {/* Understanding — wider surface (2 cols) */}
                 {hasCurrentSummaryCondition && (
+                  <div className="lg:col-span-2">
                     <CurrentUnderstandingCard currentSummary={graph?.currentSummary || result?.updatedSituationGraph?.currentSummary} plainLanguage={propUnderstanding || null} />
+                  </div>
                 )}
+
+                {/* Investigation Map — workspace artefact (1.5 cols) */}
+                {hasSelectedQuestion && (
+                  <div className="lg:col-span-1">
                     <InvestigationMap turnCount={investigationHistory.length} />
                   </div>
                 )}
+
               </div>
 
+            </>
+
+          ) : status === "success" ? (
+
+            <>
+              {/* Terminal state */}
+              {genuineCompletion && (
+                <CompletionCard summary={resolveCurrentSummary(propUnderstanding || graph?.currentSummary || result?.updatedSituationGraph?.currentSummary)} />
+              )}
+              {!genuineCompletion && (
+                <EvidenceLimitCard summary={resolveCurrentSummary(propUnderstanding || graph?.currentSummary || result?.updatedSituationGraph?.currentSummary)} />
+              )}
+            </>
+
+          ) : null}
+
+
           {/* ── Reference row — Situation + History side-by-side on desktop ─ */}
           <div className="grid grid-cols-1 gap-6 md:grid-cols-2">
             <OriginalSituation scenario={scenario} centralStatement={graph?.centralStatement} />

docs/design-evolution-log.md

@@ -0,0 +1,92 @@
+# Design Evolution Log
+
+A chronological record of why significant design decisions were made. This is NOT a changelog. It records the product's evolution of thinking.
+
+---
+
+## Phase 1
+Simple conversational investigation
+
+Question → Answer interaction.
+
+Purpose:
+Prove the reasoning loop.
+
+Learning:
+Conversation alone does not provide sufficient context during longer investigations.
+
+---
+
+## Phase 2
+Persistent investigation notebook
+
+Added:
+
+- current understanding
+- original situation
+- investigation history
+
+Learning:
+Users need persistent context rather than remembering previous answers.
+
+---
+
+## Phase 3
+Document workspace
+
+Created a coherent workspace with:
+
+- investigation status
+- current investigation
+- response
+- understanding
+- investigation map placeholder
+- situation
+- history
+
+Learning:
+The interface became usable but still behaved like a document rather than a workspace.
+
+---
+
+## Phase 4 (Current Exploration)
+Facilitated Investigation Workshop
+
+Status:
+Experimental.
+
+Hypothesis:
+
+The Confidence Engine is not:
+
+- a chatbot
+- a dashboard
+- a form
+
+It is a facilitated investigation workspace.
+
+The interface should resemble the environment in which structured thinking happens.
+
+Record discoveries rather than conclusions.
+
+Leave room for future phases.
+
+---
+
+## Phase 4 — Guiding Principles
+
+The Confidence Engine is a workspace, not a document.
+
+People think in multiple directions simultaneously.
+
+Useful context should be visible together.
+
+The interface should favour thinking over scrolling.
+
+The workspace should feel like a large desk or workshop rather than a narrow report.
+
+The engine facilitates thinking.
+
+The user contributes evidence.
+
+The workspace captures shared understanding.