robbond
97e4f3029e
experiment: archive historical project documents
2026-08-06 14:24:52 +01:00
robbond
61c8a3adbd
experiment: create current project state entry point
2026-08-06 14:06:20 +01:00
robbond
fd59845231
experiment(15): specify facilitator behaviour — behavioural model for Phase 5
...
- Create docs/facilitator-behaviour.md: behavioural specification of the
Confidence Engine with 14 identified behaviours (Orient, Acknowledge,
Observe pattern, Clarify, Validate, Connect, Challenge assumption, Refine
understanding, Expose uncertainty, Decide direction, Know when to pause,
Avoid premature closure, Communicate confidence honestly, Progressively
narrow focus).
- Update docs/design-evolution-log.md: add Experiment 15 entry documenting
what Experiment 14 proved, what emerged (the gap is behavioural not visual),
and why the next phase focuses on conversation behaviour over UI.
- Update .claude/ux-guidelines.md: add Facilitator Behaviour section with
core behavioural principles, anti-patterns, state-aware selection criteria,
and architecture relationship.
No code changes — this is a behavioural specification for future implementation.
2026-08-05 16:02:32 +01:00
robbond
863a4589b3
architecture: introduce investigation narrative layer
2026-08-05 15:53:22 +01:00
robbond
6eaf0fc246
experiment: improve semantic graph projection
...
Experiment 13 — Semantic Facilitator Translation
- Classify nodes by semantic role (observation, question, explanation,
scaffolding, relationship) rather than graph kind. Scaffolding suppressed
entirely before section routing.
- Three-tier filtering: scaffolding patterns > internal vocabulary > technical
summary patterns. Prevents structural noise from contaminating user-facing
sections.
- Deduplicate by normalised text — merge duplicate observations expressing the
same finding.
- Route resolved unknowns and assumptions to known section with epistemic
labels instead of treating them as unresolved questions.
- Prefer concrete observations (numbers, change language, temporal refs) over
abstract labels in ranking.
- Closed Experiment 12 as confirmed. Added Experiment 13 documentation.
- Updated UX guidelines with Semantic Projection principles.
- 37 tests: filtering, classification, deduplication, ranking, framing, mock
data integration, edge cases.
2026-08-05 15:26:29 +01:00
robbond
1998b84ae1
experiment: facilitator view from reasoning graph
2026-08-05 15:00:42 +01:00
robbond
ebea15c970
experiment: facilitator progress panel (Version B)
2026-08-05 14:37:43 +01:00
robbond
54acf0d565
experiment: stabilise conversation and reference lanes
2026-08-05 13:24:04 +01:00
robbond
8e96907209
experiment: improve investigation rhythm
2026-08-05 13:16:04 +01:00
robbond
7e18d0b53f
experiment: align investigation response input
2026-08-05 13:03:15 +01:00
robbond
1cf71d6ce2
experiment: reduce initial observation input
2026-08-05 12:51:48 +01:00
robbond
46f2d12726
exp(06): focused investigation — visual hierarchy without layout changes
...
Emphasise the active investigation card through stronger elevation,
clearer borders, and improved spacing. Quiet supporting panels by
reducing border opacity, softening heading weight, and lowering
text contrast — making them available without competing for attention.
Facilitator card receives a warm surface tint to read as a briefing
card rather than a generic panel.
Documentation: close experiment 05 with findings, add experiment 06
to the design evolution log, add Attention Hierarchy to UX guidelines,
defer dark mode to a future Investigation Mode experiment.
Presentation changes only — no reasoning, prompts, graph, API, or
backend modifications.
2026-08-05 12:41:13 +01:00
robbond
d1e6c2e032
experiment: facilitator panel beside workspace (Exp 05)
...
- Replace stacked landing with responsive two-column layout
- Left panel (1/3 desktop): facilitator intro card with dismiss checkbox
- Right panel (2/3 desktop): Tell me what's happening textarea + Analyse
- Mobile/tablet stack vertically as before
- 'Don't show' uses sessionStorage; future: user profile settings
- Close Exp 04 (Partially confirmed) in evolution log
- Add Exp 05 entry + Facilitator Behaviour UX section
2026-08-05 12:25:44 +01:00
robbond
048f31f43b
experiment: replace landing with workshop introduction
...
- Added Welcome card (Before we begin) to idle state
- Reduced textarea from 10 to 6 rows
- Added reassurance text below Analyse button
- Removed redundant empty-state placeholder
- Closed Experiment 03 (Partially confirmed) in evolution log
- Added Experiment 04: Facilitated Workshop Introduction
- Added Entry Experience section to UX guidelines
2026-08-05 12:14:30 +01:00
robbond
cf05c969bf
feat: begin responsive workspace layout
2026-08-05 10:51:44 +01:00
robbond
2f87cca88d
style: polish investigation workspace
...
- Summary panel: hide meaningless metrics (questions answered/remaining) until genuinely in progress; remove placeholder timestamps
- Understanding card: increased visual importance via larger heading, lighter border, more padding
- History section: reduced labels to brief forms ('History', 'Situation'), removed uppercase decorative labels from headings
- Investigation Map Preview: lighter borders, muted text, subtle background to signal provisional state
- Turn history cards: removed redundant subheadings ('Your answer', 'What changed') and divider lines
- Button label: 'Update situation' → 'Update'; padding consistent with design tokens
- Condition clarity fix: '!hasSelectedQuestion === false' → 'hasSelectedQuestion'
- Workspace polish section added to UX guidelines
2026-08-05 10:30:22 +01:00
robbond
61210c1200
fix: localise update reasoning state
2026-08-05 08:36:18 +01:00
robbond
6d11c1d503
fix: unify reasoning mode across submissions
2026-08-05 08:27:22 +01:00
robbond
437152086b
updated context documents
2026-08-04 17:33:51 +01:00
robbond
3a83944006
fix: set update loading state before request
2026-08-03 19:01:04 +01:00
robbond
7bc1c93486
feat: evolve investigation into guided conversation
2026-08-03 17:01:04 +01:00
robbond
e2960853ba
added claude context files
2026-08-03 15:51:46 +01:00