{{ dashKicker }}
{{ dashTitle }}
Updated {{ updatedAt }}
! ALERT
{{ alertText }}
Review {{ alertCount }} operators
{{ heroLabel }}
{{ heroBody }}
{{ v.label }}
{{ v.delta }}
{{ v.score }}
{{ v.spark }}
{{ c.tag }}
{{ c.initials }}
{{ c.name }}
{{ c.role }}
{{ c.value }}
{{ c.valueSub }}
Side-by-side comparison
Clear ×
{{ ce.name }}
{{ ce.role }} · {{ ce.dept }}
{{ cv.label }}
{{ cv.score }}
Overall
{{ ce.overall }}
{{ tableTitle }}
{{ tableMeta }}
{{ filteredCount }} operators
{{ col.label }}
{{ r.chkCell }}
{{ r.rank }}
{{ r.initials }}
{{ r.dept }}
{{ r.role }}
{{ r.overallCell }}
{{ r.v1 }}
{{ r.v2 }}
{{ r.v3 }}
{{ r.v4 }}
{{ r.trendCell }}
{{ empInitials }}
{{ empName }}
{{ empRole }}
{{ empDept }}
{{ empStatus }}
{{ empOverall }}
CueBench Score
30-day change
{{ empDelta }}
Sessions scored
{{ empSessionsCount }}
30-day score history
{{ empDelta }} pts
{{ empHistory }}
{{ v.label }}ⓘ{{ v.def }}
Part of Anthropic's AI Fluency Framework — anthropic.com/ai-fluency
Part of Anthropic's AI Fluency Framework — anthropic.com/ai-fluency
{{ v.score }}
Strengths
{{ s.label }}
{{ s.note }}
Where to Coach
{{ s.label }}
{{ s.note }}
Behavioral signals
{{ sig.mark }}
{{ sig.text }}
Task performance
{{ tp.category }}
{{ tp.avg }}
Coaching plan
{{ cp.action }}
{{ cp.why }}
Manager notes
Private · not visible to employee
{{ noteSavedLabel }}
Recent sessions
Session
Task
Duration
Tokens
Cost
Score
Flags
{{ s.id }}
{{ s.when }}
{{ s.type }}
{{ s.duration }}
{{ s.tokens }}
{{ s.cost }}
{{ s.score }}
{{ s.flagCell }}
{{ showAllSessLabel }}
{{ sessInitials }}
{{ sessId }}
Scored
{{ sessTask }}
{{ sessEmployee }}
{{ sessModel }}
{{ sessDate }}
{{ sessScore }}
Session Score
Interaction trace
{{ ev.t }}
{{ ev.glyph }}
{{ ev.label }}
{{ ev.detail }}
Score breakdown
{{ b.label }}
{{ b.score }}
Cost breakdown
{{ c.label }}
{{ c.value }}
Session cost
{{ sessDollars }}
{{ sessModel }}
input + tool + output tokens
input + tool + output tokens
Time to resolve
{{ sessTime }}
Checklist breakdown
CheckEval, binary scoring per dimension
{{ g.chev }}
{{ g.label }}
{{ g.pass }}/{{ g.total }}
{{ g.score }}
{{ it.mark }}
{{ it.q }}
AI Insights
Generated from session transcript
Task performance breakdown
{{ tb.category }}
{{ tb.score }}
{{ tb.note }}
Coaching plan
→
{{ cp }}
Behavioral signals
{{ sig.mark }}
{{ sig.text }}
Configuration
Settings
Organization
Organization name
{{ orgName }}
Department
{{ orgDept }}
Total operators tracked
{{ orgOperators }}
Scoring
Scoring model
gpt-4o
Proficiency threshold
70
Active vectors
✓Delegation
✓Description
✓Discernment
✓Diligence
Alert thresholds
Flag operators scoring below
Currently flagging {{ alertCount }} operator(s)
Integrations
Claude Code Stop Hook
Automatic session capture on agent stop
Webhook endpoint
POST /api/session
AI Insights
AI-generated task breakdowns, coaching plans & behavioral signals per session
LLM API key
Model
{{ insightsSaveLabel }}
Your key is stored in the org config and sent to the scorer backend. It is used only to generate per-session insights when opted in. Use an Anthropic key for Claude models or an OpenAI key for GPT models.
AI-generated · Jun 22, 2026
Reports & Insights
{{ rt.label }}
Executive summary
{{ reportSummary }}
Team score distribution
{{ reportChart }}
{{ rs.value }}
{{ rs.label }}
{{ reportMainTitle }}
{{ ri.title }}
{{ ri.value }}
{{ ri.note }}
Recommendations
{{ rr.urgency }}
{{ rr.action }}
{{ rr.rationale }}