Updated {{ updatedAt }}

{{ ac.value }}

Cost & efficiency

{{ costTotal }}

Total spend

{{ costAvg }}

Avg per session

Model usage

{{ mr.count }}

No session data yet — cost metrics will appear once sessions are recorded.

Risk signals

Sessions with loops

of total sessions flagged

Below threshold

developers below {{ alertBelow }}-point target

Review developers →

{{ c.initials }}

{{ c.value }}

People & Skills

Developers

Updated {{ updatedAt }}

! ALERT {{ alertText }} Review {{ alertCount }} developers

Side-by-side comparison

Clear ×

{{ ce.role }} · {{ ce.dept }}

{{ cv.score }}

Overall

{{ ce.overall }}

{{ tableMeta }}

{{ filteredCount }} developers

{{ r.rank }}

{{ r.initials }}

{{ r.v1 }}

{{ r.v2 }}

{{ r.v3 }}

{{ r.v4 }}

Drop in a session — get scored

Drag & drop Claude Code / Codex / Pi session logs (.jsonl), or click to browse. Scored in seconds; your file is deleted right after.

{{ empInitials }}

CueBench Score

30-day change

{{ empDelta }}

Sessions scored

{{ empSessionsCount }}

Anthropic AI Fluency Framework ↗

{{ empDelta }} pts

{{ v.label }}ⓘ{{ v.def }}

Part of Anthropic's AI Fluency Framework — anthropic.com/ai-fluency

{{ v.score }}

Strengths

Where to Coach

No session data — insights will appear once sessions are recorded.

Generating insights…

Behavioral signals

View session →

Task performance

{{ tp.avg }}

{{ tp.avg }}

Coaching plan

Task breakdown {{ empTaskPerfExpandLabel }}

{{ tp.avg }}

Recent sessions

{{ s.id }}

{{ s.duration }}

{{ s.tokens }}

{{ s.cost }}

{{ sessInitials }}

{{ sessQualityLabel }} ⓘ {{ sessQualityDef }}

{{ sessDate }} ◎ Walk through with your coach →

Session Score

                    specificity {{ sessSpecificity }}
                    ⓘ
                    Specificity measures how clearly and concretely you described what you wanted. High specificity means precise, actionable prompts that name the file, the behavior, and the acceptance condition (e.g. "return 404 instead of 500 when the record id is missing"). Low specificity means vague requests that leave the agent to guess (e.g. "fix it", "make it better").
                  

Session story

◎ Walk through →

{{ storySpan }} · active {{ storyActive }} · away {{ storyIdle }}

Turn a ✗ into this week's challenge →

+{{ ph.t }}

{{ ph.chips }}

“{{ ph.ask }}”

Files {{ ph.files }}

Activity {{ ph.activity }}

Interaction trace

{{ ev.t }}

{{ ev.glyph }}

⏸

{{ ev.label }}

Score breakdown

{{ b.label }}ⓘ{{ b.def }}

Part of Anthropic's AI Fluency Framework — anthropic.com/ai-fluency

{{ b.score }}

Cost breakdown

Session cost

Time to resolve

AI Insights

Per-axis coaching

Strengths

Areas to improve

Configuration

Settings

Account

Name

API key

Your API key identifies your personal workspace — the capture agent and any script can post sessions with it. Treat it like a password.

Connect permanently Optional

Skip manual uploads: a small agent watches your local session logs and sends each finished session automatically.

Run the CueBench capture agent with your API key:

# one-time setup — watches Claude Code, Cursor & Codex sessions (+ any file you put in ~/CueBench Drop)
curl -fsSL {{ agentInstallUrl }} | bash -s -- --key {{ orgApiKey }} --api {{ agentApiUrl }} --origin {{ agentOrigin }}

Uploading by hand works exactly the same — the agent is just the zero-effort version. It sends session logs only; scoring runs on our servers and files are deleted after scoring. To remove it later: bash ~/.cuebench/capture/uninstall.sh (asks for confirmation).

AI Insights

AI-generated task breakdowns, coaching plans & behavioral signals per session

Refresh every

days

Insights are generated by CueBench — no API key needed. They refresh on the cadence above; "Refresh now" regenerates immediately (limited to once every 5 minutes).

Your Coach

Level up, one session at a time

Focus challenge

{{ d.mark }}{{ d.tip }}

Your coach picks one measurable thing to improve — based on your weakest skill — and tracks it automatically across your next sessions.

Walk through a session

Step-by-step coaching on what happened and what to try instead.

Walk through →

No sessions yet — drop one on your dashboard to get started.

Ask your coach

Answers grounded in your real sessions — scores, traces, habits.

Try: “Why was my discernment low this week?” · “What should I do differently when the agent loops?” · “Which task types am I best at?”

{{ m.content }}

Coach is thinking…

Send

◉

No teams configured

Go to Settings → Teams to create your first team.

Teams

{{ tc.avgScore }}

{{ tv.score }}

← Teams

{{ teamDetailMemberCount }} members

{{ teamDetailScore }}

Team Avg

Team Strengths

{{ ts.score }}

Where to Coach

{{ tv.score }}

Behavioral Signals

Generating team insights…

No AI insights yet. Generate now

Task Performance

No session data yet.

{{ tp.score }}

{{ tp.score }}

Team Coaching Plan

Members

{{ tm.initials }}

{{ tm.overall }}

AI-generated · Jun 22, 2026

Reports & Insights

Executive summary

Team score distribution

30-day vector trends — org average

{{ rs.value }}

{{ ri.value }}

Recommendations

See how you're using AI — and level up.

Get your AI fluency score

{{ dashTitle }}

Developers

{{ empName }}

{{ sessTask }}

{{ teamDetailName }}

Hey {{ portalEmpFirstName }}.