Welcome back

Pick a workspace to get started.

✓

Tasks

Review and validate invoices flagged for human-in-the-loop. Claim a pending task, verify the extracted fields against the source PDF, and submit.

Open Tasks →

🔒 No access — contact your administrator

🔍

Inspector

Trace how incoming emails and their attachments moved through the extraction pipeline. Drill into invoices, and per-stage status.

Open Inspector →

🔒 No access — contact your administrator

Drag & resize, then “Copy layout JSON” to set the server default.

Your review queue · live

Awaiting review LIVE

—

across all workforces

Completed work · per hour by workforce (72h) DATA LAKE

human reviews completed (a2i submission_time) by workforce · last 72h

Review backlog by workforce

Review onPhase Team LIVE

—

Review by Crowd Sourcing LIVE

—

Review by Partner LIVE

—

Processed Invoices

Invoices Processed DATA LAKE

—

in range

/analytics/summary · COUNT(*)

Touchless rate DATA LAKE

—

requires_validation=false ÷ bypass_a2i=false (A2I-eligible)

/analytics/summary

Avg time to inbox (touchless) DATA LAKE

—

date_received → date_completed

/analytics/summary · touchless only

Exception rate DATA LAKE

—

Declined / Stopped

exception.code IS NOT NULL

Total invoice value processed DATA LAKE

—

SUM(TOTAL.value)

/analytics/summary · SUM(TOTAL.value)

Invoices per day DATA LAKE

Automation & quality

Stopped for human review · weekly DATA LAKE

requires_validation=true AND bypass_a2i=false · weekly · selected range

Validation method DATA LAKE

group by validation_method

Avg fields edited / reviewed invoice DATA LAKE

—

reviewed invoices only

AVG(num_fields_edited)

Avg confidence DATA LAKE

—

AVG(confidence_score)

Most-edited fields DATA LAKE

UNNEST(a2i_edits.fields_edited)

Fields triggering review DATA LAKE

primary headers · validation_required among reviewed docs

Reviewer productivity

Review duration DATA LAKE

duration_seconds (avg / pctl)

Reviews per worker DATA LAKE

group by a2i_worker_email

Financial & business

Top vendors by spend DATA LAKE

SUM(TOTAL.value) by VENDOR_NAME

Top customers by volume DATA LAKE

group by customer_id

min_confidence tuning

Reviewed but unchanged — is min_confidence_score too high? DATA LAKE

—

of human-reviewed invoices had zero edits — review may be firing on docs the model already got right.

Customer	Reviewed	Zero-edit	Zero-edit %	min_confidence_score

Sorted by zero-edit % — high % + high threshold = candidates to lower the threshold.

reviewed AND num_fields_edited=0, by customer + min_confidence_score

Invoice volume

Invoice volume per week DATA LAKE

COUNT(*) by week · global + top 10 mailboxes · selected range (excl. current week)

ℹ️ Analytics widgets run live queries against the permanent data lake (final_json). Each group streams in behind a skeleton; a slow query never blocks the live queue.