Product · Artifact Extraction

Seven artifact types. One evidence chain each.

A summary forgets. An artifact doesn’t. Citesvue extracts seven structured types from the transcript first - severity-graded, speaker-attributed, and carrying quote and timestamp. Optional visual evidence enriches those same artifacts with screen corroboration and frames.

Seven artifact types52:14 UAT · 24 detected
×2
Bug
critical
×3
Requirement
high
×4
Decision
info
×5
Risk
high
×2
Action
medium
×3
Question
info
×4
Insight
low
Taxonomy

The seven types, mapped.

One row per type. What triggers detection, the default severity model, and where the artifact tends to land.

Scroll to see every column →

Type
What triggers detection
Default severity
Typical destination
Bug
Observed failure or unexpected behaviour
Severity-graded
Jira · Linear
Requirement
Stated need or constraint
Severity-graded
Jira · Notion
Decision
Committed choice with rationale
Cited to the moment
Notion
Action item
Explicit assignment
Owner where stated
Jira · Linear · Slack
Risk
Flagged exposure or concern
Severity-graded
Notion · Slack
Question
Unresolved point
Cited to the moment
Notion · Slack
Insight
Something worth knowing that fits no other box
Cited to the moment
Notion · Webhook
Anatomy

Core fields first, visual fields when they exist.

Quote

Verbatim words that triggered the artifact.

Speaker

Attributed segment-by-segment.

Timestamp

Click-to-jump in the recording.

Frame

Added only after optional visual evidence provides real screen support.

Classification

Type, severity, structured sub-fields.

When a bug is visible on screen, the frame's OCR error text is carried into the artifact alongside the quote - the exact message the tester saw, not a paraphrase of it.

Pipeline

How extraction actually works.

Transcript segments are scored against artifact-type signatures and stable core artifacts become available with the recap. They do not wait for video analysis and are never deleted and recreated by a later visual pass.

When you request visual evidence, screen associations enrich the existing rows and genuinely new visual-only findings are added separately. IDs, review state, and pushed or exported state survive the enrichment.

The review queue

Extraction is a draft, not a verdict.

Every artifact lands in a review queue where a teammate can approve or reject it - individually or in bulk - and edit its title, description, and severity. Only approved findings can be pushed to your tools, and pushing the same finding again updates the existing issue instead of filing a duplicate.

Worked example

A 52-minute UAT, end-to-end.

Input

1 recording · 52 min · 3 participants

Output

4 bugs · 6 requirements · 3 decisions · 2 risks · 9 action items

Triage

PM reviews the queue, adjusts severity on 1 bug, approves the rest, pushes to Jira + Notion in under 4 minutes


The critical bug: a quote from the client at 31:08 about the export producing an empty CSV, paired with the frame showing the error toast, auto-classified critical based on the phrase “this is a blocker for us.”

Structure beats summary

Three lines that explain the difference.

  • A summary compresses.

    An artifact preserves.

  • A summary is one paragraph.

    Artifacts are seven structured tables.

  • A summary dies in a doc.

    Artifacts route into the systems where work happens.

Severity

Severity is a real object, not a vibe.

Every severity assignment is grounded in the evidence that produced it - the phrase that triggered Critical and the screen context that corroborated it stay attached to the artifact. Reviewers can override severity in place, and the evidence stays with the artifact wherever it is pushed.

Before / after

What artifact extraction actually changes.

UAT documentation time
Without Citesvue
2–4 hours of manual write-up per session
With Citesvue
Under 10 minutes of review
Bug report completeness
Without Citesvue
Screenshot disconnected from spoken context
With Citesvue
Quote + timestamp + frame + on-screen error text
Decision recovery
Without Citesvue
“Did we agree to that?” - nobody knows
With Citesvue
One queryable decision log per project
On the roadmap

Custom artifact types.

Workspaces will be able to define their own artifact types and extraction rules - for example a compliance obligation, customer commitment, or SLA breach. Tagged as coming, never promised by date.

Common questions

What enterprise buyers ask about extraction.

  • Extraction is a draft, not a verdict. The review workflow lets your team mark artifacts as reviewed before they get pushed or exported.
  • Yes - JSON, CSV, PDF, and Word export, including a one-click CSV of the findings catalogue. Connected Google Workspace destinations are available where enabled for your workspace. Citesvue does not currently provide a public API.
  • Yes, with the caveat that visual grounding (frames, OCR, on-screen evidence) is unavailable for those artifacts.
  • Existing artifact IDs, review state, and pushed or exported state are preserved. Citesvue adds visual corroboration where appropriate and creates a new visual-only finding only when the screen contributes something genuinely new.
  • Artifacts stay inside your workspace, scoped to your account at every query. Automated redaction policies are on the roadmap; today, review before push is the control.
Closing argument

Your next recording could be
your most
valuable asset.

Or it could sit in a Drive folder nobody opens again. The difference is whether it has citations attached.

  • SetupOne drag-and-drop upload, or send the notetaker. No plugins.
  • First insightCited Q&A on a 60-min recording in under 6 minutes.
  • Cancel anytimeFull data export, full right to erasure.