Product · Artifact Extraction

Seven artifact types. One evidence chain each.

A summary forgets. An artifact doesn’t. Citesvue extracts seven structured artifact types from every recording - each severity-graded, speaker-attributed, and carrying the quote, timestamp, and frame that produced it.

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

Five required fields, always populated. Two optional enrichments.

Quote

Verbatim words that triggered the artifact.

Speaker

Attributed segment-by-segment.

Timestamp

Click-to-jump in the recording.

Frame

Screen state at that moment.

Classification

Type, severity, structured sub-fields.

Two optional enrichments: suggested reproduction steps for bugs and suggested owner for action items - both labelled as suggestions, never asserted as fact.

Pipeline

How extraction actually works.

Transcript segments are scored against artifact-type signatures. Candidates are cross-checked against the visual layer - a bug candidate without an on-screen UI signal is downgraded; a decision candidate corroborated by screen context is promoted.

Severity is inferred from lexical and paralinguistic cues, then surfaced in the review queue for human override. The model is opinionated; the workflow is not.

The review queue

Extraction is a draft, not a verdict.

Every artifact lands in a review queue where a teammate can approve, reject, edit, merge duplicates, or reassign type. Reviewed artifacts build a per-workspace signal that sharpens extraction over time. Nothing ships externally until reviewed - unless the workspace explicitly opts into auto-push.

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 queue, adjusts severity on 1 bug, assigns owners to 5 actions, 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 exposes the reasoning signal that produced it - the phrase that triggered Critical, the screen context that corroborated it, the confidence score. Reviewers can override; overrides feed workspace-level calibration. Severity is auditable.

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 + reproduction
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, or straight into your own Google Sheets and Docs. A public API is on the roadmap.
  • Yes, with the caveat that visual grounding (frames, OCR, on-screen evidence) is unavailable for those artifacts.
  • 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.