Feature. The Evidence Orchestrator
Recommended Clips For Attorney Review. A Prioritized Triage Queue.
The prioritized attorney-review surface inside The Evidence Orchestrator. The recommendation layer derives clips from investigative flags, exhibit candidates, and dense-citation minute windows across the matter’s reviewed record of what the State produced in discovery. Each clip carries a severity, a reason, and a click-to-seek timestamp into the source media. Severity-sorted. Source-anchored. Built for the lead attorney’s final pass.
AI On This Page
Buddy Proposes Clips From The Canonical Recording, Ready For Approval.
Buddy is The IMC Machine’s AI assistant. Talk, upload, or speak – Buddy turns what you send into structured records you approve before anything moves.
Talk To Buddy
“Suggest Five Highlight Clips Under Thirty Seconds From Tonight”
Buddy proposes ranked clips with reasons, ready for the team to approve before publication.
Upload A Photo
Drop A Brand Kit (Logo, Font, Color Palette).
Buddy formats every clip to the brand’s caption template and color spec.
Voice Note
Voice The Day’s Narrative Angle.
Buddy reranks the clips so the ones that fit your angle surface first.
Buddy autofills are reviewable. Nothing publishes, files, or sends without a named human approval on the record.
A position the platform holds
The Evidence Orchestrator Does Not Summarize A File.
Summary is the easy product. A model reads a transcript and produces three paragraphs of prose claiming to describe what the file contains. The summary then sits in the matter folder, plausible and unverifiable, between the attorney and the source. The first time a witness or a juror or an appellate panel asks where a specific claim came from, the summary cannot answer. The model that wrote it is gone. The attorney is left re-doing the review they thought the summary had spared them. The Orchestrator converts the file into a different artifact: transcript density, citation density, severity flags, exhibit candidates, worksheet answers. Each of those is computed from the file itself and tied to a specific timestamp range. The output is not a paragraph about the file. It is a list of source moments. Each one clickable into the playhead, each one defensible in front of a judge.
Where the clips come from
Three Input Streams. One Severity-Ranked Queue.
Stream 01
Investigative Flags
Worksheet answers that raised a substantive concern. A missing Miranda element, an officer-attribution discrepancy, a search-and-seizure boundary, a chain-of-custody gap, a contradiction between two recorded statements. Each flag carries a severity (low, medium, high) and a source timestamp. High-severity flags surface near the top of the clip queue by default.
Stream 02
Exhibit Candidates
Moments the reviewer marked as candidates for use as exhibits. The photograph that shows the scene the report describes, the body-camera segment that captures the command the officer issued, the 911 audio moment that anchors the timeline. Exhibit candidates carry the reviewer’s note about why they nominated the moment, so the attorney is not guessing.
Stream 03
Dense-Citation Minute Windows
Minute windows where the reviewer’s citations cluster. The moments the worksheet kept returning to. Dense-citation windows often indicate the segments where the most was happening in the file. Rapid command sequences, multiple participants speaking, the actual point of contact. The clip queue surfaces these even if no individual flag was high-severity, because density itself is signal.
Click-to-seek, always
Every Clip Is A Source Moment, Not A Paragraph.
The clip queue lives in the right tools rail of the Cockpit, next to the AI Worksheet Panel. Click a clip and the media player in the center canvas seeks to the cited start time. The transcript scrolls to the segment. The five Cockpit gauges reposition to that moment. The worksheet question associated with the flag is highlighted in the Panel. There is no “open the source somewhere else” step. The source is right there. The clip queue carries, per clip: start time, end time, reason, priority, escalation status, export status, the transcript-driven candidate, and any attorney-review flag raised on the moment. The attorney’s verification pass is anchored to the source evidence, not to AI prose.
Downstream
The Clip Queue Is The Bridge To The Dismissal Engine.
The Distinguishing Posture
The Dismissal Engine reads the reviewed evidentiary record. When it evaluates a dismissal pathway (Miranda defective waiver, warrantless search, Brady disclosure, Article 39.14 deadline, probable-cause deficient), it cites back into the clip queue’s moments. A pathway citation in a draft motion is, in turn, a click-to-seek into the source media. Most legal-AI products read PDFs. The Dismissal Engine reads a record assembled from body-camera transcripts, 911 audio transcripts, interview transcripts, OCR’d handwritten reports, photograph flags, document citations, and severity-coded worksheet answers.
AI Proposes; The Attorney Decides
The Recommended Clips queue is a proposal. A prioritized triage list with reasoning the attorney can verify by clicking into the source. The attorney accepts, rejects, or re-prioritizes any clip in the queue. Nothing The Dismissal Engine prepares downstream proceeds without the attorney’s approval, and nothing files automatically.
Private Investigators Use It Too
A PI agency on a multi-day surveillance engagement, or working a witness-interview series for an attorney-client, uses the same prioritization surface to point the attorney to the moments most worth their attention. The platform helps PIs document and organize what their work captured. The legal interpretation of the work product is for the attorney-client.
The First Thirty Minutes
The attorney’s first thirty minutes on a body-camera file ought to be spent on the moments most worth their attention. The clip queue is the surface that decides what those moments are. The attorney decides what to do about them.
See it on a live shape
A Thirty-Minute Walkthrough On Your Matter.
Bring a current felony’s body-camera and audio mix. We will show you what the prioritized clip queue looks like across the matter, why each clip was surfaced, and how the click-to-seek into the source moment behaves under the playhead.
Why This Matters
A Clip Is A Candidate Until The Attorney Approves It.
A single matter can carry hours of body-camera, dash-camera, and interview-room video. No defense attorney can scrub all of it at the pace a caseload demands. The Recommended Clips queue replaces midnight scrubbing with a prioritized triage of clip candidates, each with a timecode, a plain-language rationale, and a link back to the source file, surfaced for the attorney to review. The clip is a candidate the platform proposes; the decision that it matters stays with the attorney.
Sources
Where The Numbers Came From.
Sources and citations
- National Endowment for the Arts, 2025 Arts & Cultural Production Satellite Account release.
- National Independent Venue Association, State of Live (2024 / 2025); Pollstar coverage; Billboard.
- Texas Commission on the Arts; Americans for the Arts / Texas Arts Action Fund 2024 fact sheet; Fort Worth Report.
- The Broadway League, 2024 to 25 End-of-Season Statistics; Demographics of the Broadway Audience 2024 to 2025 (PDF).
- Spotify Newsroom, “How the Music Industry’s Cultural and Financial Impact Define Its Success in 2025.” (Loud & Clear data on independent artist payouts.)
- Side Door, Touring By The Numbers; Octiive, The Independent Music Market.
- National Endowment for the Arts, Indicator A.5: Labor Market Status of Artists and Cultural Workers (2025).
- Global Insight Services, Music Event Market Report; Berkeley Business Review on festival economics.
- Austin Monitor on SXSW’s 2024 economic impact; The Daily Texan.
Learn This Product
