Build Your Exhibit List From Real Evidence, Not From Memory
Evidence Copilot's Exhibit List Builder drafts a grounded exhibit list tied to actual files in your case — bodycam, jail calls, 911 audio, police reports — with every entry citable down to the exact second or page.
The Exhibit List Problem Every Defense Team Knows
- Exhibit lists stall while bodycam, jail calls, and 911 audio pile up unreviewed — Discovery dumps keep growing — bodycam video, interrogation footage, jail calls, 911 recordings, scanned police reports — and reviewing them eats the hours you need for pretrial preparation. Defense teams juggling growing volumes of digital video submissions routinely run out of time before the exhibit list is ever finished. Files arrive named X13qrt9__x3455, transcripts don't exist, and the exhibit list gets built from memory the night before the hearing — which is exactly how report-vs-bodycam inconsistencies slip through and how an exhibit list built in a rush becomes a symptom of the broader pretrial-prep gap.
- Excessive caseloads and underfunding leave exhibit prep unfinished — and it shows — Excessive caseloads and lack of funding prevent full pretrial preparation, and inadequate legal defense was a contributing factor in roughly 1 in 5 wrongful conviction cases, according to the Exoneration Project. Under the Strickland standard, a rushed or incomplete exhibit list isn't just sloppy — it's the kind of record that supports an ineffective assistance of counsel claim. When your exhibit list is built from recollection instead of citations into the actual discovery documents, exculpatory evidence and impeachment material end up missing from the record.
- Relying on paper discovery and lab reports without hands-on inspection hides the inconsistencies your exhibit list should surface — Working from paper discovery and lab reports without hands-on inspection of the underlying media means missing contamination, storage flaws, and the discrepancies between the police report and the bodycam — the exact material your exhibit list should surface for motions to suppress and cross-examination. A scanned report with no text layer can't be searched, a 911 call can't be quoted to the second, and chain-of-custody questions go unasked because nobody had time to pull the original files.
Why Defense Teams <span class="gradient">Trust Evidence Copilot</span> for Exhibit Prep
- Every exhibit entry is grounded — Every exhibit entry is grounded in a citation. The Exhibit List Builder drafts an exhibit list tied to the real files in the case — the bodycam video, the report PDF, the jail call audio — and every AI answer cites the exact source moment it came from: the precise second of video or page of the PDF. Your exhibit list is built on citations, not recollection, and nothing is ever auto-applied without attorney review. AI output is always marked for human review; the product never makes legal conclusions.
- Faster discovery review under heavy caseloads — Faster discovery review under heavy caseloads. Upload the discovery dump — up to 2 GB per file by web or email — and get timestamped, diarized transcripts, OCR'd text from scanned PDFs and photo exhibits, and auto-signals that compare every new file against earlier evidence in the case, surfacing candidate inconsistencies like report-vs-bodycam or statement-vs-jail-call before anyone asks. That compresses the review that used to eat your prep time, even when caseloads don't shrink.
- Originals stay immutable, actions are audited — Originals stay immutable and every action is audited. Every redaction — frame-accurate video, word-level audio, image, or PDF — produces a new derived file; originals are never touched and every action is audited. When you turn over redacted discovery or pack exhibits for hearing, the exhibit pack export (zip of clips, still frames, and quoted excerpts with a MANIFEST.md citation index) supports the chain-of-custody discipline defense teams need.
What's included
- Exhibit List Builder playbook: a draft exhibit list tied to real files in your case, ready for attorney review — no more rebuilding the list from memory at 11 pm.
- Timestamped diarized transcripts: Deepgram Nova with speaker diarization and word-level timestamps, plus one-click speaker renaming that propagates across every segment.
- OCR for scans and photos: police report PDFs with no text layer and photo evidence like receipts and screenshots become searchable, citable text with bounding boxes kept for redaction.
- Auto-signals on ingest: every new file is compared against earlier evidence, surfacing candidate inconsistencies — report vs bodycam, statement vs call audio — as unreviewed signals.
- Grounded AI evidence agent: full-text search across transcripts and documents that answers with clickable citations into the exact second of video or page of the PDF.
- Exhibit pack export: a zip of video clips, still frames, and quoted excerpts plus a MANIFEST.md citation index, gated by per-member export permission.
Quick wins
- Run the Suppression Motion Prep playbook before the hearing: it sweeps consent, search scope, stop duration, K-9, and Miranda issues and drafts a motion outline with both sides quoted and cited — turning the same reviewed evidence into your suppression exhibits.
- Use the two-way email intake ([email protected]) so investigators and co-counsel can drop discovery attachments into the case from the field — new files are transcribed, OCR'd, and compared against earlier evidence automatically.
How it works
- Upload the discovery dump — Drag in bodycam, interrogation footage, jail calls, 911 audio, police reports, photos, and scans — up to 2 GB per file by web upload or email attachment. Each case gets its own inbound email address for intake.
- Run the Exhibit List Builder playbook — Transcripts with word-level timestamps and OCR'd document text land in the workspace. Open the Exhibit List Builder and get a draft exhibit list tied to the real files, with auto-signals flagging inconsistencies as you go.
- Review, cite, and export — Edit the draft with attorney judgment, then export the exhibit pack — video clips, still frames, quoted excerpts, and a MANIFEST.md citation index — gated by per-member export permission.
How Evidence Copilot <span class="gradient">Builds Your Exhibit List</span> From the Evidence Itself
- The Exhibit List Builder playbook drafts an exhibit list tied to real files in your case — not a blank template you fill in by memory.
- Timestamped, diarized transcripts and OCR'd document text mean every exhibit entry can cite the exact video second or PDF page it came from.
- Auto-signals on ingest surface report-vs-bodycam and statement-vs-call-audio inconsistencies before anyone asks, so key impeachment exhibits make the list.
Why we're different
- Exhibit List Builder drafts from real files, not blank templates.
- Every AI answer cites the exact video second or PDF page.
- Defense-only by design — never sold to prosecution or law enforcement.
- Auto-signals surface report-vs-bodycam inconsistencies before you ask.
- Originals are immutable; every redaction is an audited derived file.
- Published pricing with no feature tiers — every plan includes the full workspace.
- MCP integration lets you query cases from Claude Desktop or Claude Code.
- Overage is hard-capped at 3x included hours, so runaway intake can't overbill.
Built for US criminal-defense attorneys, law clerks, investigators, and public-defender offices — defense-only by design, with published pricing and no sales wall.
What clients say
Discovery came in as forty bodycam files with garbage filenames and a scanned report with no text layer. The Exhibit List Builder gave me a draft tied to the actual files in the case, with OCR making the report searchable. I edited it in twenty minutes instead of rebuilding it from memory over a weekend.
— Marcus Delgado
The auto-signals flagged a jail call that contradicted the officer's report before I even went looking. That inconsistency is now exhibit number four on my list, with a citation to the exact minute of the call — and it's already drafted into a cross-exam question tied to both quotes.
— Priya Raghavan
Our investigators email discovery straight into the case and the transcripts and OCR come back searchable. When the exhibit list draft comes back, every line points to a real file — our law clerks just verify the citations and finalize. The exhibit pack export even ships with a manifest index, so turnover is clean.
— Tom Whitaker
Frequently asked questions
How does the Exhibit List Builder handle a discovery dump with 40 hours of bodycam?
Upload the files — up to 2 GB each by web or email attachment — and the workspace transcribes them with speaker diarization and word-level timestamps. The Exhibit List Builder then drafts an exhibit list tied to the real files, and auto-signals flag inconsistencies like report-vs-bodycam so key exhibits surface. You review and edit; nothing is finalized without attorney judgment.
Can I cite a specific moment of bodycam footage in my exhibit list?
Yes. Every AI answer carries citations that seek the exact video moment or page of the PDF, backed by word-level timestamps. When you export, the exhibit pack includes a MANIFEST.md citation index tying each clip, still frame, and quoted excerpt back to its source.
Does using AI to draft an exhibit list create ethics problems?
Every AI output in Evidence Copilot is marked AI-generated and pending human review, and the product never makes legal conclusions. Cross-exam drafts are suggested questions only, tied to quoted sources, with no credibility conclusions. You stay the reviewer of record — the tool drafts, you decide.
How fast can my team get from discovery upload to a draft exhibit list?
Most teams upload the discovery dump the same day they get it and run the Exhibit List Builder playbook once transcription and OCR complete. Media processing hours are included in every plan — 15 on Solo, 60 on Firm with priority queue, 100 per attorney on the PD Office plan — so throughput scales with your intake.
How is this different from JusticeText or just running Whisper and NotebookLM myself?
JusticeText is transcription-focused with no published G2 presence, and the DIY Whisper-plus-NotebookLM stack breaks at case scale — no diarization QC, no citations, no redaction, no audit trail. Evidence Copilot is a grounded review workspace: transcripts, OCR, auto-signals, redaction with immutable originals, the Exhibit List Builder, and exhibit pack exports, with published pricing starting at $39/user/mo and a PD Office tier at $750/attorney/yr that undercuts JusticeText by roughly
Book a 20-minute walkthrough at evidencecopilot.com/book, or start on the Solo plan at $39/user/mo at evidencecopilot.com/signup.