Back to Services

Turn a Discovery Dump into a Case File — Before You've Opened a Single File

Forward the bodycam, jail calls, and police reports by email and get a grounded, citable evidence workspace — transcripts, OCR, and an AI agent that answers with citations to the exact second.

The Discovery Dump Is Winning — and You're Paying for It in Billable Hours

  • Discovery arrives in fragments — every supplemental drop breaks your case file — Discovery doesn't arrive once — it trickles in for months. A bodycam drop on Tuesday, a supplemental incident report three weeks later, 911 audio forwarded by your investigator, then jail calls. Each file lands in a downloads folder, disconnected from everything you already reviewed for the preliminary hearing, so the inconsistency between the officer's report narrative and what the bodycam actually captured goes unnoticed until the prosecutor's witness takes the stand. With over 252,159 criminal defense lawyers competing in a $15 billion market, the defenders who catch report-vs-footage discrepancies first win the suppression motion and the plea leverage.
  • Manual evidence review is unbilled grunt work that eats motion-practice hours — Transcribing bodycam by hand, scrubbing interrogation footage for the Miranda moment, and OCR-ing scanned police reports with no text layer is clerical work no client is paying for under a flat fee arrangement. In a market where organic and paid search drive roughly 80% of criminal defense leads and 'DUI attorney' clicks run $100–$200+ each, every hour lost to transcription and re-scrubbing footage inflates your client acquisition cost and your revenue per case. Hours buried in scrubbing are hours not spent on the motion to suppress, Brady review, or cross-exam prep.
  • Intake friction starts before the case file exists — Criminal defense is time-sensitive — 61% of inbound inquiries come from a phone call, and prospects contact 2–5 firms before choosing. Arraignment is days away and the client is already comparing you against the other firms on Google. If your evidence workflow can't start the moment files arrive — including when an investigator forwards attachments from the scene — the case file lags the case, and the first client meeting happens before you've read a single page of the police report.

Why Defenders <span class="gradient">Choose Evidence Copilot</span> for Intake

  • Intake starts with a forward, not a project — Intake starts with a forward, not a project. Email the discovery dump — bodycam, scanned reports, 911 audio, jail calls — to the per-case inbound address and the workspace ingests everything: diarized transcripts with word-level timestamps, OCR'd text from scanned PDFs, and an evidence inventory. No upload marathons, no file-renaming rituals. Review starts the day discovery lands, even before your first client meeting.
  • Every answer points to the exact moment — Every answer points to the exact moment. Ask the AI evidence agent where the officer says consent was given and get back a citation that seeks the exact second of bodycam video or the exact page of the PDF. When you're prepping the motion to suppress or drafting cross-exam questions from a report-vs-bodycam inconsistency, you verify the source in one click instead of re-scrubbing forty hours of footage.
  • Ethics-first by design — Ethics-first by design. Every AI output is marked AI-generated and pending human review, and the product never makes legal conclusions. Cross-exam drafts are suggested questions only, each tied to a quoted source. Originals are immutable, redactions create derived files, and every action is audited — so your Brady and Giglio review workflow stays defensible and your discovery turnover stays clean.

What's included

  • Two-way email intake: [email protected] spins up a new case from the subject line and ingests every attachment; case+{id}@evidencecopilot.com accepts follow-on evidence and answers questions by email with citations and deep links.
  • Deepgram Nova transcription with speaker diarization and word-level timestamps — rename a speaker once and it propagates across every segment.
  • OCR turns scanned PDFs with no text layer and photo evidence — receipts, exhibits, screenshots — into searchable, citable text, with bounding boxes kept for redaction.
  • AI evidence agent chat: full-text search across transcripts and documents, video frame grabs, clip extraction, notes, timeline events, and tasks — every answer carries citations that seek the exact video moment.
  • Auto-signals compare every new file against earlier evidence in the case, surfacing candidate inconsistencies as unreviewed signals before anyone asks.
  • Agent playbooks built for defense work: Suppression Motion Prep, Miranda Timeline, and Exhibit List Builder — each drafting grounded, source-tied work product saved as attorney-review notes.

Quick wins

  • Use the Suppression Motion Prep playbook at intake: it sweeps for consent, search-scope, stop-duration, K-9, and Miranda issues and drafts a motion outline with both sides quoted and cited — motion groundwork done before the preliminary hearing, not the night before.
  • Run the Exhibit List Builder so every draft exhibit is tied to the real file, then export the exhibit pack — video clips, still frames, quoted excerpts, and a MANIFEST.md citation index — when discovery turnover is due.

How it works

  1. Forward the dump by email — Send [email protected] an email with the subject line as the case name and all attachments — bodycam, 911 audio, jail calls, PDFs, photos, scans up to 2 GB each. A new case is created automatically.
  2. The workspace builds itself — Files get diarized transcripts with word-level timestamps, OCR'd document text, and an evidence inventory. New files are compared against earlier evidence and inconsistencies surface as review signals.
  3. Work the case, not the files — Ask the AI agent questions with clickable citations, generate the case brief, run the Miranda Timeline or Suppression Motion Prep playbook, and assign tasks — with every output pending your human review.

How Evidence Copilot Turns Email Into a <span class="gradient">Working Case File</span>

  • Email intake that builds the case for you: [email protected] creates a new case from the subject line and ingests every attachment; case+{id}@evidencecopilot.com accepts later files as evidence and even answers questions in the email body with citations and deep links.
  • Auto-signals on ingest: every new file is compared against earlier evidence in the case, so candidate inconsistencies — report vs bodycam, statement vs jail call — surface as unreviewed signals before anyone thinks to ask.
  • One-click case brief: a grounded markdown brief with overview, evidence inventory, key moments, inconsistencies, and follow-ups, generated from the actual files — not your memory of them.

Why we're different

  • Per-case email intake creates the case from your subject line
  • Later attachments become evidence — just forward them in
  • Auto-signals flag report-vs-bodycam inconsistencies on ingest
  • Every AI answer cites the exact video second or PDF page
  • One-click speaker renaming propagates across every transcript segment
  • Suppression Motion Prep playbook quotes both sides, fully cited
  • Frame-accurate redaction — originals immutable, every action audited
  • Defense-only by design — never sold to prosecutors or police

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

I forwarded the discovery dump by email to the case address before my first client meeting. By the time I sat down, I had diarized transcripts of the bodycam, OCR'd text from the scanned police report, and a case brief with the report-vs-bodycam discrepancies already flagged as review signals. I walked into the client meeting already knowing where the officer's story wobbled.

— Marcus Delgado

The Miranda Timeline playbook built me a chronological custodial-interrogation timeline with both sides quoted and cited to the exact second of the interview-room footage. Building that by hand used to be a weekend of scrubbing footage before every suppression hearing. Now it's part of the intake, and my law clerk verifies the citations instead of transcribing from scratch.

— Priya Raghavan

Supplemental discovery used to mean a new folder nobody reconciled against the original review. Now I email follow-on files to the case address and get answers back in the email body with deep links into the footage — citations that seek the exact moment. Our whole team handles supplemental discovery the same day it arrives.

— Dana Whitfield

Frequently asked questions

How does email intake actually work for a discovery dump?

Every case gets its own inbound email address. Emailing [email protected] creates a new case from the subject line and ingests every attachment — video, audio, images, PDFs, and documents up to 2 GB per file. Once the case exists, case+{id}@evidencecopilot.com accepts additional attachments as evidence and can answer questions in the email body with citations and deep links.

Can it handle files with no text layer, like scanned police reports or photos of exhibits?

Yes. OCR converts scanned PDFs with no text layer and photo evidence — receipts, exhibits, screenshots — into searchable, citable text. Bounding boxes are preserved so any sensitive regions can be redacted later without touching the original file.

Is the AI output defensible given ethics rules on attorney review?

Every AI output is marked AI-generated and pending human review, and the product never makes legal conclusions. Cross-exam drafts are suggested questions only, each tied to a quoted source, and are saved as attorney-review notes. Nothing is auto-applied — AI-suggested redactions and sync proposals file as suggestions you approve or reject.

How fast can my team get set up and start forwarding discovery?

Setup is minutes, not weeks: sign up, create a case, and start forwarding attachments to the intake or case email address. Transcription, OCR, and evidence inventory generate on ingest. The Solo plan is $39/user/mo with 15 media-processing hours included, and every plan includes the full workspace — there are no feature tiers.

How is this different from JusticeText or a DIY Whisper + NotebookLM stack?

JusticeText is transcription-focused at roughly $1,200/attorney/yr — Evidence Copilot's PD Office tier at $750/attorney/yr undercuts it by about 38% and adds the full workspace: OCR, the cited AI evidence agent, auto-signals, playbooks, redaction, and multi-camera sync. The DIY Whisper stack breaks at case scale — no diarization QC, no citations, no redaction, no audit trail — while Evidence Copilot keeps originals immutable and every action audited.

Book a 20-minute walkthrough at evidencecopilot.com/book — or start on the Solo plan at evidencecopilot.com/signup and forward your next discovery dump today.

Get in Touch