Build Your Motion to Suppress on Cited Evidence, Not Memory
Evidence Copilot turns your discovery dump — bodycam, interrogation footage, jail calls, and police reports — into timestamped, diarized transcripts and an AI evidence agent that answers every question with a clickable citation to the exact second or page.
Why Suppression Prep Breaks Down Before the Hearing
- Caseloads force triage, and suppression motions are the first casualty — Public defenders carry roughly 3 times the recommended caseload, according to the National Public Defense Workload Study. With 252,159 criminal defense lawyers nationwide handling over $15 billion in annual firm revenue, the math is unforgiving: when hours are scarce, the report-vs-bodycam comparison that wins a motion to suppress is the first thing that gets squeezed. Watching 40 hours of bodycam frame by frame to find the consent-search moment is not a scalable way to prepare suppression work — so most defenders skim the police report and hope the video matches.
- 1973 caseload standards were written before digital discovery existed — The outdated NAC caseload standards from 1973 assume 150 felony cases a year — with none of today's bodycam video, interrogation footage, jail calls, or 911 audio. Digital discovery and expanded collateral-consequences obligations have inflated the workload per case far beyond what those standards anticipated. A single felony case can now arrive with hours of media across bodycam, dashcam, and interview-room footage, plus scanned police reports and photo evidence — and the standards still pretend it's a paper file.
- Evidence volume keeps climbing while review hours don't — Federal caseload statistics show the volume of matters moving through the courts keeps rising, and every case now arrives with hours of media. Indigent defense systems run on triage: with over 60% of online searches happening on mobile and defenders juggling preliminary-hearing prep, Brady and Giglio review, and redaction for discovery turnover simultaneously, there is no slack in the schedule. The result is that impeachment material buried in a jail call or an interrogation recording never gets found until it's too late to use it.
Why Defense Teams <span class="gradient">Choose Evidence Copilot</span> for Suppression Work
- Every answer cites the exact moment — Ask 'when did the stop start?' or 'what did the officer say about consent?' and the AI evidence agent answers with clickable citations that seek the exact video second or PDF page — so your motion outline and cross-exam questions are grounded in the source, not paraphrase. Every answer is marked AI-generated and pending human review, and the product never makes legal conclusions, so the work stays yours.
- Inconsistencies surface before you ask — Auto-signals compare each new file against earlier evidence in the case on ingest. A police report that conflicts with the bodycam, or a statement that contradicts the jail-call audio, surfaces as an unreviewed review signal before anyone asks — turning the report-vs-bodycam comparison into a systematic step instead of a lucky catch. From a signal with both sides' quotes, cross-exam drafts suggest questions, each tied to a quoted source, saved as attorney-review notes with no credibility conclusions.
- Built for ethics-bound defense practice — Every AI output is marked AI-generated and pending human review; the product never makes legal conclusions. Originals are immutable, every redaction is a new derived file, and every action is audited — a posture you can explain to a bar-ethics question without flinching. Frame-accurate video redaction, word-level audio redaction, and image/PDF redaction all preserve the originals, with AI-suggested regions filed as cards marked 'AI-suggested — needs review' and never auto-applied.
What's included
- Timestamped, diarized transcription with word-level timestamps and one-click speaker renaming that propagates across every segment — so 'Officer Reyes' is renamed once, everywhere.
- OCR turns scanned police reports and photo evidence — receipts, exhibits, screenshots — into searchable, citable text with bounding boxes kept for redaction.
- The AI evidence agent reads transcript windows, grabs video frames, extracts clips, and writes notes, timeline events, and tasks — every answer carrying citations that seek the exact moment.
- Agent playbooks including Suppression Motion Prep and Miranda Timeline draft motion outlines and chronological custodial-interrogation timelines with both sides quoted and cited.
- Multi-camera sync links bodycam, dashcam, and interview-room footage to a single master clock with auto-sync proposals reported with match evidence — never auto-applied.
- Exhibit pack exports zip video clips, still frames, and quoted excerpts with a MANIFEST.md citation index, gated by per-member export permission.
Quick wins
- Run the Miranda Timeline playbook on custodial-interrogation footage to get a chronological timeline of the interrogation before your preliminary hearing — every entry cited to the transcript.
- Use the Exhibit List Builder to draft an exhibit list tied to the real files in the case, so trial prep doesn't start from a blank page the week before.
How it works
- Upload the discovery dump — Drag in bodycam, interrogation footage, jail calls, 911 audio, police report PDFs, and photos — up to 2 GB per file by web upload or email attachment to your per-case inbound address.
- Run the Suppression Motion Prep playbook — Transcripts, OCR text, and auto-signals build the foundation. The playbook sweeps consent, search scope, stop duration, K-9, and Miranda issues and drafts a motion outline with both sides quoted and cited.
- Walk into the hearing with citations — Your outline, cross-exam drafts, and exhibit pack are tied to exact video moments and PDF pages. Export clips, still frames, and quoted excerpts with a MANIFEST.md citation index.
How Evidence Copilot <span class="gradient">Prepares Your Suppression Motion</span> From the Evidence Itself
- Agent playbook: Suppression Motion Prep sweeps consent, search-scope, stop-duration, K-9, and Miranda issues and drafts a motion outline with both sides' quotes cited to the exact source moment.
- Auto-signals on ingest compare every new file against earlier evidence in the case, surfacing candidate inconsistencies like report-vs-bodycam or statement-vs-call-audio before you think to look.
- Cross-exam drafts from a review signal pair both sides' quotes into suggested questions — every question tied to a quoted source, no credibility conclusions, saved for attorney review.
Why we're different
- Every AI answer cites the exact video second or PDF page.
- Defense-only by design — no prosecution or law-enforcement use.
- Auto-signals surface report-vs-bodycam inconsistencies on ingest.
- Suppression Motion Prep playbook drafts outlines with both sides quoted.
- Originals are immutable; every redaction is a new derived file.
- No defense-side competitor offers an MCP integration for Claude.
- Published pricing, no feature tiers — full workspace on every plan.
- AI output is always marked pending human review, never conclusions.
Grounded evidence review for criminal-defense teams — every AI answer cites the exact moment it came from, every output marked pending human review.
What clients say
The Suppression Motion Prep playbook handed me a motion outline with the officer's consent language quoted from the bodycam and the police report side by side, each cited to the exact second. That used to be a weekend of scrubbing video with a notepad. Now it's a starting draft I review and sharpen before filing.
— Marcus Delgado
Auto-signals flagged a statement that contradicted the jail-call audio before I even finished my first pass through discovery. The cross-exam draft paired both quotes into suggested questions I could actually use — every question tied to the source, and nothing auto-applied without my review. On a triage caseload, that's the difference between finding the inconsistency and never seeing it.
— Priya Ramanathan
Our investigators email the discovery dump straight to the case address — bodycam, interrogation footage, scanned reports, all of it. The diarized transcripts with word-level timestamps mean my law clerk can pull the exact Miranda moment in seconds, with the citation attached. Multi-camera sync lines up the bodycam and interview-room footage on one clock, so the timeline builds itself.
— Dana Whitfield
Frequently asked questions
How does the Suppression Motion Prep playbook actually work?
Once your evidence is uploaded and transcribed, the playbook sweeps the case for consent, search-scope, stop-duration, K-9, and Miranda issues. It drafts a motion outline with both sides' quotes — the officer's account and the defendant's — each cited to the exact video moment or PDF page. The outline is saved as an attorney-review note; it suggests structure, never legal conclusions.
Can I cite the AI's output in a filed motion?
The AI output is a working layer, not a filing layer. Every answer carries a clickable citation into the exact second of video or page of the PDF, so you verify the source yourself before anything goes into a motion. Every output is marked AI-generated and pending human review, and originals are immutable with a full audit trail.
What happens to officer and witness names across a big case?
Named-party records track officers and witnesses plus aliases, with mentions across notes and signals. One-click speaker renaming propagates across every transcript segment, so when you confirm an officer's identity once, every citation and excerpt updates.
How fast can my team get set up before a preliminary hearing?
Uploads are immediate — up to 2 GB per file by web or email attachment, with a per-case inbound email address so investigators can forward discovery directly. Transcription and OCR run on ingest, auto-signals fire as files arrive, and the Firm plan includes a priority queue. Most teams are running playbooks the same day the discovery dump lands.
Why not just use Whisper and NotebookLM, or JusticeText?
The free DIY stack breaks at case scale: no diarization QC, no citations, no redaction, no audit trail. JusticeText runs about $1,200 per attorney per year and has faced transcription-quality complaints — the $750/attorney/yr PD Office tier undercuts it by roughly Evidence Copilot adds what neither offers: an AI evidence agent with exact-moment citations, auto-signals, suppression playbooks, redaction, and an audited, immutable evidence workspace.
Book a 20-minute walkthrough at evidencecopilot.com/book, or start on the Solo plan at $39/user/mo — every plan includes the full workspace.