# How to Build eDiscovery Document Review Workflows

Document review typically consumes up to 70% of total eDiscovery spend, presenting a significant financial hurdle for boutique law firms. Implementing a lean, folder-based review workflow allows smaller firms to bypass expensive enterprise software suites. By organizing files systematically and using structured metadata extraction, legal teams can execute a defensible review process internally.

Source: https://fast.io/resources/ediscovery-document-review/
Author: [Tom Langridge](https://fast.io/authors/tom-langridge/)
Last reviewed: 2026-08-25

## Why Document Review Drives eDiscovery Litigation Costs

Document review accounts for up to 70% of total eDiscovery costs on average, making it the single most expensive stage of the litigation lifecycle. Traditionally, eDiscovery document review is the stage in the litigation lifecycle where legal teams assess collected electronic files for relevance, privilege, and confidentiality before production. This high cost is driven by the labor-intensive nature of attorneys and paralegals examining files one by one. Under traditional manual workflows, linear review speeds average 40 to 60 documents per hour per reviewer, leaving just 1 minute per file to comprehend the text, identify relevance, and assess privilege. For small and mid-sized law firms, this slow pace often forces a choice between using expensive managed review vendors or sinking hundreds of unbillable hours into manual file sorting.

Rather than relying on complex enterprise suites designed for massive corporate law departments, boutique firms can implement a lean, folder-based workflow. This approach combines structured data organization with automated document tools to keep cases moving without driving up administrative overhead. By managing the ingestion, culling, and review processes internally, smaller legal teams can maintain complete control over their case files while keeping client bills predictable.

## How to Structure Folder Hierarchies for Case Matters

To run an efficient ediscovery review process, firms must start with a clean and predictable directory structure. Effective ediscovery file management requires a dedicated legal workspace where every file lives in a defined stage of the review lifecycle, rather than unstructured shared folders in general cloud storage platforms like Google Drive or Dropbox.

A practical structure for a matter workspace uses numbered folders to maintain a clear line of custody:

* 01_Collected_Raw: This folder contains the original, unaltered files collected from custodians. It is set to read-only for reviewers to preserve the original metadata and file structures.
* 02_Processed_Culled: Files are moved here after deduplication and file-type filtering. Suppressing duplicate files and known system files can cut the total volume of files substantially before human review begins.
* 03_Review_Pending: This folder holds the active review set. Files are distributed into subfolders for individual reviewers.
* 04_Reviewed_Responsive: Documents marked as relevant to the litigation are moved here.
* 05_Reviewed_Privileged: Files containing attorney-client communications or work product are isolated here for the privilege log.
* 06_Production_Set: The final, stamped documents ready for delivery to opposing counsel.

Organizing files this way prevents reviewers from opening the same document twice. Rather than relying on manual tracking spreadsheets, the directory itself shows the progress of the review.

In Fast.io, legal teams can establish this layout within shared [workspaces](/product/workspaces/). Granular permissions allow administrators to restrict access to folders like 05_Reviewed_Privileged, ensuring that only lead counsel can access files tagged for privilege review. Every file in the workspace carries a complete version history, allowing teams to restore prior versions of spreadsheets or pleadings if a collaborator accidentally overwrites them.

For naming workspaces, firms should adopt a consistent convention. A format combining the year, matter number, client name, and opponent name keeps the firm's directory organized. This naming convention makes it easy to find matters using Fast.io's global search. Since files stay in the org-owned workspace, transferring ownership when a case concludes or when a reviewer leaves the firm is straightforward.

## Steps for Collecting Discovery Files Directly From Clients

Collecting electronic files from clients often introduces security and chain-of-custody risks. The common practice of sending record sets as email attachments or using temporary public sharing links is insecure. These methods also strip metadata from files and risk exposing sensitive information.

To handle electronic document review legal requirements, boutique firms need a direct, encrypted method to collect files. Fast.io supports this through branded shares, specifically Receive and Exchange links. An administrator can create a secure inbound folder and send a link to the client. The client can drag and drop record sets directly into the workspace from a web browser without creating an account. This keeps the files inside the firm's controlled workspace from the moment they are transmitted.

For files already stored in external systems, Fast.io's cloud import tool allows teams to pull data directly from Google Drive, Dropbox, OneDrive, or Box, as well as via public URLs. This cloud-to-cloud import bypasses local network bandwidth, which is a major advantage when collecting gigabytes of deposition video or scanned record sets. There is no need to download files to a local office machine first, avoiding network saturation and local disk constraints.

Once files arrive, Fast.io's Intelligence Mode automatically indexes the text and metadata of all documents in the workspace. This prepares the files for hybrid search, which combines full-text and semantic search. Simple keywords or date filters can cull files quickly. This immediate indexing replaces the traditional vendor step of charging per-gigabyte processing fees just to make documents searchable. It allows paralegals to quickly filter out junk files, spam, and duplicate emails before review begins.

## Running First-Pass Review and Automated Metadata Extraction

The first-pass review is the most time-consuming part of the ediscovery review process. Reviewers must categorize documents based on their relevance and identify key details like contract dates, counterparties, and document types. Doing this manually for thousands of pages is where review speeds stall.

To accelerate this phase, firms can use Fast.io's [Metadata Views](/product/document-data-extraction/). This feature acts as a structured extraction layer that turns documents into a queryable spreadsheet database. Instead of writing complex OCR rules or building templates, users describe the fields they want to extract in plain English. The platform designs a typed schema, which supports Text, Integer, Decimal, Boolean, URL, JSON, and Date & Time formats. It matches files in the workspace and populates a spreadsheet with the extracted data.

For example, a reviewer can instruct Metadata Views to extract the counterparty name, contract expiration date, and governing law from a folder of contracts. The system populates the columns automatically, allowing the review team to sort, filter, and review the documents in a tabular view. This works with scanned PDFs, Word documents, spreadsheets, and handwritten notes. Reviews can add new columns at any time without reprocessing the files.

For developers and technical firms, Fast.io provides a consolidated Model Context Protocol toolset. This allows external AI agents to access the workspace, trigger metadata extraction, and query the results through an MCP server. This automated extraction lets the legal team focus on verifying the responsiveness of files rather than copy-pasting contract terms.

Here is an example configuration for connecting an external agent to the Fast.io MCP endpoint:

```json
{
  "mcpServers": {
    "fast-io": {
      "url": "https://mcp.fast.io/mcp/tools",
      "headers": {
        "Authorization": "Bearer YOUR_FASTIO_API_KEY"
      }
    }
  }
}
```

By connecting an agent to this endpoint, technical legal teams can automate the categorization of files. The agent can read incoming documents from the `01_Collected_Raw` folder, run extraction queries, and write the categorized files to the appropriate review folders based on relevance.

## Implementing Quality Control and Privilege Logging

Maintaining quality control and privilege logging is a critical step before documents are produced. If a privileged file is accidentally disclosed to opposing counsel, the consequences can be severe. Legal teams must inspect every file marked for exclusion and verify the privilege claims.

Reviewers can use Collaborative Notes inside Fast.io to coordinate this quality check. Collaborative Notes allow attorneys and paralegals to co-edit privilege logs in real time in the same workspace. Since these notes support concurrent access, team members can collaborate on descriptions of attorney-client communications and draft privilege assertions together without locking each other out of the document.

To ensure the integrity of the review, the platform maintains an append-only audit log. The audit log tracks every user activity, including file reads, downloads, permissions modifications, and version restores. This log cannot be edited or deleted, which provides a permanent, auditable history of the entire review process. If an opposing party questions the chain of custody, the firm can present the audit log as proof of file handling.

Every organization starts with a 14-day free trial, which requires a credit card. Creating a Fast.io account is free, but establishing a secure workspace for active litigation review requires a paid subscription. Plans scale to fit different caseloads: the Starter plan is $9.99 per month, the Business plan is $49.99 per month, and the Enterprise plan is $199.99 per month. These plans provide persistent, shared storage where human teams and software tools can collaborate on the same matter files.

Firms can run their quality control passes directly within these workspaces. For instance, a senior attorney can perform a secondary review on a random sample of the responsive documents. If any coding errors are found, the version history allows the team to see who reviewed the file and when the error was made. This continuous quality control process ensures that the final production set is accurate and defensible.

## How to Produce and Share the Final Document Set

Once the review is complete, the final step is to deliver the responsive files to opposing counsel. In traditional workflows, this involves copying files onto physical media or using consumer sharing links that lack access control and tracking.

A secure [client portal](/product/portals/) or branded share link is the standard method for modern client delivery. In Fast.io, administrators can create a durable or expiring File Share for the folders containing the production set. These shares can be restricted to specific email addresses, requiring recipients to verify their identity before downloading the files. Because Fast.io operates on a 14-day trial followed by paid plans, only the firm paying for the workspace subscription needs an account; external recipients can view and download files directly from the web portal without paying or signing up.

The activity feed shows exactly when the recipient opens the link and downloads each file. This tracking provides proof of delivery and receipt, helping resolve disputes about production timelines. Since Fast.io runs on cloud infrastructure partners, including Google Cloud Platform and Cloudflare, that are certified to industry-leading security standards, your files remain protected by standard encryption in transit and at rest during delivery.

Using a structured, folder-based workspace allows small firms to manage document reviews without the high cost of legacy enterprise software. By culling files early, using metadata extraction, and sharing files securely, boutique practices can run a disciplined review process that protects their clients and budgets. This approach replaces the habit of using unbranded file transfer tools that lack the compliance controls required for legal discovery. Instead, it provides a secure, auditable workspace where legal teams can collaborate with confidence.

## Frequently asked questions

### What is document review in eDiscovery?

eDiscovery document review is the stage in the litigation lifecycle where legal teams assess collected electronic files for relevance, privilege, and confidentiality before production. This process helps identify the key facts of a case, isolate privileged communications, and prepare documents for exchange with opposing counsel.

### How do you perform a document review in law?

Performing a document review requires a systematic process of collection, ingestion, first-pass review, quality control, privilege logging, and production. Reviewers analyze files to determine if they are responsive to the discovery request, tag them for privilege if they contain confidential attorney-client communications, and extract key metadata to organize the production set.

### What are the stages of eDiscovery?

eDiscovery follows the Electronic Discovery Reference Model, which includes information governance, identification, preservation, collection, processing, review, analysis, production, and presentation. Legal teams typically focus most of their resources on the processing, review, and production stages, as these involve the largest volumes of data and require rigorous quality control to protect privilege.

## Sources

- [Logikcull: Six Ways to Take Control](https://www.logikcull.com/blog/six-ways-to-take-control-of-your-ediscovery-process-and-realize-instant-roi): Document review accounts for up to 70% of total eDiscovery costs.
- [Everlaw: A Sprint to the Finish](https://www.everlaw.com/blog/ai-and-law/genai-faster-better-cheaper-edisclosure/): Linear review speeds average 40 to 60 documents per hour per reviewer.

## About Fast.io

Fast.io provides shared workspaces where people and AI agents work on the same files, with built-in semantic search and citation-backed chat over what they hold. Agents reach it through a remote MCP server, a REST API at https://api.fast.io/current/, and a command line client published on npm as @vividengine/fastio-cli. MCP setup is at https://mcp.fast.io/docs: Claude and most MCP clients connect to https://mcp.fast.io/mcp/tools, ChatGPT to https://mcp.fast.io/mcp/operations, and coding agents to https://mcp.fast.io/mcp/code.