Agents

Agents Overview

Agents automate repetitive legal tasks in August. Define the task in natural language, and August plans execution steps. Run agents on demand or on a schedule, and track progress through activity logs. The objective is consistency and time savings on recurring work.

This video demonstrates how to build and run agents for repetitive legal tasks.

Two Ways to Create Agents

Agents can be created in two ways:

  • From Assistant: Describe your task in a Genius Mode conversation, review the proposed agent draft card, edit as needed, and press Save. See Creating Agents from Assistant for details.

  • From the Agents panel: Build agents directly with step-by-step configuration. This approach is covered in the sections below.

Both approaches create reusable agent objects that can be run on demand, on a schedule, or triggered by document uploads.

How to Build and Run an Agent

Agents are built once by an admin or power user, then run by any team member. The full pipeline runs five steps automatically.

Build — One-time setup

1

Name & describe

Give the agent a clear name and describe the task in plain language.

2

Define steps + playbooks

Configure each step: document intake, AI analysis, playbook review, generation, tabular extraction. Add conditional logic (e.g., "if non-compete clause → flag for partner").

3

Set output + delivery

Choose output format—Word, Excel, email, or DMS—and configure delivery settings.

4

Test, publish → team-ready

Run a test pass, validate outputs, and publish so the whole team can execute it.

Run — Any team member

1

Pick agent

Select the saved agent from the Agents panel.

2

Provide input docs

Upload or connect the relevant documents.

3

Click Run → Word· Excel · DMS

The agent executes autonomously and delivers outputs in the configured format. Monitor progress in the activity log.

Build once ·run as many times as the matter demands.

Running Agents from Uploaded Documents

You can also initiate an agent directly from an uploaded document. This is useful when you're working with a specific file and want to apply an agent without navigating to the Agents panel first.

1

Open document

Locate the document in your folder or upload it directly to your workspace.

2

Select agent action

From the document actions menu, choose the agent you want to run. Available agents depend on your team's configuration.

3

Execute and monitor

The agent executes on the selected document. Monitor progress in the activity log and access outputs when complete.

Running agents from individual documents is ideal for one-off analysis when you don't need batch processing across multiple files.

Creating Agents with Natural Language

Describe what you want accomplished in everyday language:

  • "Every Monday, review new documents in the ABC Matter folder and generate a summary of key developments."

  • "When new contracts are uploaded to the NDA folder, extract term, renewal, and termination provisions into a table."

  • "Daily: Check for new emails from opposing counsel and flag any mentioning deadlines."

Refine the request if outputs are too broad or too narrow. Use specific scope statements to improve repeatability.

Manual vs. Scheduled Runs

Mode

Best For

Manual runs

One-off tasks, pilot testing, ad-hoc analysis

Scheduled runs

Recurring reporting, regular review tasks, ongoing monitoring

Choose cadence based on matter rhythm and stakeholder needs. Validate early runs before relying on scheduled automation.

Event-Triggered Agents (Upload Triggers)

Agents can also run automatically when new documents are uploaded to monitored folders. Event-triggered agents monitor specific SharePoint or OneDrive folders and execute whenever files are added to those folders or their subfolders.

How Upload Triggers Work

When you configure an agent with an upload trigger:

  • Automatic execution: The agent runs immediately after files are uploaded to a monitored folder, processing begins at upload time.

  • Recursive folder monitoring: A trigger on a parent folder matches all uploads to that folder and any subfolders nested beneath it.

  • Batch processing: Multiple files uploaded together in a single batch are processed in one agent run.

  • Owner-only access: Only agent owners can create and manage event triggers. Event trigger management is not available to all team members.

Upload triggers are distinct from scheduled agents. Scheduled agents run on a timer (daily, weekly, etc.). Upload triggers run on demand when new content appears in a monitored folder.

Creating an Upload Trigger

To set up an upload-triggered agent:

1

Create or select an agent

Build or choose an existing agent that processes documents as you need.

2

Add an event trigger

From the agent configuration, add an event trigger with the type Upload.

3

Select folders to monitor

Choose the SharePoint or OneDrive folders the agent should watch. Any uploads to these folders or their subfolders will trigger the agent.

4

Enable the trigger

Activate the trigger. The agent will now run automatically whenever matching uploads occur, as long as the trigger remains enabled.

Upload Trigger Behavior

Trigger Type

When It Runs

Manual

When a user clicks "Run Now"

Scheduled

On a recurring schedule (daily, weekly, etc.)

Event (Upload)

When files are uploaded to monitored folders

Upload-triggered agents process files from the upload batch rather than using saved agent defaults. This means the agent operates on whatever content triggered it.

Currently, Upload is the only supported event trigger type. Other event types may be added in future releases.

Permissions and Access

  • Owner management: Only agent owners can create, modify, or remove event triggers.

  • Folder access: At dispatch time, the agent owner must still have access to the monitored folder. If access is revoked, the agent run is skipped.

  • Enabled triggers only: Disabled or soft-deleted agents do not fire upload triggers.

Monitoring Agent Activity

Activity logs provide visibility into step-by-step execution:

  • See which steps completed and in what order

  • Identify where adjustments are needed

  • Review outputs at checkpoints, especially for high-impact tasks

Treat activity review as part of quality control. Logs are useful for team visibility and process refinement.

Agents follow pass-based patterns: orientation, issue spotting, and summary output.

First-pass Diligence Summaries

Upload a data room, run an agent to extract key terms across all agreements, and generate an executive summary. Review the structured output, then drill into specific documents for deeper analysis.

Issue-Based Document Triage

Set an agent to scan incoming documents for specific provisions—assignment clauses, change of control triggers, termination rights. Flag any that require attorney attention.

Internal Update Generation

Schedule a weekly agent to summarize developments in a matter folder and produce a status update for the deal team or client.

When to Use Agents

Use agents when:

  • Tasks are repeatable and structured enough for consistent execution

  • Inputs follow a predictable pattern (same document types, same extraction goals)

  • You want to reduce manual effort on high-volume, lower-judgment work

Escalate judgment-heavy or novel issues to attorney review. Agents handle the repetitive work so you can focus on decisions that require legal expertise.

Best Practices

  • Start narrow: Begin with a focused scope and expand once the agent proves reliable.

  • Validate early runs: Review outputs carefully before putting an agent into production.

  • Keep prompts concise: Specific, well-defined instructions produce more consistent results.

  • Use checkpoints: For multi-step agents, build in review points to catch issues early.

Was this helpful?
Was this helpful?