THE AGENTS FIELD GUIDE
AI agents can act. Judgment still matters.
An agent can use tools and take several steps toward a goal. Its value depends on the task it is given, the information it can access, the actions it may take, and the person responsible for checking the result.
THE PRACTICAL TEST
Four questions before an agent acts.
- 01Read
Which documents, systems, and matter data can it access?
- 02Decide
Which next steps can it choose within a task?
- 03Change
May it alter files, records, or work product?
- 04Send
Can it communicate or submit anything outside the firm?
A PATH THROUGH THE SECTION
Understand. Apply. Control. Evaluate.
Begin with the mechanism, then follow an example through the decisions, permissions, and tests that make it usable in legal practice.
- 01 / UNDERSTAND
What is an AI agent?
Follow the model, tool, and feedback loop. Separate conversation context and stored memory from model training.
Understand the system - 02 / APPLY
Agents in legal workflows
Walk through bounded research, drafting, and review tasks with visible lawyer checkpoints.
Trace the work - 03 / CONTROL
Permissions and oversight
Decide what an agent may read, draft, modify, or send, and when it must stop for approval.
Set the boundaries - 04 / EVALUATE
Evaluate an AI agent
Run a matter-based pilot. Score source support, missed issues, unauthorized actions, and the full time spent on review.
Use the scorecard
GO DEEPER
Build a fuller mental model.
The four guides above provide the path. These deeper references explain the system underneath it, the ways it can fail, and the decisions involved in adoption.
- SYSTEMS / 01
Inside an AI agent
Follow a tool call from task to result, and see how retrieval, context, stored state, and multiple agents change the system.
Explore the architecture - RISKS / 02
Failure modes and response
Recognize unsupported claims, hostile source content, wrong actions, and the steps to contain and learn from an incident.
Study the failure paths - ADOPTION / 03
Choose and pilot an agent
Pick a bounded workflow, question a vendor, account for review costs, and decide when to expand or stop.
Plan a responsible pilot
KEEP EXPLORING
Examples and perspectives, with their limits in view.
Connect the core guides to a bounded prototype, the assistant concept, and a dated prediction reassessed with current evidence.
An agentic lawyer demonstration
A video prototype using fictional matters, with its limits and human review points explained.
Read more RELATED GUIDEAI assistants for professional work
The adjacent concept: assistive tools, multi-step tasks, and why labels alone do not define autonomy.
Read more UPDATED PERSPECTIVECan agents do junior lawyer work?
A January 2026 prediction revisited with task-level limits, current examples, and a testing standard.
Read more