Example agent design
Matter Intake and Conflicts Agent for Law Firms
A matter intake and conflicts agent gathers party and affiliate names from intake forms and email, runs them against the conflicts database, and drafts the hit memo for the conflicts attorney's decision. This is a starting design. An AI Blueprint adapts it to your goals and the systems it will connect to.
Intake details are entered once, names are normalized before the search, and every clearance stays with the attorney.
- Owner
- The conflicts attorney or risk partner, who decides clearance
- Reads
- Intake forms and email · The conflicts database · Client, matter, and party records · The ethical-wall list
- Never writes
- Clearance decisions, new matters, engagement letters, or ethical walls. It drafts a screen for the risk partner and never contacts a prospective client.
- Typical cost
- AI Blueprint $4,500–$7,500, credited toward the build. Typical first build $18,000–$35,000. Agent Operations after launch $2,500/mo for one production agent. See the first engagement
The workflow
Intake and conflicts today and with the agent
Planning comparison only. Scope, timing, and outcomes vary by data, workflow, approvals, adoption, and implementation conditions.
- Intake details
- TodayRekeyed from forms and email across systems.
- With the agentGathered once from the intake form and email into one record for review.
- Party names
- TodaySearched as typed, one variant at a time.
- With the agentParty and affiliate names normalized before the search runs.
- Hit review
- TodaySearch results assembled into a memo by hand.
- With the agentA drafted hit memo lists each hit with its source record.
- Ethical walls
- TodayScreens drafted after a lateral hire or waiver, then checked system by system.
- With the agentA screen is drafted when one is needed, for the risk partner's sign-off.
How it runs
Five steps from intake to clearance
An illustrative solution design, not a reported client result. The AI Blueprint maps it to the firm's own intake and conflicts process.
- 01
Collect the intake
Reads the intake form and email, and gathers the client, affiliates, adverse parties, and related entities into one record.
- 02
Normalize the names
Normalizes party and affiliate names so the search covers the variants the firm's records hold.
- 03
Search the conflicts database
Runs the normalized names against the conflicts database and the firm's client, matter, and party records.
- 04
Draft the hit memo
Lists each hit with its source record. The conflicts attorney reviews the memo and decides clearance.
Attorney review point
- 05
Draft the screen when one is needed
Drafts the ethical wall for the risk partner to sign off. The agent never applies a wall or opens a matter.
Attorney review point
Systems
The systems it reads
- Conflicts database
- Intapp, or the conflicts records in the firm's practice-management system, such as Clio or NEOS.
- Intake sources
- New-matter intake forms and email in Microsoft 365.
- Client and matter records
- Practice-management records of clients, matters, and parties, within each user's permissions.
- Ethical-wall list
- The firm's current screens, from the systems that enforce them.
Technologies ITECS evaluates and integrates; listing a product does not imply a formal partnership. The AI Blueprint confirms which system holds the authoritative record.
Controls
Read-heavy and write-controlled by design
- Read-heavy
- Reads the systems listed above through access scoped to this workflow.
- Write-controlled
- Writes nothing listed under Never writes in the spec at the top of this page. Anything it drafts waits at the approval points below.
- Approval points
- The conflicts attorney reviews every hit memo and decides clearance. The risk partner signs off on any screen before it is applied.
- Audit trail
- Each run keeps its inputs, sources, output, and the reviewer's decision.
In this design
- Prospective clients' and adverse parties' names stay inside the firm's tenant or on its own server, and the agent never contacts a prospective client.
- Retrieval inherits matter permissions and ethical walls from the source systems, and access is denied when a permission is unconfirmed.
- It runs under no-training terms ITECS verifies before production, and privileged material stays inside the firm's tenant or on its own server.
- Client guideline clauses that restrict AI use are tracked per client. Whether to seek a client's consent stays with the firm and its counsel.
- ITECS does not provide legal advice through its agents, and no design promises an outcome. The agent drafts and flags; the firm's attorneys review the work and make every decision.
Deployment fit
Where this design can run
- Hosted AI Agents
- Runs in a governed Linux environment ITECS operates, on frontier models through enterprise API agreements, connected to the conflicts database and practice-management records through controlled integrations, with human review and an audit trail.
- Private AI Servers
- Runs on local models on a server inside your network, for the names of prospective clients and adverse parties that should not leave it. The same build ladder applies; server hardware is quoted after a sizing call.
Typical first engagement
Start with an AI Blueprint
The AI Blueprint sets the actual build rung and its fixed-fee not-to-exceed. The rows below show the typical path and the catalog range for each step.
- FirstAI BlueprintAgent Discovery & Technical Specification. Credited toward the build.$4,500–$7,500
- Typical first buildSingle-Workflow Production AgentIt is a single-workflow build because it runs one primary workflow, intake to hit memo, with a human-in-the-loop review path. Adding wall checks across the document system and Teams makes it an integrated build.$18,000–$35,000
- After launchAgent Operations, one production agent$2,500/mo
Prices from the published AI pricing catalog.
Customize this design
Bring your goals and your systems. The AI Blueprint decides the scope and the systems, not this example, and ends with a fixed-fee not-to-exceed for the build.
FAQ
Matter Intake & Conflicts Agent FAQ
Does the agent clear conflicts?
No. It drafts the hit memo with each hit's source record. The conflicts attorney or risk partner reviews it and decides clearance.
Can it open a new matter or send an engagement letter?
No. It prepares the intake record and the hit memo. Opening the matter and the engagement letter stay with the firm.
How does it handle ethical walls?
The agent inherits the firm's existing walls, so screened users cannot see walled matters through it. When a lateral hire or waiver requires a new screen, it drafts the screen for the risk partner to sign off.
Where do prospective clients' names go?
Into the firm's own tenant on a hosted build, under no-training terms ITECS verifies before production, or onto a private server inside the firm's network when client terms require it.
Is this legal advice?
No. ITECS does not provide legal advice through its agents. The agent applies rules the firm approved and drafts or flags for review; the firm's attorneys decide, and no design promises an outcome.
Related examples