Fully automated legal matters – from start to finish

lexifina.com · 2026-10-02 · by Long Nguyen ·generic
One matter from first enquiry to closed file in 40 minutes, with an agent doing the legal work: what it got right, what would fail a file review, and where people should step in.

Fully automated legal matters – from start to finish

A matter lifecycle 100% mediated by agents.

1/7

The problem

“Any tool that forces a user to change their process will not be adopted”.

Document drafting is a small component which gets most of the attention. The actual business of law occurs around the enquiry, intake and matter lifecycle.

To test the limits of how an AI system can handle this, we run a complete intake by fully automating our system. Doing so underlines some key patterns, and helps us think about exactly where we can optimally place human guardrails.

Skip to conclusions

2/7

Enquiry to closed file in 40 minutes

The client did own onboarding, the agent did the legal work, and the partner mostly moved the matter along.

In this example, a small company is hiring its first Head of Sales and asking a firm it had never used for an employment contract with a 12-month non-compete.

40 minutes, enquiry to closed file

This runTraditional

Agent 17.4 minPartner 14.5 minClient 6.9 minEmployee 44 s

  • Onboarding13.0 min
  • Research and drafting17.8 min
  • Review and signature6.7 min
  • Bill and close2.0 min

The client filled in the firm's enquiry form. One link then took her through her instructions, identity checks, the engagement letter and money on account. The agent drafted the engagement letter from the firm's precedent, researched the law and drafted the contract.

The client read the draft in her portal and asked for two changes, which came back as tracked changes. Both sides signed electronically. The partner's captured time became a bill, paid from the money on account, and the matter closed.

3/7

The agent pushed back

Asked for a 12-month non-compete, the agent drafted nine months and said why.

Before drafting, it researched the current law on restrictions for senior sales staff, using UK legislation, government papers and case law. It concluded that twelve months sits at the outer edge of what courts enforce. A shorter restraint, reduced by any garden leave, is safer.

It drafted that, explained the choice in a comment on the clause, and kept the twelve-month non-solicitation the client wanted. The client accepted the recommendation. When she later asked for a new start date and more holiday, the agent changed only those terms.

This is the part of legal work an agent should do well: weigh the instruction against the law and say so. It also made a mistake. Its research described a coming change to unfair-dismissal rights as applying from day one, when it applies after six months of service. That change affects how long the contract's probation should be, and the agent did not flag it. A partner reading the advice should catch an error like that.

4/7

Time and the bill

The bill came to a fraction of the estimate.

The matter lifecycleTime on the clockTime captured by systemTriage the enquiryTriage the enquiry: 1:02 on the clockTriage the enquiry: 0:30 captured by the system0:30 of 1:02Engagement letter (agent)Engagement letter (agent): 4:19 on the clockEngagement letter (agent): 3:15 captured by the system3:15 of 4:19Send the onboarding linkSend the onboarding link: 1:40 on the clockSend the onboarding link: 1:00 captured by the system1:00 of 1:40Record due diligenceRecord due diligence: 0:50 on the clockRecord due diligence: 0:30 captured by the system0:30 of 0:50Record money on accountRecord money on account: 0:26 on the clock0:26, nothing capturedResearch + contract (agent)Research + contract (agent): 17:49 on the clockResearch + contract (agent): 14:14 captured by the system14:14 of 17:49Share the draftShare the draft: 0:34 on the clock0:34, nothing capturedRevision (agent)Revision (agent): 2:39 on the clockRevision (agent): 1:30 captured by the system1:30 of 2:39Send for signatureSend for signature: 1:01 on the clockSend for signature: 0:40 captured by the system0:40 of 1:01Record time, bill, payRecord time, bill, pay: 0:54 on the clock0:54, nothing capturedClose the matterClose the matter: 0:39 on the clock0:39, nothing captured

Enlarge diagram

It came to £118.50 against an estimate of £900 to £1,400, because only the partner's minutes counted. When an agent does the drafting, the lawyer's time no longer measures the work. A fixed fee fits a matter like this better than the clock.

5/7

Was it a real intake?

It had the shape of one. It would not pass a supervising partner's file review.

| Check | Verdict | What happened | | ---------------------- | ------- | --------------------------------------------------------------------- | | Conflict check | Missing | Not run before the client was taken on | | Who the client is | Partly | Checks were made on the director, not the company that was the client | | Identity | Partly | Uploaded photos, checked by eye | | Engagement terms | Met | Costs, scope and complaints set out and signed | | Advice on the key risk | Partly | Given as a comment on the draft, unreviewed by the partner | | Partner review | Missing | The draft went to the client after a glance | | Execution | Failed | The signed contract still contained a placeholder | | Client money | Failed | The matter closed with a balance still held |

We can see that some trivial mistakes slipped through the cracks (a \[template\] field and payment processing mistake were made). These critical issues should be gated behind deterministic hooks.

The client's side was the strongest part. One link and steps that unlock in order took her through everything without a phone call, and the employee signed without creating an account. The firm's side worked, but was spread across too many screens.

6/7

Where people should step in

The partner touched this matter eleven times without once reviewing anything. A better design has four gates, placed where a mistake is hard to undo or the decision belongs to a lawyer or the client. Automatic checks guard everything in between.

1. Enquiry and onboardingClient and portal Questionnaire, ID, source of funds, engagement letter. Conflict search and sanctions screening run automatically. 2. Take on the clientGate 1 · partner Read the conflict result, the identity checks and the risk rating, then decide to act. A few minutes. 3. Research and draftAgent Research note, contract and a short advice note. An automatic check flags placeholders, blanks and open comments. 4. Approve the draft and the adviceGate 2 · partner The one long review: the whole contract and the advice before either leaves the firm. 30 to 60 minutes. 5. Client decides and sets a mandateClient Accepts the advice or not, and sets limits for the other side, e.g. a non-compete of at least six months. 6. The employee’s side negotiatesCounterparty agent His agent proposes changes; ours answers within the mandate. Agreed changes come back as tracked changes. 7. A concession outside the mandateGate 3 · only if needed Goes to the partner and the client. Inside the mandate, the negotiation does not stop for anyone. 8. Sign off the version to be signedGate 4 · partner The automatic check is clean; the partner confirms this is the agreed text. A few minutes. 9. Signature, bill and closeEveryone, then the system Both parties sign. Time becomes a bill paid from client account, any balance is returned, and the matter closes.

Only the second gate is long: reading the draft and the advice before either reaches the client. That is where the placeholder and the research error would have been caught. The others take minutes, because the work before them has already been checked.

The other side was missing from this run. The employee signed what he was sent; a new Head of Sales would usually take advice on a non-compete. That negotiation belongs after the client has approved the draft and set her limits, and before the final version is settled. Our agent would negotiate within those limits against the employee's agent, and only a request outside them would stop for the partner and the client.

7/7

Our Conclusions

Mechanistically, a small matter can already run end to end, and the agent's legal work was relatively credible. The failures were around it: a final check before signing, client money at the end, a conflict search at the start, and supervision that is real but sparse.

But the key question is, where is this going?

We could see agent-mediated negotiations (multiple rounds of redlines) occurring before a partner ever even looks at a matter.

We could see more artifacts being generated for QA or checking, such as:

1. A coverage matrix and branch gallery. 2. Approved requirement list with versioning. 3. Evidence triage queue and read-back. 4. Assembly receipt and regression matters. 5. API integration with real gov/regulatory systems.

Legal work is broad, and routine transactional work from a well-established and up-to-date document set is relatively trivial to automate. As the floor continues to rise it is unclear exactly how and where the limits of legal work will lie, but the common pattern is that most of the work that is being eroded is at the lower, rather than the partner tier.

Return to method

lexifina.com · 19 links

Comments (0)

No comments yet