← Selected work
Enterprise AI2022 – 2024

Redline: a legal AI assistant with verifiable answers

I was the product manager for Redline, an AI assistant for legal teams inside Microsoft Word and Outlook. I owned its roadmap, scope and adoption measures. Source verification, workspace boundaries and human review answered the concerns legal teams raised in discovery.

Enterprise AI · Redline

Trust is a product requirement

  1. Ground outputs
  2. Verify sources
  3. Human review

Make the answer traceable. Keep a professional in control.

0 → 1

Redline, from discovery to adoption by enterprise legal teams

4

legal workflows turned into user journeys and PRDs

6

parts to the trust layer

At a glance

Role
Product Manager. I owned the roadmap, scope, requirements, backlog and adoption measures
Product
Redline, an enterprise LLM legal assistant embedded in Microsoft Word and Outlook. Redline is a codename; the client and the product’s real name are confidential
Period
2022 – 2024
Company
Frontline Labs, an AI and software product studio. Redline was built for a studio client
Users
Legal teams, administrators and enterprise buyers
Team
Three engineers, with design and QA

Context

At Frontline Labs, I owned product direction across AI and software products, working with founders on priorities, scope and release decisions.

This case study is about one of them. Redline is an AI assistant for legal teams that works inside Microsoft Word and Outlook, the tools they already used. It was built for a studio client. Redline is a codename, because the client and the product’s real name are confidential.

I was its product manager from the first discovery sessions to adoption. I decided what was built next and what was cut, and agreed that scope with the client. I wrote the requirements. After launch I defined how usage and adoption would be measured, and tracked them to decide what came next.

The problem

Legal teams needed help with drafting and review, but accuracy, confidentiality and accountability shaped whether they would adopt the assistant.

Discovery with enterprise buyers and users surfaced three recurring concerns, alongside the complexity of the legal workflows.

It might invent facts or citations

The assistant drafts, reviews, verifies facts and analyses filings on behalf of lawyers. If it invents a citation, the lawyer carries the liability.

Client documents might leave the firm

Legal teams would not adopt a tool if client documents could leave the firm or be used to train a model.

No record to defend the work

Without a record of what the tool did, its work could not be defended later.

Dense, ambiguous workflows

Drafting, compliance review, fact-verification and regulatory-filing analysis each had to be understood before it could be specified.

Finding the cause

Discovery with users and buyers

I ran discovery workshops and interviews with enterprise users, buyers, and compliance and legal stakeholders, to understand their buying criteria and what stopped them adopting.

Learning the domain

I developed a working understanding of the legal workflows and documented the agreed requirements, giving engineering a clear reference for product decisions.

Alpha and beta programmes

Each full release was preceded by alpha and beta programmes with real users.

Product decisions

Own the scope with the client

I decided what went into each release and what waited, and agreed that scope with the client. The first releases covered four workflows: drafting, compliance review, fact verification and regulatory-filing analysis.

With three engineers and the trust controls taking priority, scope had to be explicit and agreed, release by release.

Require human review, and accept the cost

I defined what the assistant could do on its own and when a person had to review. Nothing is sent or filed externally without a person approving it.

The cost of an unreviewed error falls on the lawyer, not the software.

Trade-off: Mandatory review made the tool slower. We kept it.

Decline to answer instead of guessing

The assistant refuses to give a legal conclusion with no source to support it, and refuses to answer from outside the documents in the user's workspace.

A visible limit helps users understand when they can rely on the assistant and when they need to review the source themselves.

Ground every output in a source the user can check

Outputs were grounded in a retrievable source, with verification the user could do for themselves.

A lawyer cannot rely on a claim they cannot trace. This answered the fear of invented citations directly.

Spend engineering time on trust before features

The audit trail, workspace data boundaries and admin controls were built ahead of new capabilities.

These controls addressed specific adoption barriers raised in discovery. I prioritised them before expanding the feature set.

Trade-off: With three engineers, that was time features would have used.

Agree the rules with compliance before building

I facilitated agreement between users, compliance stakeholders and engineering on data handling, human review and the audit trail.

All three groups had to agree. Agreeing early was cheaper than rebuilding after a compliance review.

Make output quality a release gate

A fixed set of test prompts ran on every release. Outputs were scored for accuracy and for whether each claim traced to a source, and a legal stakeholder reviewed a sample.

Model behaviour changes between versions, so quality was checked every time, alongside security and risk reviews.

What shipped

Four legal workflows

Drafting, compliance review, fact-verification and regulatory-filing analysis, each turned into user journeys, PRDs and acceptance criteria.

The trust layer

Citations, source verification, workspace data boundaries, human review, an audit trail and admin controls.

Documentation

FAQs and user documentation for the people using and administering the product.

Delivery

I owned the roadmap and the backlog. I decided what went into each release and what waited, and agreed the scope with the client.

I worked with three engineers and design in short Agile cycles: sprint planning, backlog refinement, sprint demos and release scheduling.

Every release passed QA, security, privacy and risk reviews, and a launch-readiness check.

I presented product demos to client stakeholders and explained model behaviour and limits to non-technical audiences.

Measuring success

A fixed set of test prompts was run on every release.

Outputs were scored for accuracy and for whether each claim traced to a source.

A lawyer or legal stakeholder reviewed a sample before release, and quality was tracked over time.

After launch I defined the usage and adoption measures for legal teams and tracked them, and used what they showed to set the next priorities on the roadmap.

Outcomes

Delivered Redline, an enterprise legal assistant embedded in Microsoft Word and Outlook.

Redline was adopted by enterprise legal teams.

Its controls addressed the accuracy, confidentiality and accountability concerns raised during discovery.

Lessons learned

In regulated AI, limits are a feature

Clear boundaries helped legal teams understand where the assistant could support their work and where their own judgement remained essential.

Answer the buyer's objection before adding a feature

The controls addressed specific objections raised by buyers. I now make those objections an explicit part of enterprise discovery.

Give the team a shared domain reference

Documenting legal workflows and agreed constraints gave engineering a clearer basis for decisions and reduced repeated clarification.

Slower can be the right product decision

Human review added time, and verification work reduced the capacity available for new features. I accepted those costs because they addressed the risks users had identified.

Explore the product

Three objections, and what answered each

Each part of the trust layer exists because of something a buyer said. Pick an objection.

“It might invent a citation.”+

Answered by citation-grounded outputs and source verification: every output points to a retrievable source the user can check.

“Client documents might leave the firm.”+

Answered by workspace data boundaries and admin controls: each workspace's documents stay inside that workspace.

“We could not defend its work later.”+

Answered by human-in-the-loop review and a full audit trail of what the system did and why.

What the assistant refuses to do

Limits were designed in and shown to users.

A conclusion with no source+

It will not give a legal conclusion with no source to support it.

Answers from outside the workspace+

It will not answer from outside the documents in the user's workspace.

Sending without approval+

It will not send or file anything externally without a person approving it.

Next case studyRoomReady ↗