Case study · Legal · Email Outreach
How a legal services company took campaign launch time from weeks to same day
A legal services company of 20-80 staff moved email outreach off a manual queue and onto agents that run it continuously. The build, the numbers, and what stayed human.
Email Open Rate
A legal contact went quiet — handle the email outreach.
3 AI agents · 5 tools connected · live in half a day · no code
- Company
- Legal services company
- Team size
- 20-80 staff
- Industry
- Legal
- Time to live
- Half a day
- Agents deployed
- 3 AI agents
- Tools connected
- 5 integrations
The context
Why Email Outreach is hard in legal.
Nothing about email outreach is complicated on a single instance. What makes it expensive in legal is volume arriving through client intake forms, opposing counsel email, court notices, and document requests, against the docket and the billable hour. Miss the window and the cost is not the minutes — it is a deadline that was in an email nobody opened.
Constraints the build had to hold
Matter-scoped access
Agents work inside a matter, so a workflow set up for one client cannot read another’s file.
Privilege is preserved
Privileged material never leaves firm systems. Where a step needs the substance, it works from a firm-written summary.
Nothing is filed automatically
Agents prepare, calendar, and chase. Filing and advice stay with the attorney.
The change
Same job. Two chains.
Every handoff in the left-hand chain is somewhere Email Outreach used to wait. The right-hand chain has the same steps and none of the waiting.
By hand
- List pulled and dedupedby hand, in a spreadsheet
- One email personalisedthe rest get the template
- Sent in a batchno suppression check
- Second touch planned
usually never sent
With agents
- Work arrives on any channelpicked up in seconds
- Research agenthanded straight on
- Drafting agenthanded straight on
- Cadence agent
logged, and reviewable
When the work can happen
Before and after
What Email Outreach cost them, and what replaced it.
The challenge
With a growing prospect database of 10,000+ contacts, this legal services company couldn't scale their legal email outreach without sacrificing quality. Their team of 20-80 staff was managing outreach campaigns across multiple segments, but the manual process created constant bottlenecks. Campaigns took weeks to plan, write, segment, and execute — by which time the market moment had often passed.
The full background
Follow-up sequences were the biggest gap. Only 23% of prospects received a second touchpoint within the first week, and multi-step nurture campaigns were practically non-existent. The team tracked engagement in spreadsheets, leading to duplicate sends, missed follow-ups, and embarrassing errors like emailing prospects who had already converted. In the legal space, where relationships and timing matter enormously, this lack of systematic outreach was costing them an estimated $200K in annual pipeline.
What they built
Rather than blasting a bigger list, this legal team used DeskFerry to make every touch worth sending. They connected Clio, Google Drive, and Slack, and moved the whole outreach process onto agents that work one contact at a time.
How it was wired
Campaign setup collapsed from weeks to an afternoon because segmentation, research, drafting, and scheduling stopped being four separate manual passes. The team writes the brief and the guardrails; the agents produce the drafts and run the schedule. Approval mode was kept on for the first fifty drafts of any new segment, which is how the team built confidence in the voice before letting a segment send automatically. Replies route to one queue sorted by intent, so the sales team spends its time on people who answered rather than on people who have not.
The impact
What changed, measured the same way on both sides.
Before and after across the metrics that matter for legal Email Outreach.
Email Open Rate
Major increase
Reply Rate
Significant improvement
Campaign Launch Time
Dramatically faster
Follow-Up Coverage
Full coverage
Pipeline from Outbound
Strong growth
How these were measured
- Baseline
- The "before" column is the team’s own measurement of their manual email outreach process, taken over the four weeks before anything was connected.
- Comparison
- The "after" column is the same measurement repeated on the same process once the agents were live, so both sides count the same things in the same way.
- Why no percentages
- These are composite scenarios built from patterns across many deployments, not one audited customer’s books. Directional language is the honest way to report that — your own numbers will depend on your volume, your process, and your starting point.
A day, either side
The same day, before and after.
What Email Outreach actually looked like for this legal team — the version they described in the first call, and the version they run now.
Before DeskFerry
9:00
Pull a list. Paste it into a spreadsheet. Start deduping by hand.
10:30
Write one genuinely personalised email. It takes eighteen minutes.
11:00
Give up on personalising the rest and send the template.
14:00
Realise two people on the list already replied last week. Send anyway.
17:00
Second touches for last week’s batch do not get sent. Again.
After DeskFerry
9:00
Review the queue: drafts for every legal contact due a touch today.
9:20
Approve the batch. Anything with an open thread was already suppressed.
9:21
Sequences fire on their own schedule, spaced to protect the domain.
14:00
Replies land in a single queue, sorted by intent rather than arrival.
17:00
Every second and third touch went out. None of them by hand.
The build
The 3 agents that run it.
One job each, with an explicit handoff between them. Splitting Email Outreach this way is what makes a failure legible — you can see which step it went wrong at instead of debugging one agent that does everything.
- 01
Research agent
Trigger
A contact enters a sequence
Pulls what is already known from Clio plus public signals, and produces the two or three specifics worth referencing.
Agent 1 of 3 in the Legal workflow.
- Passes a research note to the drafting agent.
- 02
Drafting agent
Trigger
A research note is ready
Writes the email against the legal messaging guide and the sender's own past emails, so it reads like the person it is from.
Agent 2 of 3 in the Legal workflow.
- Queues the draft for approval, or sends directly for approved segments.
- 03
Cadence agent
Trigger
A send completes, or a reply arrives
Schedules the next touch, spaces sends to protect the domain, and suppresses anyone with an open thread or a recent human conversation.
Agent 3 of 3 in the Legal workflow.
How they did it
From nothing to production in half a day.
No code, no IT ticket, no vendor implementation team. These are the steps in the order this team took them.
Step 01
Mapped the current workflow
Every step of the manual email outreach process, including exceptions — and which of them a person should keep.
Step 02
Built it in DeskFerry
Clio and DocuSign as sources, legal decision logic, automated actions and alerts.
Step 03
Ran it in parallel
One week alongside the manual process. Edge cases flagged for review rather than actioned.
The stack
Nothing was replaced. Everything was connected.
The legal team kept the tools they already ran — DeskFerry sits between them.
Clio
Matter, deadline, and document context, scoped per matter
LawPay
Billing and trust accounting events
DocuSign
Signature events that start the workflow the moment a deal is real
Google Drive
Document intake and the filing destination once processing is done
Slack
Where the team is told, and where approvals happen in one tap
Email Outreach handled end to end · higher, every time
What stayed human
The parts they deliberately did not automate.
Automating Email Outreach end to end was never the goal. Removing the volume so the judgement calls got proper attention was.
The first send to any new segment
New segments run in approval mode until the team has read fifty drafts and agrees the voice is right. Only then does that segment go to auto-send.
Anything that reads as a negotiation
Pricing, terms, and anything a reply turns into a commitment stops at the owner. The agent will draft it; it will not send it.
The client intake efficiency question
Asked first by every legal team. Agents run on the access the staff account already had, every action is logged, and any step can be stopped without unwinding what ran.
Takeaways
What transfers to your team.
The parts of this that are not specific to one company's tooling or volume.
- 01
The routine email outreach volume stopped needing a person. The judgement calls still get one.
- 02
Live in under a day — no IT queue, no development cycle.
- 03
Errors fell because validation runs before the write, not after.
- 04
It paid for itself on saved hours, not on a headcount cut.
In their words
“Before DeskFerry, our email outreach process was the bottleneck that every legal team complained about. Now it's our competitive advantage. We process faster, more accurately, and at a fraction of the cost. Our competitors are still doing this manually.”
Composite — written from what teams running this workflow report, not a single named customer.
FAQ
Questions people ask about this build.
Automating Email Outreach in legal — what it takes, and where it stops.
How long does it take to set up email outreach automation for a legal business?
This team was live in half a day. Pre-built legal templates cover the wiring, so most of that time goes on your business rules rather than on connecting things. No code.
How many AI agents does email outreach automation actually need?
3 here: research agent, drafting agent, cadence agent. The split matters more than the count — one job and one handoff each means a failure tells you which step broke. One agent doing everything does not.
What results can a legal business expect?
The figures here are directional, not audited — composite scenarios, not one customer's books. What transfers is the shape: routine volume stops needing a person, exceptions surface instead of sinking, and nothing waits for office hours. Your numbers depend on your volume and starting point.
How does DeskFerry handle legal data and access?
Agents run on the same access the staff account already had — throughput widens, permissions do not. Every action is logged with what it read and changed, and any step can be stopped without unwinding what ran. DeskFerry holds no formal legal certification, so scope it as you would any other system in your control environment.
What still needs a person?
More than most automation pages admit. Anything outside the rules stops and goes to a named owner with context attached, rather than being guessed at. The rules themselves are changed by people — agents never widen their own tolerances. The carve-outs this team kept are named above.
What tools does this connect to?
1,500+ integrations. This build used Clio, LawPay, DocuSign, Google Drive and Slack; most legal stacks are a variation on that. CRM, email, chat, databases, and industry-specific software all connect without code.
Run this in your own stack.
Describe how Email Outreach should work at your legal business, in a sentence. DeskFerry builds the agents, wires your tools, and takes the routine volume from there. Start free — no credit card.
Or start from a template — Email Outreach agent for Legal.
Keep exploring
Related case studies.
The same job in another industry, or another job in this one.
More Legal case studies
Email Outreach in other industries
Composite scenario — built from patterns across many legal Email Outreach deployments rather than one customer's books. Figures are directional; your own depend on your volume, process, and starting point.