Case study · Healthcare · Follow-Up
From Days to On schedule: Follow-Up in Healthcare
Follow-Up was the step everything else waited on. It now runs itself on the same stack — live in 2 hours, judgement calls still going to a person.
Time to Second Touch
A healthcare contact went quiet — handle the follow-up.
3 AI agents · 5 tools connected · live in 2 hours · no code
- Company
- Mid-size healthcare provider
- Team size
- 50-200 employees
- Industry
- Healthcare
- Time to live
- 2 hours
- Agents deployed
- 3 AI agents
- Tools connected
- 5 integrations
The context
Why Follow-Up is hard in healthcare.
Follow-Up is not hard in the abstract. It is hard in healthcare, where the work arrives as referral faxes, patient portal messages, phone calls, and EHR work queues — every channel a different shape, none of them waiting their turn. The team runs against the appointment book and the payer clock, so the real cost of a slow follow-up step is never the step. It is a record touched by the wrong hands, or a detail dropped between a referral and a chart.
Constraints the build had to hold
Protected health information
Agents were scoped to the records the staff account could already see. Throughput widened; access did not.
The EHR is the system of record
Nothing counts as done until it is in the chart. Agent queues are scratch space, never a second truth.
Clinical judgement stays human
Agents move information and prepare decisions. Anything clinical goes to a person with the context attached.
The change
Same job. Two chains.
Every handoff in the left-hand chain is somewhere Follow-Up used to wait. The right-hand chain has the same steps and none of the waiting.
By hand
- A promise is made on a callwritten in a notebook
- Nothing queries the notebookso nothing surfaces it
- Reminder set, then snoozedevery day for a week
- Thread goes cold
nobody notices which
With agents
- Work arrives on any channelpicked up in seconds
- Commitment agenthanded straight on
- Cadence agenthanded straight on
- Close-out agent
logged, and reviewable
When the work can happen
Before and after
What Follow-Up cost them, and what replaced it.
The challenge
Follow-up was where deals and commitments quietly died at this mid-size healthcare provider. Not because anyone was careless — because remembering who is owed what, across a 50-200 employees team and hundreds of open threads, is not something a person can do reliably alongside their actual job.
The full background
The pattern repeated weekly. A proposal went out and nothing happened for eleven days. A prospect asked for a call back and the note stayed in a notebook. A promise made on a Thursday call was never written down anywhere a system could see. Their healthcare sales cycle depended on persistence, and persistence was the thing least likely to survive a busy week. Calendar reminders had been tried and were snoozed into meaninglessness within a fortnight.
What they built
DeskFerry solved the part of follow-up that was never a discipline problem: knowing what is owed. Connected to Kareo, Epic, and the team's calendar, a commitment agent reads email, meeting notes, and CRM updates and extracts who owes what to whom by when — turning promises that lived in prose into a list something can query.
How it was wired
From there a cadence agent drafts each follow-up with the original thread attached, in the owner's voice, at the intervals the healthcare team agreed. Most go out on one tap. When a reply arrives the sequence stops automatically and the record updates, so nobody chases a person who already answered. The cadence has a hard end — deciding whether to reopen a dead thread stays a judgement call, and it stays with the owner.
The impact
What changed, measured the same way on both sides.
Before and after across the metrics that matter for healthcare Follow-Up.
Time to Second Touch
Never missed
Open Commitments Tracked
Full visibility
Untouched Pipeline
Major reduction
Follow-Up Coverage
Full coverage
Revenue Left on the Table
Meaningful impact
How these were measured
- Baseline
- The "before" column is the team’s own measurement of their manual follow-up 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 Follow-Up actually looked like for this healthcare team — the version they described in the first call, and the version they run now.
Before DeskFerry
9:00
Try to remember who is owed a reply. Search the inbox for clues.
11:00
Find a proposal sent eleven days ago with no follow-up.
14:00
Set three calendar reminders. Snooze all of them tomorrow.
16:00
A deal goes cold because the second touch never happened.
Friday
Half the healthcare pipeline has not been touched this week.
After DeskFerry
9:00
A single list: every open commitment, with the age of each one.
9:10
Drafts are ready for the ones due today, in your voice, with the thread attached.
11:00
Nothing is eleven days old — the cadence chased it at day three and day seven.
16:00
Replies reopen the thread and pause the sequence automatically.
Friday
Nothing in the pipeline went a week without a touch.
The build
The 3 agents that run it.
One job each, with an explicit handoff between them. Splitting Follow-Up 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
Commitment agent
Trigger
An email, meeting note, or CRM update mentions a promise
Extracts who owes what to whom by when, across the shared inbox and Epic, and keeps one list of open loops.
Agent 1 of 3 in the Healthcare workflow.
- Feeds the open-loop list to the cadence agent.
- 02
Cadence agent
Trigger
A commitment ages past its threshold
Drafts the follow-up with the original thread attached, in the owner's voice, at the intervals the healthcare team agreed.
Agent 2 of 3 in the Healthcare workflow.
- Queues for one-tap send, or sends on approved cadences.
- 03
Close-out agent
Trigger
A reply arrives, or a commitment is met
Closes the loop, pauses the sequence, and updates the record so nothing chases a person who already answered.
Agent 3 of 3 in the Healthcare workflow.
How they did it
From nothing to production in 2 hours.
No code, no IT ticket, no vendor implementation team. These are the steps in the order this team took them.
Step 01
Connected the healthcare stack
Epic, Cerner, and Athenahealth via pre-built connectors. No API keys, no custom code.
Step 02
Wrote the business rules
Scoring, routing, escalation thresholds, and exception handling for healthcare follow-up — in the visual builder.
Step 03
Tested on real history
Replayed a week of past follow-up to check accuracy and surface edge cases, then adjusted the weights.
Step 04
Launched and watched
Live with close oversight for 48 hours, then down to a weekly review.
The stack
Nothing was replaced. Everything was connected.
The healthcare team kept the tools they already ran — DeskFerry sits between them.
Epic
The chart — read for context, and written back so it stays the record
Cerner
Second system of record; reconciled against the chart before any write
Athenahealth
Scheduling, billing, and clinical work queues
Kareo
Practice management, scheduling, and claim state
Google Forms
Structured intake so the first agent starts from clean fields
Follow-Up handled end to end · on schedule, every time
What stayed human
The parts they deliberately did not automate.
Automating Follow-Up end to end was never the goal. Removing the volume so the judgement calls got proper attention was.
The tone of a chase
Drafts arrive in the owner’s voice, and the owner reads them. A follow-up that lands wrong costs more than one that lands late.
When to stop
The cadence has a hard end. Deciding whether an unanswered thread is worth reopening is a judgement call, and it stays one.
The patient data security question
Asked first by every healthcare 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
No technical expertise needed — the people who own the follow-up process built it.
- 02
Capacity scaled without headcount, which changed the unit economics.
- 03
Every decision is logged, so the workflow can be audited rather than trusted.
- 04
Leadership got follow-up numbers in real time for the first time.
In their words
“The ROI came quickly. Our follow-up throughput increased significantly while our error rate dropped dramatically. For a healthcare business of our size, that translates directly to the bottom line.”
Composite — written from what teams running this workflow report, not a single named customer.
FAQ
Questions people ask about this build.
Automating Follow-Up in healthcare — what it takes, and where it stops.
How long does it take to set up follow-up automation for a healthcare business?
This team was live in 2 hours. Pre-built healthcare 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 follow-up automation actually need?
3 here: commitment agent, cadence agent, close-out 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 healthcare 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 healthcare 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 healthcare 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 Epic, Cerner, Athenahealth, Kareo and Google Forms; most healthcare 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 Follow-Up should work at your healthcare 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 — Follow-Up agent for Healthcare.
Keep exploring
Related case studies.
The same job in another industry, or another job in this one.
More Healthcare case studies
Follow-Up in other industries
Composite scenario — built from patterns across many healthcare Follow-Up deployments rather than one customer's books. Figures are directional; your own depend on your volume, process, and starting point.