Case study · Healthcare · Report Generation
From A full day to Automatic: Report Generation in Healthcare
Report Generation was the step everything else waited on. It now runs itself on the same stack — live in 3 hours, judgement calls still going to a person.
Report Build Time
Build this week's healthcare report.
Key metric · Healthcare. Compiled from your connected tools and shared automatically.
Google FormsSlackGmail3 AI agents · 5 tools connected · live in 3 hours · no code
- Company
- Multi-location health clinic
- Team size
- 50-200 employees
- Industry
- Healthcare
- Time to live
- 3 hours
- Agents deployed
- 3 AI agents
- Tools connected
- 5 integrations
The context
Why Report Generation is hard in healthcare.
Report Generation 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 report generation 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 Report Generation used to wait. The right-hand chain has the same steps and none of the waiting.
By hand
- Export from four systemseach counting things differently
- Pasted into a master sheetone renamed column breaks it
- Reconciled by handa full analyst day
- Sent Monday afternoon
already several days old
With agents
- Work arrives on any channelpicked up in seconds
- Collection agenthanded straight on
- Analysis agenthanded straight on
- Narrative agent
logged, and reviewable
When the work can happen
Before and after
What Report Generation cost them, and what replaced it.
The challenge
Reporting consumed the first day of every week at this multi-location health clinic. Exports from four systems, pasted into a master spreadsheet, reconciled by hand because each source counted things slightly differently, then formatted into the deck leadership expected by Monday afternoon.
The full background
It was fragile in the way all spreadsheet pipelines are fragile. A renamed column upstream broke a formula silently. Two sources disagreeing meant starting again from raw pulls. And by the time the healthcare report was distributed, the numbers in it were already several days old — which meant the meeting it drove was a discussion of last week rather than a decision about this one. With 50-200 employees, that was a full analyst-day gone weekly to work that produced no new insight, only new formatting.
What they built
The team used DeskFerry to move reporting off spreadsheets entirely. A collection agent pulls from every connected source — Epic, a shared sheet, and finance — and reconciles them onto one set of definitions, which is where the arguments about whose number was right used to start.
How it was wired
An analysis agent then computes the healthcare metrics, compares against prior periods and targets, and works out which movements are worth a sentence. A narrative agent writes that summary in plain language, links each figure back to its source, and delivers to the channel the audience already reads — before anyone opens a laptop on Monday. Schema changes upstream are caught by validation rather than by a silently broken formula, and a figure outside its expected band holds the report and alerts the owner instead of publishing a number that has to be walked back.
The impact
What changed, measured the same way on both sides.
Before and after across the metrics that matter for healthcare Report Generation.
Report Build Time
Analyst day returned
Data Freshness
Near real-time
Metric Disputes
Definitions settled
Ad-Hoc Question Turnaround
Dramatically faster
Reporting Cost
Major savings
How these were measured
- Baseline
- The "before" column is the team’s own measurement of their manual report generation 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 Report Generation actually looked like for this healthcare team — the version they described in the first call, and the version they run now.
Before DeskFerry
Monday 9:00
Export from four systems. Paste into the master sheet.
Monday 11:30
A column moved in one export. Fix the formulas.
Monday 14:00
Numbers do not tie. Start again from the raw pulls.
Monday 17:00
Send the deck. Two figures are already stale.
Tuesday
Someone asks why the healthcare number differs from last week's.
After DeskFerry
Monday 7:00
The report is compiled and in the channel before anyone opens a laptop.
Monday 9:00
Read the summary. The movements are already called out in words.
Monday 11:30
Schema changes were caught by validation, not by a broken formula.
Monday 14:00
Spend the afternoon on what the numbers mean.
Tuesday
Every figure traces to its source with one click.
The build
The 3 agents that run it.
One job each, with an explicit handoff between them. Splitting Report Generation 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
Collection agent
Trigger
The reporting window opens
Pulls from every connected source — Epic, the reporting sheet, finance — and reconciles them onto one set of definitions.
Agent 1 of 3 in the Healthcare workflow.
- Passes a validated dataset to analysis.
- 02
Analysis agent
Trigger
A dataset is validated
Computes the healthcare metrics, compares against prior periods and targets, and identifies which movements are worth a sentence.
Agent 2 of 3 in the Healthcare workflow.
- Hands findings, not just figures, to the narrative agent.
- 03
Narrative agent
Trigger
Analysis completes
Writes the summary in plain language, links each figure back to its source, and delivers to the channel the audience already reads.
Agent 3 of 3 in the Healthcare workflow.
How they did it
From nothing to production in 3 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 report generation — in the visual builder.
Step 03
Tested on real history
Replayed a week of past report generation 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
Report Generation handled end to end · automatic, every time
What stayed human
The parts they deliberately did not automate.
Automating Report Generation end to end was never the goal. Removing the volume so the judgement calls got proper attention was.
The interpretation
The narrative agent describes what moved. What it means, and what to do about it, is written by the person presenting it.
Anomalies
A figure outside its expected band holds the report and alerts the owner, rather than publishing a number that will have to be walked back.
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 report generation 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 report generation numbers in real time for the first time.
In their words
“We went from spending half our day on report generation to having it just happen automatically. The AI agents handle the routine work perfectly, and our healthcare team can focus on the strategic decisions that actually move the needle. I wish we had done this a year ago.”
Composite — written from what teams running this workflow report, not a single named customer.
FAQ
Questions people ask about this build.
Automating Report Generation in healthcare — what it takes, and where it stops.
How long does it take to set up report generation automation for a healthcare business?
This team was live in 3 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 report generation automation actually need?
3 here: collection agent, analysis agent, narrative 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 Report Generation 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 — Report Generation agent for Healthcare.
Keep exploring
Related case studies.
The same job in another industry, or another job in this one.
More Healthcare case studies
Report Generation in other industries
Composite scenario — built from patterns across many healthcare Report Generation deployments rather than one customer's books. Figures are directional; your own depend on your volume, process, and starting point.