Case study · Insurance · Report Generation
Insurance Report Generation: A full day → Automatic
The whole build: 3 ai agents, 5 tools, and the before-and-after on metrics the team already tracked.
Report Build Time
Build this week's insurance report.
Key metric · Insurance. Compiled from your connected tools and shared automatically.
SalesforceDocuSignGmail3 AI agents · 5 tools connected · live in half a day · no code
- Company
- Insurtech company
- Team size
- 20-100 employees
- Industry
- Insurance
- Time to live
- Half a day
- Agents deployed
- 3 AI agents
- Tools connected
- 5 integrations
The context
Why Report Generation is hard in insurance.
Nothing about report generation is complicated on a single instance. What makes it expensive in insurance is volume arriving through submissions, ACORD forms, carrier portals, claims notices, and renewal lists, against the renewal date and the claims service standard. Miss the window and the cost is not the minutes — it is a renewal that lapses because a form sat in someone’s inbox.
Constraints the build had to hold
Forms are structured, and messy
Extraction is checked against each form type’s expected schema. Failures escalate rather than get guessed at.
Carrier rules differ
Each carrier gets its own branch inside one pipeline, rather than a pipeline nobody maintains.
Coverage decisions stay licensed
Anything constituting advice or a coverage determination is prepared for a licensed producer, never issued.
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
Nobody at this insurtech company trusted the reports, and everyone knew why. The same metric came out differently depending on who pulled it, because the definitions lived in individual spreadsheets rather than anywhere shared. Every leadership meeting spent its first fifteen minutes arguing about whether the numbers were right.
The full background
Building them was worse than reading them. Their 20-100 employees team pulled insurance data from systems that did not agree on customer identity, date boundaries, or currency handling, and reconciled the differences manually each cycle. Ad-hoc questions — the ones that actually mattered — were quoted at two days because that was how long the pull took. So most of them were never asked, and decisions got made on instinct instead.
What they built
Reporting was rebuilt around definitions rather than exports. The team connected Applied Epic and Google Sheets to DeskFerry and wrote each insurance metric down once — what it counts, which source owns it, how the period boundary works.
How it was wired
Everything downstream follows from that. The same numbers come out regardless of who asks, ad-hoc questions are answered in minutes rather than quoted at two days, and every figure in the summary traces to its source in one click. The analyst day that used to go on pulling, pasting, and reconciling now goes on the part of the job that needed a person: deciding what the movement means and what to do about it. Interpretation was deliberately left with the human presenting the report.
The impact
What changed, measured the same way on both sides.
Before and after across the metrics that matter for insurance 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 insurance 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 insurance 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 — Applied Epic, Google Sheets, finance — and reconciles them onto one set of definitions.
Agent 1 of 3 in the Insurance workflow.
- Passes a validated dataset to analysis.
- 02
Analysis agent
Trigger
A dataset is validated
Computes the insurance metrics, compares against prior periods and targets, and identifies which movements are worth a sentence.
Agent 2 of 3 in the Insurance 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 Insurance 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 report generation process, including exceptions — and which of them a person should keep.
Step 02
Built it in DeskFerry
Applied Epic and DocuSign as sources, insurance 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 insurance team kept the tools they already ran — DeskFerry sits between them.
Applied Epic
Policy, submission, and renewal state
Salesforce
System of record for accounts and pipeline; every write is scoped to owned fields
DocuSign
Signature events that start the workflow the moment a deal is real
Gmail
Where the work arrives, and where drafted replies go back out
Google Sheets
The lightweight ledger the team already reads, kept current automatically
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 claims processing speed question
Asked first by every insurance 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
Connecting the existing insurance stack beat replacing it.
- 02
Backlogs went away because the work no longer waits for office hours.
- 03
Quality stopped varying by whoever picked the task up.
- 04
Starting from a template and tightening the rules weekly beat designing it upfront.
In their words
“Before DeskFerry, our report generation process was the bottleneck that every insurance 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 Report Generation in insurance — what it takes, and where it stops.
How long does it take to set up report generation automation for a insurance business?
This team was live in half a day. Pre-built insurance 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 insurance 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 insurance 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 insurance 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 Applied Epic, Salesforce, DocuSign, Gmail and Google Sheets; most insurance 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 insurance 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 Insurance.
Keep exploring
Related case studies.
The same job in another industry, or another job in this one.
More Insurance case studies
Report Generation in other industries
Composite scenario — built from patterns across many insurance Report Generation deployments rather than one customer's books. Figures are directional; your own depend on your volume, process, and starting point.