Case study · Insurance · Content Creation
How a insurtech company took time to first draft from days to hours
A insurtech company of 30-150 employees moved content creation off a manual queue and onto agents that run it continuously. The build, the numbers, and what stayed human.
Time to First Draft
A insurance contact went quiet — handle the content creation.
3 AI agents · 5 tools connected · live in half a day · no code
- Company
- Insurtech company
- Team size
- 30-150 employees
- Industry
- Insurance
- Time to live
- Half a day
- Agents deployed
- 3 AI agents
- Tools connected
- 5 integrations
The context
Why Content Creation is hard in insurance.
Nothing about content creation 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 Content Creation used to wait. The right-hand chain has the same steps and none of the waiting.
By hand
- Topic picked from the planthen the blank page
- Research, hours of itfor four hundred words
- Rewritten to sound like the branda second full pass
- One piece ships
the other three slip
With agents
- Work arrives on any channelpicked up in seconds
- Brief agenthanded straight on
- Draft agenthanded straight on
- Repurpose agent
logged, and reviewable
When the work can happen
Before and after
What Content Creation cost them, and what replaced it.
The challenge
Content at this insurtech company was expensive, slow, and inconsistent in voice. Freelancers needed heavy briefing and produced work that had to be substantially rewritten to sound like the brand. In-house drafts were better but arrived a fortnight late, because the people who could write them had insurance day jobs.
The full background
The deeper problem was that every piece started from nothing. No shared research, no reusable structure, no way to turn one good article into the five formats other channels needed. So a piece that took two days produced two days of value and then sat there. With 30-150 employees, the organisation was paying full price for content and capturing a fraction of what each piece could have returned.
What they built
Content moved from heroic effort to a running process. Applied Epic, Gmail, and the team's docs were connected to DeskFerry, and the insurance content calendar became the trigger rather than a wish list.
How it was wired
Each slot now produces a briefed, sourced draft on schedule. The writer's hour goes into judgement, opinion, and voice instead of into research and structure, which is both a better use of the hour and the reason the pieces got better rather than merely more frequent. Claims are checked against the source the brief collected, and unsourced assertions are cut rather than softened. Freelance spend dropped because the briefing overhead that made freelancers expensive was the thing that got automated.
The impact
What changed, measured the same way on both sides.
Before and after across the metrics that matter for insurance Content Creation.
Time to First Draft
Dramatically faster
Pieces Published
Significant increase
Voice Consistency
Notable improvement
Formats per Piece
More value per piece
Cost per Piece
Major savings
How these were measured
- Baseline
- The "before" column is the team’s own measurement of their manual content creation 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 Content Creation actually looked like for this insurance team — the version they described in the first call, and the version they run now.
Before DeskFerry
9:00
Open a blank document. Close it. Open the calendar instead.
11:00
Research for two hours to write four hundred words.
14:00
Rewrite it to sound like the brand rather than like the research.
16:30
Publish one piece. The other three slip another week.
Month end
The insurance content plan is a third done.
After DeskFerry
9:00
Briefed drafts are waiting, each with sources and an outline already agreed.
10:00
Edit for judgement and voice — the structural work is done.
14:00
Repurposed variants for other channels are generated from the approved piece.
16:30
Three pieces ship, not one.
Month end
The plan is complete and the backlog is ideas, not drafts.
The build
The 3 agents that run it.
One job each, with an explicit handoff between them. Splitting Content Creation 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
Brief agent
Trigger
A topic enters the calendar
Researches the insurance angle, gathers sources, and produces an outline with the argument already settled.
Agent 1 of 3 in the Insurance workflow.
- Sends the brief for a quick human yes or no.
- 02
Draft agent
Trigger
A brief is approved
Writes to the outline in the brand voice, keeping claims tied to the sources the brief collected.
Agent 2 of 3 in the Insurance workflow.
- Hands an editable draft to the writer, not a finished piece.
- 03
Repurpose agent
Trigger
A piece is published
Cuts it into the formats other channels need and files everything back to the content library.
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 content creation 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
Content Creation handled end to end · hours, every time
What stayed human
The parts they deliberately did not automate.
Automating Content Creation end to end was never the goal. Removing the volume so the judgement calls got proper attention was.
Every published word
Nothing publishes without a human edit. The drafting agent removes the blank page and the structural work; the judgement, the opinion, and the voice are added by a writer.
Claims and figures
Anything asserting a fact is checked against the source the brief collected. Unsourced claims are cut rather than softened.
The fraud prevention 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
The routine content creation 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
“The ROI came quickly. Our content creation throughput increased significantly while our error rate dropped dramatically. For a insurance 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 Content Creation in insurance — what it takes, and where it stops.
How long does it take to set up content creation 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 content creation automation actually need?
3 here: brief agent, draft agent, repurpose 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 Content Creation 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 — Content Creation agent for Insurance.
Keep exploring
Related case studies.
The same job in another industry, or another job in this one.
More Insurance case studies
Content Creation in other industries
Composite scenario — built from patterns across many insurance Content Creation deployments rather than one customer's books. Figures are directional; your own depend on your volume, process, and starting point.