Case study · Insurance · Resume Screening
From Over a week to Hours: Resume Screening in Insurance
Resume Screening 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.
Time to First Screen
New candidate just applied — screen them.
Taylor Brooks
Applicant · Insurance · role rubric
ICP fit
3 AI agents · 5 tools connected · live in 3 hours · no code
- Company
- Multi-line insurance firm
- Team size
- 15-80 employees
- Industry
- Insurance
- Time to live
- 3 hours
- Agents deployed
- 3 AI agents
- Tools connected
- 5 integrations
The context
Why Resume Screening is hard in insurance.
Resume Screening is not hard in the abstract. It is hard in insurance, where the work arrives as submissions, ACORD forms, carrier portals, claims notices, and renewal lists — every channel a different shape, none of them waiting their turn. The team runs against the renewal date and the claims service standard, so the real cost of a slow resume screening step is never the step. 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 Resume Screening used to wait. The right-hand chain has the same steps and none of the waiting.
By hand
- Applications stack uphundreds on one opening
- Read in whatever gaps existoften not for days
- Judged against a drifting bardifferently at forty than at four
- Shortlist emailed
everyone else hears nothing
With agents
- Work arrives on any channelpicked up in seconds
- Parsing agenthanded straight on
- Scoring agenthanded straight on
- Coordination agent
logged, and reviewable
When the work can happen
Before and after
What Resume Screening cost them, and what replaced it.
The challenge
Hiring at this multi-line insurance firm was gated on one step: somebody reading applications. A single insurance opening drew hundreds, and reviewing them fell to a hiring manager with a full workload, which meant it happened in gaps and often not for days.
The full background
The delay cost them candidates. Strong applicants accepted other offers while their application sat unopened. Worse, quality drifted: the rubric a reviewer applied at application forty was not the one they applied at application four. Candidates who did not progress heard nothing at all, which was both unkind and expensive in a market where the same people apply again later. With 15-80 employees, the team was carrying the cost of open roles far longer than the pipeline justified.
What they built
DeskFerry took the queue out of hiring. A parsing agent reads every application whatever its layout and extracts experience and skills as structured evidence. A scoring agent evaluates it against the rubric the insurance hiring manager signed off, and cites the evidence behind each sub-score rather than returning a bare number.
How it was wired
That citation is what made the process defensible: a reviewer can see exactly which line of a resume mapped to which requirement. Recruiters still review the band just below the cut, because that is where a strong candidate with an unusual background sits. A coordination agent books screens from live availability without an email thread, and sends every applicant an outcome — including the ones who did not progress, which had simply never happened before. Connected tools: Applied Epic, Gmail, and the calendar.
The impact
What changed, measured the same way on both sides.
Before and after across the metrics that matter for insurance Resume Screening.
Time to First Screen
Dramatically faster
Applications Reviewed
Full coverage
Scoring Consistency
Significant improvement
Candidates Who Hear Back
Full coverage
Cost per Hire
Major savings
How these were measured
- Baseline
- The "before" column is the team’s own measurement of their manual resume screening 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 Resume Screening actually looked like for this insurance team — the version they described in the first call, and the version they run now.
Before DeskFerry
8:30
Two hundred applications on an open role. Start at the top.
10:00
Skim forty. Realise the rubric drifted somewhere around fifteen.
13:00
A strong candidate from Tuesday has already taken another offer.
15:00
Schedule screens by email. Four threads, no confirmations.
Friday
The insurance req is still open and the pipeline is stale.
After DeskFerry
8:30
Applications are scored against the same rubric, every one of them.
8:35
The shortlist has evidence attached: which requirement each answer maps to.
10:00
Every applicant heard back within the day, including the declines.
15:00
Screens are booked from live availability without an email thread.
Friday
Time-to-first-screen is measured in hours instead of weeks.
The build
The 3 agents that run it.
One job each, with an explicit handoff between them. Splitting Resume Screening 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
Parsing agent
Trigger
An application is submitted
Reads the resume whatever its layout, extracts experience and skills as structured evidence, and normalises titles across formats.
Agent 1 of 3 in the Insurance workflow.
- Passes a structured profile to scoring.
- 02
Scoring agent
Trigger
A profile is parsed
Scores against the role rubric the insurance hiring manager signed off, and cites the evidence behind every sub-score.
Agent 2 of 3 in the Insurance workflow.
- Shortlists with reasoning attached; nothing is scored on a hunch.
- 03
Coordination agent
Trigger
A candidate is shortlisted or declined
Books screens from live availability and sends every applicant an outcome, including the ones who did not progress.
Agent 3 of 3 in the Insurance 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 insurance stack
Applied Epic, Salesforce, and DocuSign via pre-built connectors. No API keys, no custom code.
Step 02
Wrote the business rules
Scoring, routing, escalation thresholds, and exception handling for insurance resume screening — in the visual builder.
Step 03
Tested on real history
Replayed a week of past resume screening 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 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
Resume Screening handled end to end · hours, every time
What stayed human
The parts they deliberately did not automate.
Automating Resume Screening end to end was never the goal. Removing the volume so the judgement calls got proper attention was.
Every rejection above the line
The rubric shortlists; a recruiter reviews the band just below the cut, because that is where a good candidate with an unusual background sits.
The rubric
Hiring managers own the criteria and the weights, and review them per role. An agent scoring against a stale rubric is worse than no agent.
The policy renewal rates 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
No technical expertise needed — the people who own the resume screening 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 resume screening numbers in real time for the first time.
In their words
“The difference is night and day. Our insurance clients used to wait days for resume screening to be completed. Now it happens in minutes, and the quality is consistently higher than what we achieved manually. Customer satisfaction scores went through the roof.”
Composite — written from what teams running this workflow report, not a single named customer.
FAQ
Questions people ask about this build.
Automating Resume Screening in insurance — what it takes, and where it stops.
How long does it take to set up resume screening automation for a insurance business?
This team was live in 3 hours. 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 resume screening automation actually need?
3 here: parsing agent, scoring agent, coordination 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 Resume Screening 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 — Resume Screening agent for Insurance.
Keep exploring
Related case studies.
The same job in another industry, or another job in this one.
More Insurance case studies
Resume Screening in other industries
Composite scenario — built from patterns across many insurance Resume Screening deployments rather than one customer's books. Figures are directional; your own depend on your volume, process, and starting point.