cd /news/artificial-intelligence/i-built-an-ai-agent-fleet-that-fight… · home topics artificial-intelligence article
[ARTICLE · art-107975] src=dev.to ↗ pub= topic=artificial-intelligence verified=true sentiment=↑ positive

I Built an AI Agent Fleet That Fights Your Insurance Company for You

A developer built DenialDefender, an 8-agent AI fleet that automates the preparation and verification of health insurance claim appeals, with human authorization as a mandatory final step. The system uses Google ADK and Gemini 3.6 Flash to classify denials, gather evidence, and draft appeal letters, while enforcing a strict 'AI prepares, AI verifies, human authorizes' boundary. The project includes three evaluation harnesses and transparent labeling of synthetic data to ensure trustworthiness.

read2 min views1 publishedAug 23, 2026

Every year, 1 in 7 insured Americans has a health insurance claim denied.

The denial letter isn't the hard part. What comes after is: someone, usually a medical billing specialist, not a doctor, not a lawyer, has to read the denial, decode the reason code, dig through payer policy, track down clinical evidence, draft an appeal, check every citation by hand, watch the deadline, and get it submitted before the window closes.

That's hours of procedural work standing between a patient and care they were already supposed to get.

Where should an AI agent stop in an enterprise workflow?

Not "how autonomous can I make this." A narrower, harder question: where does preparation end and a human decision begin?

The answer I landed on became the whole architecture:

AI prepares. AI verifies. Human authorizes.

That boundary, not the model and not the agent count, is the actual product. Everything else exists to make that boundary enforceable.

DenialDefender is an 8-agent Google ADK fleet that runs an insurance denial through a governed pipeline instead of a single prompt.

Agent Job
Patient Advocate Intake, urgency, deadline extraction
Denial Triage Reason-code classification, appealability assessment (Gemini 3.6 Flash)
Policy Research Payer policy contradiction retrieval
Evidence Assembly Clinical evidence with provenance tiers
Citation Verification Citation resolution and SHA-256 hash matching
Letter Drafting Evidence-grounded appeal letter with inline citations (Gemini 3.6 Flash)
Quality Review Adversarial 7-check battery that refuses to pass until every claim is grounded
Deadline Tracker Deadline monitoring and escalation

Two human-in-the-loop gates sit inside that pipeline. Gate 1: a human confirms the triage before research begins. Gate 2: a human approves the final letter before it's submitted. No letter reaches a payer without explicit human sign-off.

Two agents in the fleet do the real reasoning, and both run on Gemini 3.6 Flash via the Vertex AI global endpoint. Denial Triage classifies the denial and estimates appeal success. Letter Drafting generates the appeal letter itself, with citations that resolve back to hashed evidence. Take away Gemini 3.6 Flash and those two agents have nothing to reason with.

Trust isn't a claim here. It's four mechanisms, each with an auditable proof:

I built three evaluation harnesses instead of just asserting the system works.

Honesty is an asset, not a liability.

The outcome-learning dataset uses 5 public records and 45 synthetic ones. I labeled it that way instead of presenting all 50 as real. The GEAP components report backend=local

honestly instead of hiding it. Every one of those choices made the architecture stronger, because the claim can be independently checked against the underlying evidence.

AI prepares. AI verifies. Human authorizes.

── more in #artificial-intelligence 4 stories · sorted by recency
── more on @denialdefender 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
Live at https://your-agent.zahid.host
Get free account → Pricing
from €0/mo · no card required
LIVE [news/i-built-an-ai-agent-…] indexed:0 read:2min 2026-08-23 ·