How we help you compare health plans
Choosing a health plan means weighing premiums, deductibles, and copays against how much care you actually expect to use. Here's a plain-language look at what Coverage Companion does to help with that — without diving into the internals.
The Companion Chat
The chat assistant is powered by Claude by Anthropic, a large language model. It's designed for educational conversations about health insurance concepts — not to give medical, legal, or financial advice.
The chat can ground its answers in real plan data when it's helpful — looking up a specific benefit or estimating a premium — but your profile for the Confidence Engine always comes from the explicit questions you answer on the Engine page, not from anything you say in chat.
Constraints: The chat provides educational guidance only. It is not instructed to recommend a specific plan or diagnose conditions or advise on medical treatment. Always verify coverage details with your insurer or HR.
Estimated Out-of-Pocket Costs
For each plan, the engine estimates what you'd likely pay out of pocket over a year under three scenarios — light, moderate, and heavy use of care — based on national healthcare usage patterns. For plans in our database, those estimates are also adjusted for regional cost differences, so the same plan can show a different expected cost depending on where you live. Plans you upload or enter manually use the national baseline.
These are educational estimates built from aggregate national data, not a bill or a guarantee — your actual costs depend on your specific providers and claims.
The Confidence Score
Each plan you compare gets a Confidence Score from 0–100, meant to summarize how well it fits your situation in a single number. It weighs a few things together: how cost-efficient the plan is relative to your other options, how much protection it gives you against a bad year, how predictable your costs are likely to be, and how well its coverage matches the specific care needs you told us about.
The balance between those factors shifts based on your own priorities — for example, someone optimizing for the lowest monthly premium gets a different emphasis than someone who wants to minimize worst-case risk. The score is a decision aid, not a definitive ranking — we'd encourage you to read the plan details behind any score before deciding.
Behavioral Insights
Health insurance decisions are vulnerable to a few predictable mental shortcuts — like anchoring too heavily on the monthly premium, or underestimating how likely an expensive year actually is. When the engine notices a pattern like that in the plans you're comparing, it surfaces a short, plain-language nudge alongside your results — not to second-guess you, but to make sure the tradeoff you're making is one you're making on purpose.
⚠️ Educational simulation — not financial advice
Coverage Companion is an educational tool. The cost simulations use benchmark utilization data — not your actual claims history. Scores reflect relative plan performance under assumed scenarios and should not be the sole basis for a coverage decision. Actual costs will differ based on your providers, claims history, and plan-specific rules. Always verify details with your insurer or a licensed benefits advisor.