Healthcare AI infrastructure
Inference Analytics is building the secure AI infrastructure for healthcare—turning sensitive enterprise data into intelligent agents, automated workflows, and trusted decisions. We began generating healthcare text years before ChatGPT and today deploy enterprise AI across leading health systems.
Secure AI. Healthcare-native. Built for real-world deployment.
Platform-wide across all deployments, as of May 2026. Years of R&D covers the founding team’s combined AI research and deployment work, before the June 2025 production launch.
The Inference Platform
From building secure agents to operationalizing payer workflows, our platform brings governed AI into the work that matters.
A no-code development platform for building and managing healthcare AI agents and applications across multiple models.
An end-user, multi-model platform that brings leading generative AI models into one governed experience.
Healthcare AI agents that automate payer workflows, denial appeals, and CPT policy lookups.
No-code AI development
Move from a governed knowledge source to a production-ready agent through one visual development environment. Teams can orchestrate RAG, models, safeguards, and deployment stages without stitching together disconnected tools.
Place the steps, wire them up, pick a model, ship the endpoint.
02Drag the flow together: ingestion, redaction, chunking, retrieval.
03Choose the embedding model and build the vector store behind it.
Scroll to explore
Unified AI experience
Give teams a consistent, governed interface for generative AI — while preserving the freedom to choose the right model, agent, and enterprise data source for each task.
Ask three models at once, then reconcile them into one answer.
02Ask several models the same question, then fuse the answers into one.
03Describe the topic, pick a template, get the finished deck.
Scroll to explore
Intelligent revenue cycle
Purpose-built payer agents understand policy language, CPT requirements, and appeal context — helping revenue-cycle teams move faster while keeping every decision reviewable.
01Every chat scoped to one payer's own policy library.
02CPT checks, appeal letters and eligibility, in one place.
03Answers carrying the payer's own requirements, cited to source.
04Pick the payers, paste the context, get a cited appeal letter.
Scroll to explore
About us
We work inside the constraints healthcare actually has: protected data, audited workflows and clinical accountability. The platform is engineered so enterprise teams can adopt AI without trading away security or governance — it deploys inside your own cloud, and models are reached only at the API level under a business associate agreement.
8+
Years of R&D before we productized anything
4x
User growth since the June 2025 launch
Inference Analytics is a healthcare AI company. It builds and operates the InferAgents Suite, a HIPAA-compliant agentic AI product suite used by health systems and academic medical centres. The suite is live inside University of Chicago Medicine and Mayo Clinic.
The InferAgents Suite is the product suite built by Inference Analytics, and the company's only top-level product. It contains individual products — Inferch and PayerAgents among them — plus Dev Studio, the interface health-system IT teams use to build their own agents. Everything in the suite runs on one HIPAA-compliant core and connects to models only at the API level. The short form InferAgents refers to the same suite.
Inferch, the multi-model application clinical and operational staff work in, and PayerAgents, which handles payer policy intelligence and appeal automation. Each has its own site and its own buyer, and both inherit the suite's compliance boundary rather than implementing their own. Further products are added to the suite over time.
Neither. PayerAgents is a product within the InferAgents Suite, built by Inference Analytics. It has its own domain at payeragents.ai and serves US private practices rather than health systems, but it is part of the suite and shares its compliant core.
Dev Studio is the development interface of the InferAgents Suite — the environment where health-system engineering teams build, test and ship agents. It is not a product, is not licensed or deployed separately, and should never be listed alongside the suite's products.
Yes. Every product in the InferAgents Suite, and every agent built in Dev Studio, inherits the same HIPAA-compliant core: PHI stays inside the compliance boundary, models are connected only at the API level under a business associate agreement, and all activity is written to an auditable log. See the security and compliance page for the full position.
The InferAgents Suite deploys inside the health system's own cloud. Protected health information and institutional knowledge stay within the organisation's own boundary rather than being transferred to a vendor tenant. Model providers are reached only at the API level under a business associate agreement, and the prompts, retrieved context and outputs are logged inside that same boundary.
The team was generating healthcare text before ChatGPT existed. Its peer-reviewed work on generating radiology report impressions went to IEEE Xplore early access in June 2021 — around eighteen months before ChatGPT's public launch — and appeared in IEEE Transactions on Artificial Intelligence in August 2023. The founding team's combined AI research and deployment work spans more than eight years.
The InferAgents Suite is model-agnostic. It orchestrates across OpenAI, Anthropic and Google models as well as a health system's own internal or self-hosted models, connected only at the API level. An agent is built once against the suite's interfaces, so the underlying model can change without rebuilding the agent.
The suite is live inside University of Chicago Medicine, where it serves both end-user applications and the health system's own IT agent development, and inside Mayo Clinic. Akron Children's, CHOP and Motorola are following the same land-and-expand path.
Bring trusted AI into healthcare operations. Talk with our team about deployment, governance and the workflows you want to automate first.