What’s happening at Performance Home Medical?

Performance Home Medical runs a high-volume intake and customer service operation as a respiratory and sleep medical equipment supplier. Their Director of Intake, Ben Hauge, manages a mix of remote and on-site teams responsible for processing hundreds of incoming orders daily. Before Tennr, checking for accuracy and ensuring teams were operating error-free was a slow, manual, and reactive process. They relied on internal audits, denials, and one-off reviews to catch mistakes and keep up the quality in their processes. This meant delays, training & onboarding bottlenecks, and extra staff hours to keep quality high.

Tennr’s Autopilot feature, with built-in quality control, changed that.

Performance Home Medical compared August through October 2025 to the same period in 2025 and saw an 18% increase in orders output, all while operating with 29% fewer staff members dedicated to that process than the prior year. That’s a 65% productivity increase per team member. All with the help of fully automated data entry fields.

The efficiency gains also strengthened their ability to stay responsive to referring providers, keep documentation complete, and move patients through the pipeline without delays.

“Even on a busy day, my process is current. I’m within an hour all day, every day” - Ben Hauge, Director of Intake

How did they do it?

Cutting Workload Without Cutting Quality

When working with inbound documents and automating data entry, teams need a way to make sure that the information going into their systems is correct every time. And whether that’s an automated system doing that or a human reviewer, you want to make sure you’re getting it right every time.

Performance Home Medical needed a way to ensure they could speed through the process while maintaining the highest quality. There was no method for monitoring how teams were performing when it came to getting the right information, how data was flowing, and how often costly errors were going undetected.

Within months of using Tennr's Autopilot and Quality Control suite, Performance Home Medical was able to monitor the performance of Tennr’s ML models and the performance of their team members working with Tennr to reduce the intake team’s overall time spent by 29% and improve their order processing accuracy at the same time.

With autopilot, Tennr reads their inbound documents and updates patient information in their systems, eliminating 12 data entry points in Performance Home Medical’s process, which now run fully autonomously. Every time an employee doesn’t need to manually review and enter that patient data, hours are saved weekly.

Their document classification queue, which feeds every downstream operation with over 17,000 inbound faxes per month, now stays current within one hour, even on days where the team processes more than 860 incoming documents.

Staff Ramp Time Cut in Half

Beyond efficiency and accuracy gains, Quality Control has also cut Performance Home Medical’s new staff hiring and training time in half.

Traditionally, Performance Home medical spent up to 6 weeks onboarding new intake operators. With Tennr guiding new hires through workflows step-by-step, presenting the exact documentation they need to learn, and providing the guardrails to keep them on track, the time dropped over 50% to under three weeks.

Quality Control: A Clear Path to Safe Automation

Before Tennr, automation driven by a platform felt “risky”. Ben described the early automation platforms as seeming like a black box.

Autopilot in Tennr comes standard with built-in quality control tools, which give him transparent accuracy metrics, field-by-field confidence in data entry, and the ability to selectively put parts of his process on Autopilot with a click. He evaluates risk by looking at accuracy and frequency and checks whether downstream steps would be vulnerable to compounding errors.

The path from the moment you receive a referral to the moment you get reimbursed for that patient's care is an American Ninja Warrior-style series of hoops to jump through. Acrobatics of the time-consuming, frustrating, and essential task of handling the flow of patient information, sifting through documents, dialing payers, and reaching patients to get them through the doors, AND making sure you’re going to get paid for it.

It’s tempting to believe the fastest path is to automate every repeatable task and trust the machines to just take it from there. I can totally understand this instinct. And yes, dozens of processes and tasks are perfectly positioned to be automated.

When you’re staring at a referral queue, all of those documents in the inbound worklist, insurance cards, chart notes, and handwritten orders, the dream of pushing all of it into an “AI-powered” super system is hard to resist.

But when automation is adopted without a disciplined plan for monitoring, the dream can wobble fast. We see examples across the industry where “autonomous” systems promise “intelligent document processing” without explaining what that means.

Why human-in-the-loop isn’t enough

For those in the know, this leads to the oh so coveted “human-in-the-loop” approach. A genuinely sensible compromise that should be embraced. When you need to double-check an automated process, you put a person in as a safety net. Makes perfect sense. But who’s that person’s safety net? How is their performance evaluated? You can imagine a scenario where all the information is automatically pulled from a patient chart and entered into the EHR to create an order. But it’s unverified. And the human decision that looks over that information (incorrectly) is also not monitored, creating a two-layer black box instead of one.

For example, we see this pattern in certain automated “intelligent document processing” offerings on the market that try to automate across the board with no real performance plan in place. Without a rigorous quality control system, automation failures hide beneath human inconsistency, and both problems compound quietly until they show up as denials, delays, or missed work.

What does a system that can really fly on autopilot look like?

First, it starts with clear definitions of correctness for each operation that you’re asking an automated step to take, collecting binary human judgments along the way on whether model outputs are correct from an external judge, like a human-in-the-loop, and then using systematic, bias-free sampling to verify both machine work and human judgment through something like a review process.

Running on Autopilot

We’ve helped businesses put entire processes on rails with autopilot systems that handle huge chunks of data entry, document classification, and insurance verification BUT only after the system can:

(1) Prove the accuracy of the automated portions and the human review portions. And prove it to the level of confidence the business needs in that part of the process.

(2) Keep monitoring it even after automation goes live to ensure it stays performant over time.

When we set out to build an Autopilot function in Tennr, we thought exactly about that kind of system.

You start by building the best aircraft you can. That is your model: well-engineered, tuned up over time for a specific function, and flexible to the needs of your process. But even the best plane needs a pilot at the controls. The pilot is your human-in-the-loop, steering, correcting, and learning the feel of the system, identifying where improvements should be made to the model. To know whether that pilot is doing well, you bring in ground control that double-checks the decisions, flags drift, and keeps everyone honest, and keeps good data on everything that’s happened. This is the secret sauce that most automation initiatives leave out. The one in the chair back at HQ who’s crunching the numbers. A trusted source who can report on the performance of all the pilots and feed that back into the system to root out biases and common mistakes.

And then you have all the information you need to do something really cool. Switch on autopilot. At that point, the system can fly itself with confidence, so long as you continue monitoring occasionally. And if something ever looks off, you can always flip the switch back, give the pilot control again. Now, imagine you have an autopilot switch for every single one of your workflows that works independently, dynamically turning it on and off as performance fluctuates. What about each step in each workflow? Where you only autopilot the steps you know are going to perform 99%+ accurately when handing over to automation. Would you feel better about flying through storms?

Saranga Arora is a Senior Product Manager leading Tennr’s core product experiences. After receiving her MS/MBA from Northwestern University and working in product development at Google and Flatiron Health, Saranga joined Tennr to build dynamic solutions to give visibility to obscure patient referral workflows, address the massive adoption and problems of “AI” and automation in healthcare, and highlight the practical solutions for specialty care providers.

The Challenge

Typically, these are the words every CEO hopes to say when describing their business. But this rapid growth drove Josh Arabian and the team at Home Medix into a new problem. A good problem to have, but a problem nonetheless.

As Home Medix saw their monthly DME sales jump nearly 4x, the inefficiencies in their document processing at scale started to take center stage as keeping up with the work became increasingly difficult. Home Medix was needing to balance rapid growth with the escalating burden of manual processing and servicing as many patients and referral sources as they could without leaving them waiting weeks for their equipment or updates.

As Josh put it -

Life with Tennr

With Tennr and an automation-first approach, Home Medix flipped the script and tackled its resourcing issues head-on.

Over a 6-month period, what once required 5 full time team members now runs smoothly with just 2 Tennr users handling all fax wrangling and referral intake tasks.

Each intake process now takes less than 5 minutes—down from the previous 25 minutes—saving 32 days of the team's time over a 6 month stretch. Home Medix is now maturing their processes with Tennr, not quadrupling their processing with the platform and taking on more and more of their pre-placement order processing but also folding in insurance verification and billing qualification review at the same time.

“Instead of spending a half an hour on each entry, we’re now in and out in less than 5 minutes,” Josh notes, emphasizing the dramatic shift in efficiency.

The Next Frontier - A 360 view

About 6 months ago when we asked Josh and his team about the future of Home Medix, he was excited about the opportunities. Josh envisions an even more dynamic approach to their operations that loops in his sales team:

And that's exactly what Home Medix did with Tennr. Josh and his sales team were among the first partners to work with Tennr's Patient Pipeline -- a 360 degree view into the referral process right in the sales rep's pocket.

We sat down with one of Home Medix's reps, Andrew Ortiz, and he talked about how the insights on which referrals are coming through and getting processed the quickest are helping him engage with referral sources.

Before Tennr, Andrew had to pick up the phone and call his intake coordinators back at the office to get a status update, flip through columns on a spreadsheets, and dig through EHR records just to get a comprehensive view of what was going on with each of his referring provider: all of which took precious time away from his day-to-day.

Beyond the numbers, Tennr has liberated the on-site intake team and sales team to focus on what Home Medix has become known for: elite patient engagement. They’re also engaged more in building trust with referral sources and investing in creative business development strategies to keep up their growth.