Your compliance team won't sign off on cloud LLMs touching patient data. Your clinicians are already using ChatGPT on their personal phones.
The gap is real, and it's growing. Every week without an approved AI tool is a week of shadow usage your compliance team can't audit.
The Project Shape
Four decisions determine whether this project ships in 6 weeks or 18 months.
Which model fits the clinical workflow. Documentation assistance, decision support, and triage screening require different model sizes and different output formats. Most teams pick a model before they've defined the task. The consequence is 3 months optimizing a model that produces the wrong kind of output for the workflow it's supposed to support.
Platform sequence. iOS runs on-device AI faster, with better battery performance, than Android at equivalent hardware age. That's not a preference - it's a benchmark result. The platform you ship first determines which clinician group gets the capability and when the rest follow. Rolling out in the wrong order means re-doing the performance work twice.
Server boundary. Which tasks run on-device, and which run on-premise inside the firewall. This looks like an architecture question. It's a compliance question. The answer determines what your BAA needs to cover and what your Privacy Officer can sign off on in a single review cycle.
Audit trail format. Your Legal and Risk teams need proof that patient data never left the device. "Trust us" isn't the format they accept. The audit logging architecture has to produce machine-readable evidence before the app goes to a compliance review, not after.
Most teams spend 4-6 months discovering these decisions by building the wrong version first. A team that has shipped this before compresses that to 1 week.
The Off Grid Anchor
We built Off Grid because we hit every one of these problems in production. Off Grid is the fastest-growing on-device AI application in the world, with 50,000+ users running it today. It's open source, with 1,650+ stars on GitHub and contributors from across the world. It has been cited in peer-reviewed clinical research on offline mobile edge AI. Every decision named above - model choice, platform, server boundary, compliance posture - we have made before, at scale, for real deployments.
The Delivery Shape
The engagement is four sprints. Each sprint is fixed-price. Each sprint has a named deliverable your team can put on a roadmap.
Discovery (Week 1, $5K): We resolve the four decisions - model, platform, server boundary, compliance posture. Deliverable: a 1-page architecture doc your CTO can take to the board and your Privacy Officer can take to Legal.
Integration (Weeks 2-3, $5K-$10K): We ship the on-device model into your app behind a feature flag. Deliverable: a working build your QA team can test against real workflows.
Optimization (Weeks 4-5, $5K-$10K): We hit the performance and compliance targets from the discovery doc. Deliverable: benchmarks signed off by your team.
Production hardening (Week 6, $5K): Edge cases, OS version coverage, app store and compliance review readiness. Deliverable: shippable build.
4-6 weeks total. $20K-$30K total. Money back if we don't hit the benchmarks. We have not had to refund.
"Retention improved from 42% to 76% at 3 months. AI recommendations rated 'highly relevant' by 87% of users." - Jackson Reed, Owner, Vita Sync Health
The Close
Worth 30 minutes? We'll walk you through what your version of the four decisions looks like, what a realistic scope and timeline would be for your app, and what your compliance posture and on-device target mean in practice. You'll leave with enough to run a planning meeting next week. No pitch deck. If we're not the right team, we'll tell you who is.
Top comments (0)