Accelerate healthcare and life sciences workflows with AI coding and skills
by Zachary Phillips, May Merkle-Tan, Praneeth Paikray, Peter Hawkins, Vimal Thomas Joseph, Rohan Parikh and Yen Low
Genie Code, our coding agent optimized for Databricks, allows you to chat instead of code to perform your data and AI tasks. Critically, Genie Code’s integration with Unity Catalog ensures that the agent understands your enterprise’s data and follows the same security and governance rules as the rest of the Databricks platform. Thus, Genie Code significantly outperforms a leading coding agent by more than twice on real-world data tasks such as exploratory data analysis, machine/deep learning, creating dashboards, agents, apps, declarative automation bundles, Lakeflow jobs and scheduling them.
However, Genie Code and other general AI coding assistants lack domain specificity and assume generic methods and clinical thresholds that do not meet healthcare and life sciences (HLS) standards or best practices.
Databricks Vital Skills bridges this gap by providing packaged playbooks built in the open Agent Skills standard. They equip AI coding agents with industry knowledge so agents know which questions to ask, which steps are non-negotiable, and which tested tools to use.
Vital Skills is designed for Genie Code to make the best use of the unified Databricks ecosystem so generated code is not disconnected from your governed data, and you're not left to stand up serving, GPUs, governance, and scheduling yourself. You get a system, not just a sandbox. With the Databricks ecosystem, you:
We tested Genie Code with and without Vital Skills on BiomniBench, a public benchmark of biomedical data-analysis tasks graded against expert-written rubrics. Genie Code alone rarely failed on the obvious parts.
It parsed documents and generated charts with ease. However, it sometimes fell short on domain-specific methodology and knowledge and was prone to overassumptions. With Vital Skills, Genie Code scored higher on the relevant tasks and had no negative impact on tasks that were out of scope of Vital Skills.
Each skill started with a field engineer who had solved the problem several times with customers. We held on to three principles:
Vital Skills puts the know-how of a biostatistician, privacy officer, bioinformatician, or actuary directly in the hands of every analyst, helping teams move faster before engaging additional expertise. The Databricks Healthcare and Life Sciences field team has built skills across the industry, covering key steps in data processing, analysis, model life cycle management, evaluation, report and slide generation.
These skills can be used directly, or further customized to your needs and to leverage your deep expertise in your discipline. We expect this starter set of skills to grow over time and welcome contributions to the open source repository.
| Skill | What it does |
|---|---|
| Bioinformatics | |
bulk-rnaseq |
Find top differentially expressed genes from bulk RNA-seq counts. |
open-weight-models |
Package, register, validate & deploy open-weight HLS models on Databricks, e.g. TEDDY and Geneformer. |
pathway-enrichment-analysis |
Pathway enrichment for RNA-seq (ORA or GSEA). |
sc-rnaseq |
Analyze single-cell RNA-seq data from .h5ad files. |
| Clinical | |
cohort-builder |
Build a reproducible, feasibility-checked patient cohort from coded + free-text clinical data. |
rwe-cohortstudy |
Comparative effectiveness (cohort study) with propensity adjustment (matching, IPW). |
semantic-builder |
Build a semantic layer like Metric Views using 64 common measures from EHR or claims so they are dashboard or agent ready |
phi-deidentifier |
HIPAA Safe-Harbor de-identify a Unity Catalog table (k-anonymity + governed view). |
| Others | |
presentation-builder |
Build presentation-ready slides |
report-writer |
Move your analysis methods and results to a report |
accelerators |
Route to a relevant HLS accelerator or library with the right tools for your task |
skill-eval |
Benchmark a skill: paired runs with/without it, MLflow genai.evaluate scoring, win/loss + failure taxonomy. |
Go from data to a [finished report](https://databricks-industry-solutions.github.io/vital-skills/guide/skills/report-builder/) or agent or dashboard seamlessly on Databricks.
For example, our [semantic-builder skill](https://databricks-industry-solutions.github.io/vital-skills/guide/skills/payer-provider-measure-catalog/) defines and computes [commonly used metrics](https://github.com/databricks-industry-solutions/vital-skills/blob/main/skills/semantic-builder/references/catalog.md) (e.g. length of stay) into a [Metric View](https://docs.databricks.com/aws/en/uc-semantics/metric-views/) from claims or electronic health records. Once Metric Views are defined in Unity Catalog, you can easily [re-use them across multiple tools](https://docs.databricks.com/aws/en/uc-semantics/metric-views/query#consume-metric-views-in-tools) like dashboards, Genie Agents, external BI or spreadsheets.
In the following sections, we will dive into a couple of key skills.
An analyst describes a population in plain language — "patients with type 2 diabetes and uncontrolled blood sugar" — and the skill turns that into a cohort they can reproduce, explain, and defend. Cohort building is an integral starting point for nearly every analytics effort: RWE studies, clinical-trial feasibility, payer care-management and population-health outcomes research.
After building cohorts, consider comparative effectiveness studies and share your results using the presentation-builder.
Some of the most promising AI applications for life sciences are open source biological foundation models that encode single-cell transcriptomics (Geneformer, scGPT, Scimilarity, TEDDY) or protein structure (AlphaFold/OpenFold, Boltz2, etc). They are also difficult to get running, requiring specialized infrastructure and abilities. Because this skill summons the appropriate code, libraries and GPU serving, a scientist can go from “I need this model" to serving a governed model that one can actually use.
Along the way it:
On a TEDDY single-cell model deployment task, Genie Code without the skill wrote correct code but missed key deployment-readiness steps — pinned dependencies, a post-registration smoke test, and more — completing 19 of 27 checks. With the skill, all 27 completed.
We included a skill to evaluate skills because there is no single universal “accuracy” for healthcare and life sciences workflow. For each skill, it builds a customizable evaluation harness, complete with appropriate tasks, data, scorers, and expected results and behavior, tailored to what each skill is designed to achieve. We ran and scored the evaluation tasks with and without Vital Skills.
We also tested Genie Code with and without Vital Skills three times on BiomniBench which curated tasks from top biomedical peer-reviewed papers.
The right skill makes the right behaviors reliable. On one cohort task, the baseline silently dropped half the eligible patients; with the skill, every one was recovered.
Previous research has shown that Genie Code is more cost-efficient than other coding agents because it uniquely understands your data on Databricks, skipping the typical random walk search.
Extend Genie Code with additional skills like Vital Skills for healthcare and life sciences tasks. Together, one can chain a myriad of skills into complex tasks. For example, after deploying open-weight models, create and schedule a batch inferencing job. If it is an embedding model, prompt Genie Code to create a vector search index.
Browse and install Vital Skills in Genie Code, Genie One or Genie Code CLI. Publish these skills to Unity Gateway to govern and share them with your coworkers. Try the ones that fit your work or customize them to suit your needs. Genie Code even helps you create new skills. Vital Skills is open source and welcomes your contributions.
Solutions, News, Best Practices, Healthcare & Life Sciences and Solution Accelerators
Subscribe to our blog and get the latest posts delivered to your inbox.