48 posts tagged with "development"

For a year, every AI feature in Parthenon spoke to a model the same way: build a prompt, send it, get one answer back. Abby answers a question. The publication writer drafts a paragraph. Useful — but fundamentally a vending machine. You put a prompt in, a completion comes out, and the model never gets to look around, use a tool, or change its mind.

This milestone changes that. Parthenon now runs genuine agentic copilots — built on Anthropic's Claude Agent SDK, the same autonomous loop that powers Claude Code — inside two workflows: the Study Designer and the Publication assistant. The agent decides which tools to call, iterates (search → draft → validate → refine), keeps a session across turns, streams its work to the browser, and — critically — asks for permission before it writes anything. It ships on a reusable, profile-agnostic core, behind a super-admin runtime switch, with PHP still holding the pen on every database write.

This post is the full story: the architecture, the four pull requests that built it, the human-in-the-loop approval gate, and the engineering discipline (and bugs) along the way.

Parthenon Enterprise Edition has crossed an important infrastructure milestone: it now has a real Kubernetes deployment foundation.

This is not a marketing placeholder, and it is not a pile of disconnected YAML. The new work establishes a second, deliberately separate deployment lane beside the host-native VPS and bare-metal installer track. The native path remains focused on non-Docker Linux hosts. The Kubernetes path now has its own architecture, Helm chart, Terraform module, existing-cluster example, validation evidence, and todo trail toward cloud-provider orchestration on AWS, Azure, and GCP.

The point of this milestone is simple: Parthenon EE can support two very different enterprise realities without letting them blur into one fragile installer.

Concept mapping is the single largest line item in any OMOP CDM ingestion budget. Published estimates put it at 40–60% of total ETL effort per source system — measured in clinician-weeks, not engineer-hours. Today we landed the architectural piece that's been missing from Parthenon's vocabulary stack since the beginning: Harmonia, an automated decision layer that sits between Hecate (read) and Ariadne (write) and does the cognitive work that's been falling on humans.

The name is deliberate. In Greek mythology, Harmonia is the goddess of agreement, accord, and fitting together — daughter of Aphrodite and Ares, born of love and conflict. That's what concept mapping is: bringing disparate source vocabularies (an ICD-10 code from one EHR, an NDC string from another, a hospital's local lab nomenclature) into harmony with a single canonical OMOP standard. Every approved mapping is a small act of harmony. Until today, Parthenon could show candidates and record decisions but couldn't reach harmony on its own.

This post walks through what we built, why it's an improvement over the existing Hecate + Ariadne pair, and the four real bugs we hit getting a benchmark to actually run.

A landmark day for the Parthenon platform: the Abby Study Design Compiler crossed the finish line and landed in production. Alongside that headline feature, we completed a deep structural refactor of the Study Workbench, patched a collection of critical runtime bugs, and hardened the frontend with accessibility improvements and unsaved-changes guards. Phase 19 smoke testing confirmed everything holds together against the live DEV environment.

A busy Tuesday on Parthenon with work spanning three distinct fronts: consolidating the GIS layer we stood up in Phase 19, continuing to clean up the study design workbench on the frontend, and tightening several infrastructure and testing rough edges that had accumulated over the sprint.

A focused day on Parthenon with three distinct threads advancing in parallel: the GIS-backed urban/rural stratification pipeline moved from concept to tested RED-phase scaffolding, the Study Designer received several important bug fixes and UX improvements, and the architectural groundwork for Abby's guided Study Design Compiler workflow was laid out in detail.

A dense Saturday of stability work across Parthenon — today's 89 commits concentrated on three converging themes: getting the cross-platform installer into a shippable state, closing out a backlog of high-severity audit findings in the Care Bundles engine, and restoring broken workspace workflows in Patient Similarity. No new features today; this was deliberate debt-clearing ahead of the next feature milestone.

A dense day on Parthenon with 58 commits landing across a wide surface area: the Care Bundles workbench reached a meaningful analytical milestone with Phase 3 Tier A methodology complete, the macOS CI pipeline was significantly streamlined, and we laid down a comprehensive design spec for the installer's first-run experience. Sprinkled throughout were a handful of i18n fixes and auth UX improvements that round out the release candidate picture.

A heavy day on the Parthenon installer front — 81 commits landed across the repo, pushing installer-v2 from "wired up" to "genuinely trustworthy." We added Docker secrets support, closed a handful of correctness bugs surfaced in post-review, scaffolded the omop_cdm phase for existing-CDM deployments, and nudged Finnish, Japanese, and Chinese localizations well into the mid-90s. Here's a full breakdown.

Today was a focused, high-volume internationalization push across Parthenon — thirteen commits dedicated entirely to extracting i18n strings from nearly every major workflow surface in the platform. If you've been waiting for the day Parthenon could speak your language (literally), we made a serious down payment on that today.