Study intelligence. Human authority.
One study ontology connects your documents, decisions and data. AI drafts the work. Your team approves.
The semantic layer
Every visit, form, rule and decision has one definition, linked to its source and everything it touches. One shared model for people, systems and AI.
01 · Today
Documents, spec sheets, inbox threads and a separate copy in every system, kept in step by hand.
02 · Read once
Visits, forms, rules, lab tests and decisions become typed entities, each tied to the clause, record or signature it came from.
03 · Change once
Widen a visit window and the layer counts every form, check and value behind it before anyone signs. Nothing is retyped or rebuilt.
ACT-217Study
What it reads
Study documents, the decisions behind them and the data itself, read once and never retyped. The panel shows what is live today.
What runs on it
Forms, checks and AI agents read the definition your team approved, and move with it when the trial changes.
What connects
AccuraTrials EDC runs on the layer today, with randomization, ePRO and eConsent built in. Connectors to central labs, eTMF, CTMS and safety systems are in development.
Built on CDISC USDM and OpenStudyBuilder. Every entity carries a standard definition, so your study means the same thing to every system that reads it.
When the study changes
Arms open and stop, amendments land, forms gain a field. Each change is applied to the running study and signed, and the data already collected stays where it is.
01 · When an arm is added
Its visits, forms and checks arrive as a reviewed change to the running study, counted before anyone signs. Participants already enrolled keep their study as it was.
Amendment review and apply built into AccuraTrials EDC02 · When an arm stops or graduates
Proposed, reviewed by a different qualified person, then e-signed. Only new assignments change, and arm names stay out of the general audit view to protect the blind.
Governed arm decisions built into AccuraTrials EDC03 · When a form needs a field
Existing patient forms update where they are, with values, queries and locks untouched and every copy audited. A signed form changes only if you opt in, with the reason recorded.
Form propagation built into AccuraTrials EDC04 · When the data disagrees
Adverse events are matched to safety reports case by case, each discrepancy verified by a second investigator. Kit counts and imports are reconciled against their source, and open safety items hold closeout.
Safety, supply and import reconciliation built into AccuraTrials EDCAccuraTrials EDC
Data capture, edit checks, queries, source data verification, data lock and the audit trail, running on the study ontology.
AI agents
We’re building agents to draft, check and trace from that same study ontology. Your team reviews and approves the work.
Configure visits, forms, branching and checks from your study documents, each linked to its source.
Worked example · AI build workflows in developmentInvestigate issues as data arrives. The check fires with its source clause, and a query is drafted for your approval.
Edit checks in production · AI drafting in developmentSuggest MedDRA and WHODrug codes for events and medications. A coder confirms each one.
In development · shaped with medical codersSee every form, check and collected value an amendment touches, before anyone signs it.
Illustrative · in developmentAgent run
Trust
EDC controls designed to support the rules your study answers to. Study-specific validation and your own procedures still apply.
Infrastructure built to the SOC 2 trust principles, with an information security program aligned to ISO 27001. Neither is a completed audit or certification yet.
Who it’s for
01
Every sponsor’s study on one governed ontology, from build to lock.
02
One definition of each study across programs, vendors and amendments.
03
Your first trial, without a long vendor build.
Questions
The core of the intelligence layer: one shared definition of the study that people, systems and AI agents all read. Arms, visits, activities, forms, items, rules, endpoints and decisions are typed entities with explicit relationships, each linked to the document clause, specification or approval it came from. AccuraTrials calls it Accura OS: AccuraTrials EDC runs on it today, and connectors to central labs, eTMF, CTMS and safety systems are in development.
AccuraTrials EDC, in production on a paid study: data capture, edit checks, queries, source data verification and data lock, with randomization, ePRO and eConsent built in, audit trails and electronic signatures, mid-study amendments, governed arm decisions and reconciliation. The AI agents for study build, data review, medical coding and amendment impact are in development.
They are the backbone of the ontology. USDM gives the study definition its structure, OpenStudyBuilder is its open-source foundation, and CDASH, SDTM and controlled terminologies such as MedDRA, WHODrug, LOINC and SNOMED CT give each element a standard meaning.
No. AccuraTrials EDC is in production and can run a study end to end, and the semantic layer is designed to sit across the systems you already use. Connectors to other trial systems are in development.
Yes. A new or changed arm arrives as a reviewed amendment applied to the running study, with every form, check and collected value it touches counted before anyone signs. Stopping, graduating or reopening an arm is a governed decision: proposed, reviewed by a different qualified person and executed with an electronic signature. Participants already enrolled keep their assignments and their data, and the study is not rebuilt.
Continuously, inside the study rather than in a cleanup sprint before lock. Adverse events are reconciled against safety reporting case by case, with each discrepancy resolved and verified by a second investigator; drug-kit counts are reconciled site by site with signed evidence; and every import is reconciled against its source. Open safety items hold the study’s closeout until they are resolved.
See the EDC in production and the agent workflows we’re building next.