This workflow is designed for
Safety/Pharmacovigilance Writers in pharmaceutical and device companies
CRO delivery teams
The real-world problem
A periodic safety report (PSUR) summarises the benefit-risk profile of a drug or device for the reporting period. It is a resource-intensive activity and has to be drafted periodically for the drug or device starting from phase 1 clinical trials, till it is in the market to be consumed or used by people. Following are some of the key challenges that writers face while drafting PSURs.
Fragmented safety information across systems
Critical safety inputs are distributed across multiple sources—such as safety databases, quality systems, complaint logs, and literature repositories. Bringing this information together requires extensive manual effort to extract, align, and verify data consistency.
Time-intensive evidence review and narrative construction
A large proportion of authoring effort is spent on reading source documents, distilling findings, and translating data into regulatory narratives. This slows down PSUR cycles and limits time available for clinical interpretation and benefit–risk assessment.
Inconsistent structure and writing quality
Differences in templates, section organization, analytical depth, and narrative tone often lead to variability across PSURs. This inconsistency increases review comments and rework during QA and regulatory review.
Weak linkage between source data and final content
Authors often lack a clear, auditable connection between underlying data and the conclusions presented in the report. Responding to reviewer queries requires time-consuming manual back-tracking to justify how specific insights were derived.
Under-utilization of prior knowledge and historical reports
Information from earlier PSURs, CERs, vigilance reports, or PMCF activities is not easily reusable or searchable. As a result, authors must repeatedly scan past documents to understand product history, emerging trends, and evolving safety signals.
High risk of errors from manual, repetitive work
Routine tasks such as copying tables, updating figures, reformatting content, and managing references increase the likelihood of inconsistencies and errors. Despite significant manual QC effort, formatting and narrative discrepancies often persist.
What Asthra helps with — and what it doesn’t
Where Asthra can help
All tasks related to retrieve or generate content where the context required is available. For example, copy-paste, change tense, summarisation, table & figure interpretation.
Asthra can also do simple calculation and math, and simple table manipulation with high accuracy.
Asthra can compile information from different source documents and present them in the form of tables.
Where Asthra cannot help
Complex calculation and math.
Retrieving information from huge tables or manipulation of huge tables.
Asthra can assist with drafting descriptive and analytical sections of a PSUR, including structured summaries of safety and performance data, trend discussions based on available inputs, and consistent narrative across sections. This means that Asthra can generate 100% of the PSUR as an initial draft. Benefit-risk conclusions are expected to be reviewed and finalized by human experts.
Asthra uses only the source documents and datasets explicitly provided by the user. If required information is missing or incomplete, Asthra flags the gap rather than inferring or fabricating content, ensuring draft text remains grounded in available evidence.
Statements generated by Asthra are linked to their supporting source documents, sections, or tables wherever applicable. This allows reviewers to verify content efficiently during internal review or notified body assessment.
Yes. Asthra supports iterative drafting by reusing prior PSURs and updated safety or performance inputs as source material. This helps maintain consistency across reporting periods while allowing writers to focus on reviewing changes.
No. Asthra is designed to accelerate drafting and improve consistency, not to replace clinical, safety, or regulatory expertise. Human oversight and approval are mandatory for all PSURs generated using Asthra.
When safety or performance data are incomplete or evolving, Asthra explicitly highlights missing information or uses placeholders. It does not assume outcomes or generate conclusions beyond the provided data.
Asthra can be configured to support PSUR workflows across different regulatory contexts, depending on the document structure, source inputs, and organizational requirements. The specific applicability should be assessed during a pilot or demo.
Asthra is available as a secure SaaS offering and can also be deployed within a customer-managed private cloud or VPC, depending on data residency and security requirements.
Teams using Asthra typically experience faster first-draft generation (by more than 60%), improved consistency across PSUR sections, and reduced review effort due to built-in traceability—while retaining full human control over final content.
How Asthra supports this document
Asthra supports the writer by generating the initial draft of the entire PSUR from its source documents, previous PSURs, Core Data Sheets, data on exposure across clinical trials etc. Writers can generate the content on MS Word section-by-section by just clicking the pre-configured prompts.
Unified ingestion and traceability of safety evidence
Asthra brings together safety data, quality inputs, literature, and prior reports from multiple source formats into a single PSUR workspace, with clear lineage from source documents to final narratives.
Governed, compliant authoring aligned to SOPs
Role-based access, controlled workflows, and SOP-aligned guardrails ensure PSURs are authored consistently and in line with organizational and regulatory expectations.
Word-native, human-in-the-loop writing experience
Authors work directly within Microsoft Word, using AI assistance to draft and refine content while retaining full control over medical judgment and final decisions.
Reuse of historical knowledge and prior submissions
Insights from previous PSURs, Core Data Sheets, and vigilance documents are made searchable and reusable, enabling continuity in safety narratives and benefit–risk evaluation.
Intelligent automation across drafting and review
Agent-based workflows accelerate evidence synthesis, narrative generation, and iterative review, reducing manual effort while improving consistency and audit readiness.
Inputs → Draft → Review
Template
Import the relevant CSR template that has been onboarded. It can either be either the standard ICH or Trancelerate templates or the customer’s custom template
Inputs
-
Upload Source documents for the CSR – Trial Protocol, Tables Figures Listings (TFL)
-
Documents can either be uploaded from the writer’s local machine or via integration with a DMS (Document Management System)
Drafting with Asthra
-
Writers can straightaway start generating content section-by-section by just clicking and running on the pre-configured prompts.
-
There is ZERO configuration or manual effort that the writer has to put before generating content
-
Writers can review the provenance and citations on the fly
2. Asthra generates the initial draft in 30 minutes
Inputs → Draft → Review
01
Template
Import the relevant PSUR template that has been onboarded. It can either be either the standard ICH based template or the customer’s custom template.
02
Inputs
-
Upload Source documents for the PSUR – Previous PSUR, Core Data Sheet, Exposure data, sales data, Line-listings etc.
-
Documents can either be uploaded from the writer’s local machine or via integration with a DMS (Document Management System).
03
Drafting with Asthra
-
Writers can straightaway start generating content section-by-section by just clicking and running on the pre-configured prompts.
-
There is ZERO configuration or manual effort that the writer has to put before generating content.
-
Writers can review the provenance and citations on the fly.
2. Asthra generates the initial draft in 30 minutes.
04
Human Review & QC
-
Writers are empowered to jump in and edit content at any point in the draft generation process.
-
If the provenance needs to be corrected for any output, writers can easily select the prompt and seamlessly select the file and then the section/table/image from that file and run the prompt to regenerate content.
-
Since Asthra is built as an Add-in on MS Word, writers can easily review and edit content during and after the initial draft is generated.
-
All transactions on Asthra are persistent and reviewers and auditors/inspectors can review anytime in the future.
Evidence, traceability & controls
Asthra is purpose-built as a closed system. All content generated originates strictly from the source documents uploaded.
-
There has not been any hallucination so far. This is due to our approach on granular context engineering.
-
LLMs are not allowed to use their own knowledge. Our guardrails and prompts ensure that is the case.
Asthra flags missing information with an appropriate response for example, “There is no relevant information in my context to answer this question.”
Asthra transparently shares the provenance for each output. That is, the writer can easily get information on which file and section/table/image in the file was referenced for the output.
In addition, writers can select any sentence generated and verify its citation i.e. which file, its page number, and relevant snippet of text from which the sentence was generated from.
Asthra enables writers to review and edit content generated.
-
Writers can directly modify content in the word document.
-
Writers can easily modify the pre-configured prompts to generate alternate responses.
-
Writers can change the provenance i.e. change the file and section/table/image and regenerate alternate content.