DataHowLab 25.11

Iterative Loops for Insight-Driven Process Development
The engine of the structured development framework is the development loop, which allows users to organize work into clear iterations that mirror experimental cycles. Following an active learning philosophy, each loop drives the user to generate actionable insights within a structured, repeatable procedure. Teams can track their goals and tag best results keeping projects tidy while maintaining visibility of past work.

Step-by-Step Success: Guided Active Learning
The workflow guide helps users navigate complex projects by providing explanations, progress tracking, and contextual hints at each stage of the loop. Acting as both a checklist and a guide, it helps less experienced users adopt best practices and work with confidence.

Smarter Feeding: Rule-Based Flow Control
Real-world processes often rely on rule-based flows, such as feeding to maintain glucose levels or compensating flows in perfusion systems to stabilize process volume. The new Feed and Flow Composer integrates these concepts directly into model-based tasks, ensuring simulations and optimizations reflect the way processes are actually run.

Enhanced Continuous Modeling
We’re introducing an upgraded version of our continuous model in DataHowLab. This new release comes with a re-engineered algorithmic backbone, designed to deliver stronger performance across diverse process formats. While its parameters differ from the previous version, the purpose remains the same: to reliably model process dynamic variables. With this improvement, users can expect more accurate and flexible insights to support their bioprocess development.

Stay Aligned: Notes, Context & Collaboration
Project Notes allow teams to capture insights, thoughts, and discussions directly within each DataHowLab project. Linked specifically with datasets, models, and visualisation boards, this replaces scattered notebooks and external documents, ensuring critical context remains tied to the work itself. All notes are automatically collected in a Journal, giving teams a shared and searchable overview.

See What Matters: Smarter Project Views
New project headers create a unified way of displaying key information across DataHowLab. By making core entities such as datasets, models, and designs visually distinct and placing critical information upfront, users gain a faster, clearer understanding of their projects.

Empower Your Team: Manage Users & API Keys
Organizations can now designate internal User Managers to create and remove users and generate API keys directly in DataHowLab. With this change, companies can act immediately when new colleagues join or when SDK usage grows, without waiting on external support.

Seamless Connections: API for Any Tech Stack
A new external Web API extends the functionality of the Python SDK, making it possible to integrate DataHowLab simulations into any environment, independent of programming language. Customers can now upload data, run simulations, and visualize forecasts directly in their own systems, without needing a Python-based infrastructure.