MACg Platform Update: GPT-5.4 and Image 2 Across Writing, Slides, and Visual Creation
This update reflects a major step forward in how MACg supports scientific and medical content creation. With GPT-5.4 now powering the platform, users benefit from stronger writing, better reasoning, improved responsiveness, and more consistent outputs across AskMACg, slide generation, and search. At the same time, the integration of Image 2 into both AskMACg and slide creation significantly expands MACg's visual capabilities, enabling users to generate higher-quality infographic visuals, presentation graphics, congress-ready posters, and other professional assets directly within the platform. The redesigned Slide Agent builds on these model upgrades with improved orchestration, greater contextual awareness, and more accurate slide generation. Together, these enhancements make MACg a more unified and capable environment for searching, writing, visualizing, and presenting complex scientific information. For users, this means a faster path from idea to polished deliverable, with stronger support for both narrative content and visual communication.
Today, I'm excited to share one of the most important product upgrades we've made to MACg.
Over time, our goal has remained the same: build a platform that helps medical teams, researchers, writers, and speakers move faster without sacrificing quality. This latest release is a major step in that direction.
We've upgraded MACg to GPT-5.4 across the platform, including AskMACg (the main composer), slide generation agents, and search. We also integrated Image 2 into both AskMACg and slide creation. Together, these upgrades improve writing quality, reasoning, visual generation, accuracy, and the overall end-to-end creation experience inside MACg.
Just as importantly, we've completed a major redesign of the Slide Agent. Slides have become the most-used feature in MACg, and that adoption has come from exactly the audience we built this for: global medical speakers, key opinion leaders, medical writers, and researchers. This redesign reflects the importance of presentation creation for scientific information sharing.
What's New
GPT-5.4 Across the Platform
MACg now runs on GPT-5.4 throughout the platform, and our multiple agents are now built on GPT-5.4. This upgrade strengthens content generation, reasoning quality, responsiveness, and output consistency across a broad range of use cases.
From a founder's perspective, this matters because MACg is solving multiple workflows. Users search, write, summarize, generate slides, refine narratives, and create visuals in the same environment. A stronger core model improves all of it.
Image 2 in AskMACg and Slide Creation
We've also expanded our visual generation capabilities with Image 2, now available in AskMACg and used for slide creation. This gives users stronger image-generation capabilities for standalone visual content and for presentation workflows.
That means MACg can now support a wider range of professional visual outputs directly inside the platform, giving teams more options for sharing scientific knowledge.
Congress-Ready Posters and Other Visual Assets
With Image 2, users can create congress-ready posters and other professional visual assets directly within MACg. This is an important expansion of what the platform can do. MACg is no longer just a writing tool or a slide tool. It is a more complete environment for scientific and professional content creation.
More Detailed and Accurate Infographic-Style Slide Visuals
The Slide Agent now provides more infographic-style images that better align with slide content. The goal here is simple: presentations should not just be faster to create; they should also look more coherent, more visual, and more presentation-ready.
This upgrade helps ensure that visuals support the story of each slide rather than simply filling space.
Slide Agent Receives a Major Redesign
This is one of the updates I'm most excited about.
The MACg slide generator and editor has become the most-used feature in the platform. We're seeing strong adoption among global medical speakers, key opinion leaders, medical writers, and researchers who are using MACg to save time and improve the quality of presentation development.
This is why we made a significant investment in redesigning the Slide Agent.
The new Slide Agent uses GPT-5.4 plus additional orchestration layers to improve accuracy, contextualization, and image generation with Image 2. The result is a more capable system for turning source material and user intent into polished presentation content.
We've also added presentation theme previews, and users can now select layouts from different themes when creating individual slides in the slide editor. This gives users more creative control without slowing down the workflow.
What This Means for Our Users
From the beginning, we've believed that medical and scientific content creation should be faster, smarter, and more integrated.
This release moves us closer to that vision.
With GPT-5.4, Image 2, and a redesigned Slide Agent, MACg now delivers a stronger generation stack for content and visuals. Users can search, write, create more accurate presentations, generate better slide visuals, and produce higher-quality professional assets in one platform.
We're continuing to build MACg for teams that need more than generic AI output. They need accuracy, speed, structure, and visuals that are actually useful in real professional workflows.
Imagine creating a text document, turning it into an infographic, and then a presentation, all on one platform.
Start creating & editing content in minutes with AINGENS' MACg.
Discover all the amazing things you'll create with AI.
100 AI Slide Presentation Prompts for Busy Medical and Scientific Professionals
This article provides 100 ready‑to‑use AI prompts to help medical and scientific professionals create high‑quality slide presentations with MACg. The prompts are organized into practical categories, including clinical education, drug and mechanism‑of‑action decks, PubMed‑driven evidence reviews, specialty teaching, medical affairs and HEOR, training and curriculum, data‑visualization, and conference or grant presentations. Each prompt uses clear “Instruction:” wording and customizable placeholders (e.g., [condition], [audience], [timeframe]) so users can quickly adapt them to their specific topic and setting. By removing blank‑slide paralysis, the collection speeds up evidence‑based slide creation while supporting consistent, structured, and compliant communication.
Feb 4, 2026
10 Tips For Using MACg and Other AI Solutions For Medical and Scientific Writing
This article shares 10 practical tips for medical writers, pharma/biotech professionals, HCPs, and researchers on how to use MACg and other AI solutions effectively and responsibly. It emphasizes that MACg's AI agent training knowledge is not a citable evidence base and must be anchored in real, verifiable sources such as publications, CSRs, labels, guidelines, and internal documents. Readers are encouraged to treat all AI outputs as Version 0.1, iterating with expert review rather than accepting the first draft. The article frames MACg as a drafting and thinking assistant, not an autonomous author, and stresses the importance of clear prompts about audience, purpose, region, timeframe, and scope. It recommends breaking complex projects into smaller tasks, using MACg to improve structure and clarity, and explicitly asking for limitations and caveats. Finally, it advocates creating institutional checklists and making expert human review and sign‑off mandatory for any impactful content.
Mar 1, 2026
Reliability of MACg for Source‑Aligned Clinical‑Trial Data Extraction: Hallucination, Accuracy, and Contextual Understanding
We evaluated MACg, a GPT–5–based writing and research assistant, for medical writing and data extraction, on five uploaded clinical‑trial PDFs (15 questions per study; 75 total). Questions on design, endpoints, efficacy, safety, limitations, and interpretation were asked one at a time, without instructions to avoid hallucinations or rely on the document. A clinician compared each answer with the source. MACg demonstrated zero hallucinations, 100% accuracy for requested data, contextual integration across sections, appropriate handling of missing information, and clinically coherent interpretation grounded in the trials, supporting its use for reliable, source‑aligned medical communication.
Feb 14, 2026
