Software Development | Accelerated Focus

AF BLOG

Accelerated thoughts

Testing the Guardrails: What Actually Happens When Your AI Agent Misbehaves in ODC

You enabled the safety filters. But what does the developer experience actually look like when they fire? TL;DR Summary For OutSystems Developers: ODC's agent guardrails give you configurable, platform-level enforcement for prompt attack detection, PII masking, and harmful content filtering. Your LLM provider (Azure, Bedrock, etc.) catches some of these on its own, but inconsistently and without your control. Guardrails make it explicit, observable, and tunable. Two minutes

Natasha De Guzman

Jun 25

All articles

Bringing Clarity to Undocumented OutSystems Code with AI

Use AI tools like Amazon Q Developer to generate documentation for undocumented OutSystems apps. Start by extracting the source code, then prompt AI for app overviews, technical docs, user stories, and maintenance notes. Regular AI-powered updates keep docs fresh. Tools like ChatGPT, Copilot, and Gemini also work. This turns mystery code into clear, maintainable systems and builds a culture of documentation.

Natasha De Guzman

Aug 19, 2025

🚀 Building Bridges: Empowering OutSystems with n8n

Discover how n8n, the open-source automation powerhouse, can elevate OutSystems apps by seamlessly connecting APIs, orchestrating AI, and managing complex workflows. From enriching a bookshelf app with AI-generated summaries to embedding a document-aware RAG chatbot, I explore how these platforms combine to build smarter, scalable solutions — all without burdening the core app with extra complexity or code.

Alex Fernandes

Jul 29, 2025

When AI Becomes Both a Bridge and a Backbone: An Engagement Manager Perspective

An Engagement Manager at Accelerated Focus shares lessons from a state government AI project involving the migration and enrichment of 20,000 legacy PDFs using LLMs and vector indexing. The AI powered both data migration and real-time search. Key takeaways include evolving scope, the importance of broad data sampling, UI alignment, managing AI accuracy expectations, and planning for long-term AI maintenance and human-in-loop workflows.