https://adaas.ai/blog/index.htmlField notes, research and insights from ADAAS.enWed, 09 Sep 2026 00:00:00 GMThttps://adaas.ai/blog/b-009-from-rag-to-context-architecture/https://adaas.ai/blog/b-009-from-rag-to-context-architecture/Wed, 09 Sep 2026 00:00:00 GMTContext EngineeringRAG solved how a model reaches information it was not trained on. Enterprise agents face a harder problem: operating inside the right knowledge, application, capability and governance context at runtime. That is a composition problem, not a retrieval one.https://adaas.ai/blog/b-008-software-intent-is-the-bottleneck/https://adaas.ai/blog/b-008-software-intent-is-the-bottleneck/Wed, 09 Sep 2026 00:00:00 GMTAI-Native DevelopmentAI can increasingly produce the implementation. The scarce resource is shifting to the layer above it — a durable, structured representation of what the software is supposed to be. That is the bottleneck the next phase of AI-native development has to solve.https://adaas.ai/blog/b-007-personalization-vs-apperception/https://adaas.ai/blog/b-007-personalization-vs-apperception/Wed, 09 Sep 2026 00:00:00 GMTArchitecturePersonalization and apperception can both make software look different for different users. Architecturally they solve opposite problems: personalization selects a predefined experience for a user; apperception constructs the appropriate experience from runtime context.https://adaas.ai/blog/b-006-ai-native-software/https://adaas.ai/blog/b-006-ai-native-software/Wed, 02 Sep 2026 00:00:00 GMTAI-Native ArchitectureWhen software can reason, generate, act and dynamically compose capabilities, you are not adding a feature — you are changing the architecture. This is the shape of the post-AI software era.https://adaas.ai/blog/b-005-rag-not-enough-enterprise-agents/https://adaas.ai/blog/b-005-rag-not-enough-enterprise-agents/Wed, 19 Aug 2026 00:00:00 GMTContext EngineeringRAG solved the problem of finding information. It did not solve the problem of understanding the software context in which that information matters — and that is the problem production agents actually have.https://adaas.ai/blog/b-004-end-of-the-software-application/https://adaas.ai/blog/b-004-end-of-the-software-application/Wed, 05 Aug 2026 00:00:00 GMTAI-Native ArchitectureThe next generation of software may not be a set of large applications that humans navigate. It may be an ecosystem of capabilities that humans and agents dynamically compose.https://adaas.ai/blog/b-003-from-code-to-intent/https://adaas.ai/blog/b-003-from-code-to-intent/Wed, 22 Jul 2026 00:00:00 GMTAI DevelopmentThe real limit of AI-assisted development is that humans still express software intent through code, prompts, tickets and fragmented docs. The next programming artefact is intent itself.https://adaas.ai/blog/b-002-ai-native-software-development-lifecycle/https://adaas.ai/blog/b-002-ai-native-software-development-lifecycle/Wed, 08 Jul 2026 00:00:00 GMTAI EngineeringThe real AI revolution in software is not that AI writes more code. It is that AI can participate across the entire lifecycle — from intent to continuous evolution.https://adaas.ai/blog/b-001-ai-agents-need-architecture/https://adaas.ai/blog/b-001-ai-agents-need-architecture/Wed, 24 Jun 2026 00:00:00 GMTAgent ArchitectureGiving an AI agent access to APIs is not the same as giving it architectural understanding. Enterprise agents fail on permissions, context and boundaries — not on model capability.