Controlled AI-assisted delivery, DevSecOps and compliance engineering, written from inside environments where somebody eventually has to answer for the outcome. 11 posts and counting.
A good AWS reference architecture will find you the passage that mentions Acme. It will not tell you whether three of those documents are about the same Acme, which one is out of date, or that two of them disagree. Finding something is not the same as knowing something, and the gap between them is where the next few years get interesting.
Salesforce did not raise margin guidance this year because it is covering token spend. That is the first visible instance of a large, sophisticated customer looking at the invoice and asking whether the frontier model was worth it. Behind it sits a 3 to 5 trillion dollar financing requirement and a lot of buildings about to switch on.
Your organisation holds a huge amount of knowledge. That is not the same as your AI being able to consume it. Information survives text extraction while meaning does not, and most retrieval failures are created upstream, at the moment a document became a pile of characters. Why the real transition is documents to knowledge, not documents to AI.
Everyone is wrapping an existing API catalogue in MCP and calling it an agent platform. Anthropic's own figures put a large tool surface at 77K tokens before the model does any work, and tool-selection accuracy drops with it. Integration and agent capability are different design problems, and they should not have the same owner.
Twelve months building Scout taught us that answering a question and knowing whether you can answer it are two very different problems - and only one of them is the actual agent problem. Here is what we built, what we got wrong, and the one thing left to solve.
After 3 years of GAR we've seen AI everything - horror stories and fairytales in every news article, so where are we heading with LLMs and AIs?
MCP introduced the ability to give Agents tools and data; A2A gives Agents the ability to use other Agents - interconnectivity is a known driver for innovation, so what does a network for Agents look like? Coming soon to a future near you!
With Atlas, Salesforce have driven architecture into Agents - that's critically important for performance and cost. Atlas is not another agent workflow; it's a mature and well-considered architecture that we all can use.
Everyone talks about MCP; almost nobody shows what happens on the wire. We trace one real call end to end - the question, the JSON the AI sends, the server response, and the answer the user reads - using our own Visionaire fashion MCP.
Weve done the heavy lifting os you know what standard to align to - and more imprtantly - how to align in the brave new LLM world.
Enterprise AI fails when the cloud does. AeonEdge Ollama brings local inference, control, and survivability to real environments.
