There Is No Cake
The Sweet Illusion of a Feature Sprint In every development cycle, there’s a moment of clarity—a fresh feature, well-defined, ready to be built. At the start, it looks simple, digestible. A piece of cake. As engineers dive in, that cake gets eaten. Each commit, each pull request, each problem solved takes a bite out of […]
Managing (Agentic) Expectations: A Case Study in Memory Management
Understanding and working with AI agents is going to be one of the most transformative technological shifts in human history. As humans, we have a long tradition of anthropomorphizing the world around us, projecting human-like qualities onto deities, animals, weather, and even social constructs. Historically, this has often been a flawed exercise, as it imposes […]
Why Agents Can’t Learn from Historical Data: The Importance of Counterfactuals
Agents can’t learn from historical data. They can make assumptions from it, but they can’t learn. Say a user often shows up on Friday between 6–7pm. Does that mean it’s a good time to engage them? No one knows. Because the real question isn’t “When does the user show up?” It’s: “Would they show up more […]
The Importance of Abstraction Layers in Agentic Systems
One of the most important components of an agentic system is its abstraction layer — a framework that organizes surface-level details into higher-level, strategic categories. Abstraction enables transfer learning. It allows your system to take insights from one context and apply them to another. That’s essential to agentic learning (and, therefore, is core to how […]
A/B Testing vs. Bandits vs. Predictive Models vs. Agentic Learners: A Stock Market Analogy
I’ve had people ask me what the difference is between A/B testing, multi-armed bandits, predictive/ML models, and agentic learners. Let’s use an analogy. Imagine you’re investing in the stock market: A/B Testing is like back-testing a single stock strategy (e.g., “Tech stocks beat energy in 2020, so we’ll only buy tech”). It’s rigid—once you lock […]
The Explore/Exploit Tradeoff: Understanding Its True Implications in AI Systems
When someone claims their system “navigates the explore/exploit tradeoff,” they’re not saying anything meaningful — that phrase has become table stakes in conversations about agentic systems. But that doesn’t make the underlying challenge any less important. Think of it this way: if you only explore, you’re like a mountaineer who says “I don’t care which […]
Five Pillars of Agentic Decision Making
As we’ve built Aampe, I’ve come to the view that if you’re trying to build or evaluate an agentic system, here are the questions you need to answer: Do you have a massive, dynamic inventory of messages? An agentic system requires thousands — often tens or hundreds of thousands — of unique, sendable messages. This […]
LLMs aren’t sufficient to build agentic systems
An LLM, by itself, cannot be truly agentic. This is also true of swarms, teams, workflows, and other kinds of “multi-agent” systems. If an LLM is doing all of the driving, then you’re dealing with something other than an agentic system. That’s why, at Aampe, LLMs are an appendage, not a foundation. LLMs excel at […]
How Agentic Systems Balance Exploration and Exploitation
In an agentic architecture, that balance between exploration and exploitation emerges naturally from the system’s structure — no need for hand-tuned ratios. Thompson Sampling is a convenient tool for navigating that tradeoff. Early on, when every option is uncertain, the system explores widely: flat distributions mean random draws lead to random choices. As the system […]
Why LLMs and RAG Aren’t Enough for Building Agentic AI Systems
I wrote a post recently (linked in comments below) on why agentic systems require structures for semantic-associative memory, and why LLMs lack the architecture to do anything but procedural memory. Therefore: LLMs aren’t sufficient to build agentic systems. Someone replied with a very thoughtful question about Retrieval-Augmented Generation (RAG), a method that enhances language models […]