@svpino: How to build an agent that gets better over time: There are 3 areas an agent can learn from: 1. The model: Only works f…
Summary
Santiago Valdarrama shares a framework for building AI agents that improve over time through three learning areas: model refinement, harness optimization, and context accumulation, emphasizing the importance of learning from user corrections.
View Cached Full Text
Cached at: 06/25/26, 09:27 PM
How to build an agent that gets better over time:
There are 3 areas an agent can learn from:
-
The model: Only works for code and math, where a computer can score right vs. wrong. Leave this to the big labs.
-
The harness: These are the steps, tools, and safety checks you build around the model. This is easy to control and will give you a huge payoff now.
-
The context: This is a plain-text representation of what the agent has learned. Probably the simplest place to start.
But there’s something else that most people miss:
Your agent should learn from its users.
You want to learn from every time a user fixes the agent’s decision. Nothing can replace feedback from real usage.
Similar Articles
@svpino: How you can build a moat with self-learning agents: If you can build an agent that gets better every time people use it…
A Twitter thread offering strategic advice on building self-learning agents that improve with use, covering dual learning sources, memory types, and data ownership.
@Saboo_Shubham_: Static agents won't survive 2026. Self-learning agents are WHAT you need, and the best ones get better every time someo…
A discussion on how AI agents learn in three layers (model, harness, context) and why capturing user corrections as labeled examples is key to building self-learning agents that improve over time.
@DeRonin_: How to naturally build your own self-improving agents: a self-improving agent learns from its own mistakes and rewrites…
A practical guide explaining three levels of building self-improving AI agents, from manual loops to automated design, with recommended tools and frameworks.
@qinzytech: https://x.com/qinzytech/status/2066585405479371092
A technical analysis of two approaches to building self-evolving AI agents: model-based (via architecture like SSMs or transformer with fast-weight updates, and training methods) and harness-based (via memory or meta harness that can rewrite itself). The author provides practical recommendations for different audiences.
Building agents taught me the model is rarely the problem. What's your hard-won lesson?
A developer shares hard-won lessons from building AI agents: focusing on tool design over model choice, using small loops instead of giant prompts, logging agent context, adding guardrails early, and creating small evals to catch bugs.