Tag

agents.

12 writings found

Latest Archives

Why Lines of Code Still Matter When Agents Code

Coding agents are changing productivity metrics. I argue lines of code remains meaningful when measuring agent output - if the quality stays high.

Gemini 3.7 Flash: The Workhorse Model That Changes Agent Economics

Google's new Gemini 3.7 Flash delivers major coding improvements and 50% lower pricing. What it means for building production AI agents.

Agent Memory Without the Collapse: Why Context Matters More Than Compression

How selective retrieval beats comprehensive playbooks for agentic memory. Same lessons, radically different token costs.

LFM2.5-2.6B: Small Models Win on Agents

The 2.6B parameter LFM2.5 outperforms models 4x its size on instruction following and tool use. What this means for on-device AI.

Building the Agent Cloud: Infrastructure for a Non-Human Future

The cloud we built for humans won't work for agents. Here's what an agent-native infrastructure actually needs to look like.

How GitHub Cut Copilot Review Cost 20% by Fixing Agent Instructions

GitHub's Copilot code review team found that swapping tools wasn't enough. Rewriting agent instructions around reviewer workflows cut costs by 20%.

How Near-Free AI Intelligence Rewrites Data Systems

AI inference costs have fallen 50x per year. Here's what that means for how we build, query, and trust data systems going forward.

How Near-Free AI Intelligence Will Reshape Data Systems

AI inference costs have dropped 50x per year. Here's what that means for data systems, agentic workloads, and the developers building them.

How Near-Free AI Intelligence Will Reshape Data Systems

AI inference costs have dropped 50x in a year. Here's what that means for data systems, agentic workloads, and developers building the next layer of infra.

How Near-Free AI Intelligence Will Reshape Data Systems

AI inference costs have dropped 50x per year. Here's what that means for how we build, query, and trust data systems going forward.

AI as an Organizational Multiplier: The Case for Fine-Scoped Agents

How AI amplifies existing organizational practices, why averages deceive us, and the emerging patterns for safer agentic systems in production.

Agentic AI – From Buzzword to Gamechanger (The Real Story)

Agentic AI is dominating AI headlines and industry conferences—and for good reason. The arrival of autonomous AI agents is forcing a rewrite of what automation means and what virtual assistants can really do.

View all writings →