Jonathan Schneider

As AI agents take more and more of a leading role in crafting code, it’s suddenly become apparent that the “first user” of engineering productivity tooling will be shifting towards agents rather than individual human developers.

With a human still at the helm of a fleet of agents in producing software, and increasingly less involved in the writing of individual lines of code, maximizing engineering value delivery means making every tool call faster, more token efficient, and more accurate.

Many of our members have now brought in not one but several coding agents and foundation models in an effort to accelerate everything from feature delivery to application modernization. But now attention will shift to how to ever tighten the tool call feedback loops. Each percentage gain in tool call efficiency multiplied across an increasingly large fleet of agents creates an outsized impact.

We’ll cover a variety of concrete cases where tool call efficiency can be harvested immediately:

• Trigram index based code search
• Lossless Semantic Tree access/manipulation patterns
• Mining data from chat transcripts
• Exposing multi-repository commit/PR activity to agents.