When a Copilot agent responds poorly, the instinct is to blame the model.
Spoiler: it’s almost never the model. The problem sits somewhere between your
prompt and the response — a skill that never loaded, a file that never reached
the context, a t...
BCQuality At Directions NA, Microsoft laid out its vision for the future of
Business Central development. As you might expect, it’s an agentic one. The role
of an AL developer is moving toward an agentic workflow — how far and how fast
will depend...
Where are we coming from? Just six days ago. On April 22, I wrote that things
were moving at a pace most people weren’t really noticing, at least in my
circle. Anthropic, GitHub, and SAP all made their moves almost at the same time.
The signal was...
This guide provides a comprehensive overview of setting up and utilizing
BC-Bench for agent evaluations. It includes the installation process, running
evaluations, and interpreting results, emphasizing the necessity of a Windows
Server VM for full...
AL Development Collection (ALDC) revolutionizes AI-assisted coding by
introducing a structured delivery model that prioritizes clarity and human
oversight. Each project begins with a detailed spec contract, ensuring that
every requirement, design,...
Busy stretch this week. Anthropic, GitHub and SAP all moved within days of each
other, and the signal isn’t random: the flat-rate AI subscription model that
carried us through the last couple of years is starting to break. Not for users
— for the ...
Microsoft's Business Central version 28 introduces significant changes to the
payment reminders module, transforming it from a rarely used feature into a
vital part of automated collections management. The mandatory incorporation of
new communicat...
BC-Bench is an innovative open-source benchmarking framework from Microsoft that
revolutionizes how coding agents are evaluated within the Business Central
ecosystem. It allows for a standardized comparison of agents like Claude Code
and GitHub Co...
14
Like
(0)