24 au 26 février, 2027
Montréal, Canada
Clean Context, Clear Mind
LLM agents often feel random, forgetful, or fragile, but in most cases the problem is the context, not the model. Prompts, tool output, memories, and failed hypotheses all compete for attention. This talk shows how clean context makes agents more reliable, cheaper, and easier to trust, with practical patterns like forking, filtered CLI output, and careful MCP usage to keep agents focused and out of the token landfill.
Florian Engelhardt
Datadog
Florian is married with six kids and likes to play table tennis, table football, chess, and MTG. He is also a software engineer and builds a PHP profiler at Datadog.
He started writing software on an IBM PS/2 30 286 in GW-BASIC back in 1993, throughout the 90s he learned HTML, JavaScript, Perl, C, and a bit of Assembler. It was September 2000 when he was introduced to PHP and he thought nobody would ever need it, but boy he was wrong.
