https://courses.digitable.life/en/tags/ai-agents/ Recent content in ai agents on Digitable Courses Hugo -- gohugo.io en-US Tue, 01 Sep 2026 10:00:00 +0300 https://courses.digitable.life/en/post/prompting-study/ Tue, 01 Sep 2026 10:00:00 +0300 https://courses.digitable.life/en/post/prompting-study/ Nine of our measurements in a row: eight well-known prompting techniques against a plain prompt, a detailed brief against a short one, a cluster of agents against a single one. Self-consistency gives +28.8 points on arithmetic and +48.0 on tasks that were in nobody’s training set; on code the techniques only do harm; on recall questions seven techniques out of eight lose. Three measurements ended in an honest “cannot be told apart”, one was never finished. Everything is brought together here — together with the list of what we did not measure. https://courses.digitable.life/en/post/spec/10-ai-agents/ Mon, 03 Aug 2026 06:10:00 +0300 https://courses.digitable.life/en/post/spec/10-ai-agents/ How to integrate flang into the agent loop: read-only MCP tools, programmatic document build, guard on real data, and machine-readable refusal. https://courses.digitable.life/en/post/spec/00-overview/ Mon, 03 Aug 2026 06:00:00 +0300 https://courses.digitable.life/en/post/spec/00-overview/ A business rule usually lives in three places — the ticket, the code and the tests — and drifts apart. This course is about writing it once in flang, so the compiler proves termination, checks the postcondition, runs the examples and prints the result into working code. https://courses.digitable.life/en/video/ai-basics/ Sun, 31 May 2026 15:58:07 +0300 https://courses.digitable.life/en/video/ai-basics/ In this video: