Tag
9 posts
3 posts
Inside the AI agent backend: LangGraph runtimes cached on a 16-part key, progressive skill disclosure with a 128-tool cap, compare-and-swap settings mirrors, and a feedback pipeline that groups meetings by red flags.
Building a voice agent that takes real phone calls: HMAC-verified webhooks, a sideband transcript pump, delegation-based tool dispatch, and a refusal layer protected by cryptographic digests.
A centralized settings module as the last line of defense: boot gates that collect every missing variable, fallbacks that log at ERROR instead of degrading quietly, and why point-of-use beats boot-time for some checks.
4 posts
The small but sharp security machinery behind an API endpoint: in-memory token buckets, peppered SHA-256 with constant-time comparison, and deterministic session namespacing.
iCalendar RRULE looks like a solved problem until INTERVAL=0 hangs your sweep, BYHOUR means the wrong hour across timezones, and legacy rows encode their whole schedule in one string. A field guide to doing it safely.
My DevBG talk on Python's versatility: its syntax and features such as context managers and decorators, object-oriented programming, and its role in machine learning.
Notes from the Enterprise AI Application panel at the Confindustria Bulgaria conference, where I discussed how AI and machine learning drive innovation in manufacturing and integrate with MRP/ERP systems like SAP.
1 post
An introduction to the stack data structure in Python, covering sequential and linked implementations, a push/pop speed comparison, and two applications, an infix-to-postfix expression converter and a maze solver.
1 post
An introduction to linear lists in Python, comparing sequential lists (arrays) with linked lists, deriving the average cost of insert and delete operations, and implementing linked list insertion, deletion and polynomial addition.