BLOG.

Why login history in the J+P Autodíly admin panel gets its own table instead of sharing the audit log — and why the login record must never touch the critical path.

Why having an e-shop isn't enough — and how a single generated XML feed puts a small bike shop's catalog in front of shopping comparators, twice a day, with no manual work.

Why we removed the Filter button from the J+P Autodíly admin panel and let filters write directly to the URL. Debounce, server-rendered listings and progressive enhancement in one shared component.

How we unified search and catalogue on J+P Autodíly: same filters, same sorting rules, shared component — and everything lives in the URL so a filtered result set is a shareable link.

Why a delivery note per order wasn't enough — and how a single page grouped by delivery routes, one button per route, and an order timeline transformed warehouse operations.

Why 'just refresh the page' doesn't cut it when an admin monitors orders in real time — and how a single SSE pipe with a fingerprint replaced ten polling queries.

Why typing part numbers on a phone keyboard while standing at a pallet is the wrong workflow — and how a mix of native scanning, WebAssembly and server-side OCR turns a phone into a receiving terminal.

Why storing a few numbers in a database isn't enough — document state transitions, correct VAT splitting from gross prices, and a unified outstanding balance for both admin and customer.

How delivery route management works in a white-label auto parts e-shop — from assigning customers to routes to displaying delivery info on documents.

Elowen is a self-hosted AI agent for chat, tools, memory, automation and work across CLI, web, Discord and WhatsApp. Not just another chatbot, but a user-owned control layer for real work.

An AI agent needs access to tools — but not all tools are equally risky. Orca introduces per-tool permissions with a YOLO mode, giving each tool its own trust level.

Complete redesign of the Sarah Hair Salon homepage — from a generic SaaS template to an editorial experience that actually looks like a salon.

How I added automatic language switching to my portfolio based on timezone and browser language — entirely client-side, no API, no flicker.

CoreSynth now has a dedicated AI API landing page that finally explains the real value of Alex Code: you can use it as an AI agent in a web panel or as an API inside your own apps. This is more than a content update — it is sharper product positioning.

I reworked how CoreSynth presents its AI services so they no longer feel like a side note, but like a clear offer with a direct path to action. Small content and navigation changes, big difference in how quickly the product makes sense.

Mission planning in Orca no longer forces a sequential pipeline. The planner now builds a dependency graph where independent phases run in parallel and actually use the available agent capacity.

Orca now sends web push notifications to your phone. When an agent needs your input, a phase needs approval, or a mission finishes, you get a notification with action buttons right in it.

Every task in Orca can now have its own GitHub PR setting: default, on, or off. Two bugs were also fixed that allowed shipping a partial PR before the mission was complete.

Rebuilding Orca's dashboard from a data-dense layout into a spacious, calm overview: glass hero with aurora glow, big stat cards, live agent lane, and no unnecessary tables.

Orca turns the timeline from a simple activity feed into an oversight tool: human task names, clear events, project context, and diffs directly in the event detail.

OrcaSynth — a tool for orchestrating autonomous AI coding agents — is now available as an open-source project under the MIT license. A standalone daemon, web UI, API, and CLI, ready to self-host.

Orca is gaining a product layer for working with multiple AI agents at once: a dashboard, missions, live sessions, outcomes, and a clear view of what the system is doing.

Orca helps manage multiple AI agents at once — from task assignment and progress tracking to safety boundaries. It is built for teams and projects where one agent in one terminal is no longer enough.

Autonomous AI agents can significantly speed up software work, but without clear rules they introduce new risk. Orca combines autonomy levels, safety boundaries, and continuous supervision.

Every stylist now gets her own ICS link for bookings. Connect it to Google Calendar, Apple Calendar, or Outlook and you'll see all your appointments without logging into the admin panel.

Alex generates massive system prompts — hundreds of thousands of tokens. OpenAI automatic prefix caching is free, but only when the prefix stays stable. Here's how a single timestamp bug was killing the cache, and how we fixed it.

AI tools are powerful, but each one usually lives in its own thread. So I built a shared memory layer that connects Claude Code, Codex and Hermes into one long-term context.

Sarah Hair Salon is no longer built around a single calendar. The booking system now supports multiple stylists, separate services, clearer operations, and a smoother reservation flow for clients.

I stopped showing users raw numbers and gave them progress bars, a clean token breakdown, and a modal with cost projections instead. Here's how and why.

We added a communication-style toggle to Alex — four detail levels for responses that persist across devices. How we designed it and why it matters.

Alex is an AI agent that actually runs an auto shop: finds parts by VIN, shows exploded diagrams, orders DIRECTLY on the CORAHB.CZ store, books appointments and answers customers on WhatsApp. 26 tools, 4 languages, built on Next.js and OpenAI.