Engineering notes from the people who build the systems
Practical write-ups on agentic AI, SaaS architecture and automation, plus case studies from our own products. No hype, no invented benchmarks: how we think about the problems and what we would do again.
Building a staged research pipeline over a fixed text corpus
What we learned engineering Taaweel: why research questions need stages, an evidence ledger and a model that argues against itself.
Building a staged research pipeline over a fixed text corpus
What we learned engineering Taaweel: why research questions need stages, an evidence ledger and a model that argues against itself.
Read the insightAgentic AI · 7 minSupervisor vs hierarchical agent orchestration: how to choose
Three orchestration patterns, what each costs you, and a simple rule for picking the smallest one that works.
Read the insightAgentic AI · 8 minHybrid RAG on PostgreSQL: vectors, keywords and filters together
Why vector search alone fails on real enterprise data, and how to combine pgvector, full-text search and metadata in one database.
Read the insightAgentic AI · 6 minDesigning human-in-the-loop review lanes for AI agents
Autonomy is a dial, not a switch. How to decide what an agent may do alone, what needs a person, and how to build review that is fast.
Read the insightAgentic AI · 6 minIdempotent tool calling: letting agents act without duplicating work
Models retry, repeat and misread. Here is how to make state-changing tool calls safe when they do.
Read the insightSaaS architecture · 8 minMulti-tenant SaaS: pool, bridge or silo?
The tenancy model shapes cost, isolation and operations for years. A practical guide to choosing it and to proving isolation works.
Read the insightAutomation · 7 minAI customer support triage: routing by urgency and mood
How to classify incoming requests, honour service levels, resolve the routine ones and hand over the hard ones with context.
Read the insightCase study · 8 minRealtime Firestore, tenant isolation and long AI jobs: lessons from a homeschooling platform
Engineering notes from building a multi-tenant family platform on Vue, Firestore and Cloud Functions with AI agents.
Read the insightHave a problem like one of these?
Bring it to an engineer. We will tell you plainly whether and how we can help.