Field reports from the TechKis team.
Engineering notes, architecture deep-dives and honest takes on what we’re learning while shipping AI-first software.
Top highlights
- 9 min read·AI EngineeringCostEngineering Practice
What an AI pilot actually costs — a line-item breakdown
Most AI pilot budgets are wrong because they only price the build. Here's the honest line-item breakdown — discovery, data prep, evaluation, build, inference and the run cost nobody quotes — and where pilots quietly overrun.
Read post - 9 min read·PerformanceCore Web VitalsSEO
A Lighthouse 100 doesn't mean your site is fast
Lighthouse is a lab simulation on a throttled mid-range phone. Google ranks on field CrUX p75 for LCP, INP and CLS. Here's why the two disagree, and what to measure instead.
Read post - 9 min read·AI EngineeringSEOContent
Getting cited by AI search — how to be the answer, not the tenth blue link
ChatGPT, Perplexity and Google AI Overviews cite sources instead of listing links. Here's how answer engines pick what to quote, and how to be the citation.
Read post
All posts
29 posts · page 2 of 5
- 9 min read·AI EngineeringArchitectureAPIs
MCP vs A2A vs HTTP APIs — what's actually different, and when each one wins
MCP, A2A and plain HTTP APIs solve overlapping but distinct problems. Here's what each protocol is really for, how they compose, and how to pick without cargo-culting the newest acronym.
Read post - 9 min read·AI EngineeringProductSaaS
Why every SaaS will have AI agents by 2027 — and what that changes about how you build
Agents are moving from bolt-on chat widgets to the primary way users get work done inside software. Here's the shift that's driving it, what an agent-native SaaS actually looks like, and what it means for your architecture and moat.
Read post - 9 min read·AI EngineeringArchitectureDeveloper Experience
Building AI features without LangChain — the raw-SDK path most teams should take first
You don't need a framework to ship an AI feature. Here's what the raw provider SDK actually gives you, the small amount of glue you write yourself, and when a framework finally earns its place.
Read post - 10 min read·AI EngineeringRAGRetrieval
RAG is not dead — you're just building it wrong
"Just use a bigger context window" doesn't kill RAG. Bad chunking, no reranking, and retrieval you never evaluate kill RAG. Here's what a retrieval pipeline that actually works looks like.
Read post - 9 min read·AI EngineeringMemoryArchitecture
AI memory explained — short-term vs long-term, and why the difference matters
"Memory" in AI apps means two very different mechanisms with different costs and failure modes. Here's what short-term (context) and long-term (retrieval/state) memory actually are, and how to design both.
Read post - 9 min read·AI EngineeringPrompt EngineeringTesting
Prompt engineering is becoming a software engineering problem
Clever wording was phase one. Production prompts now need versioning, tests, evals, regression tracking and CI — the same discipline as any other code. Here's what that looks like in practice.
Read post