Engineering
How Tomorrow Central is built.
Deep dives into the architecture, tradeoffs, and engineering decisions behind the platform.
Try site search on your own website before you verify it
A demo shows you someone else's catalogue. The useful test is your own pages, your own product names and the searches your visitors actually type. How to try Tomorrow Central Search on your website in a few minutes, what to test, and how to go live when you're ready.
Site search for publishers: helping buyers find the right report, book or course
Buyers of reports, books and courses type a market, a country and a year, not your title. Why that defeats a publisher's search box, eight searches to try on your own site today, and what makes them work.
Part number search for B2B catalogues: making model numbers, part codes and specs findable
Buyers of parts type codes, not descriptions, and they type them with dashes, spaces, half the digits or a size on the end. Why most website search misses those, how to write your catalogue so codes are found, and what Tomorrow Central Search handles for you.
How to make your catalogue searchable by AI agents, with your permission and nothing more
Ask an AI assistant whether you stock an item and it will usually guess, or scan whatever you pasted into the chat. Here is how to give Claude and other MCP-capable agents a real search over your catalogue, what an agent can and cannot do once connected, and how to set it up on Tomorrow Central.
Let your AI agent update your search index, with your consent
Your catalogue changes every day and your site search only knows what you last uploaded. Here is how to let an AI agent upload the catalogue, read the zero-result searches and report back, doing only what you approved, with a worked example and the checks to put in place first.
Algolia alternative for small catalogues: Algolia vs Elasticsearch, OpenSearch and managed search
For a few thousand items, picking the search engine is the easy part. A fair comparison of Algolia, Elasticsearch, OpenSearch and Tomorrow Central Search, and when each one is the right choice.
Site search for your catalogue: typo-tolerant search without running a search cluster
When a catalogue search says "no results", the item is often there. Here is why catalogue search fails, what typo tolerance should actually mean, how to choose between running a search engine and using a managed one, and how Tomorrow Central Search handles catalogues of a few thousand items.
How to add search to your website: upload a file or import your site
Adding search to a website is mostly a data job. The whole path in nine steps: bring your catalogue in as a file or import it from your site, verify the domain, test, then put a search box live.
How Cloud Cost Sentinel works: finding AWS waste without guessing
Cloud Cost Sentinel reads an AWS account and reports what looks idle, with the evidence behind every call. Here is exactly what it inspects, how a verdict is reached, how confidence is scored, and why it can never delete anything.
How AgentState handles crash recovery
A deep dive into how Tomorrow Central detects agent failures, checkpoints state, and resumes execution — without duplicating work.
Thread isolation: why it matters for parallel agents
When multiple agents run concurrently, state cross-contamination is a silent killer. Here's how we solve it.
Building a resilient agent loop
The anatomy of a production-grade agent loop: retries, timeouts, checkpointing, and why most frameworks get this wrong.