Instructor-led IT courses across web, mobile, data, design and more.
Many organisations still keep a data warehouse for reporting apart from a data lake for raw files, and pull data from their core systems with nightly batch ETL. The result is data stored twice, numbers that do not match, slow answers to questions that need…
When an organisation's key systems run on PostgreSQL, getting it installed is not enough. The team needs to know why the database slows down, whether data can be restored to the moment before an incident, and how service carries on when the primary server…
Car rental businesses today compete on convenience and how quickly they respond. Most customers browse promotions on their phones, message the shop on LINE and expect to book, pay and get a confirmation straight away, even outside opening hours. Many owners…
In 2026 PostgreSQL is the main database of many organisations, both in newly built systems and in systems migrated from Oracle, SQL Server or MySQL. Reporting teams therefore need to pull data from PostgreSQL directly, yet many still wait for IT to send them…
Many system replacement projects fail or slip, not because the new system does not work, but because the legacy data never makes it across. Data built up over many years tends to be inconsistent, full of duplicates and values that no longer mean anything to…
Hardly any system in today's organisations works on its own. Every project has to connect to accounting, payment gateways, partner systems or cloud services. The common problem is that business and system analysts only specify what happens when everything…
Many business analysts and system analysts have to wait for the development team or a DBA to pull data every time they need to check a problem case. The cycle is slow, and the data that comes back often does not answer the real question. Yet writing SQL well…
The most common problem in system projects is not badly written code but misunderstanding the data from the start. Requirement documents written as plain text, which do not say where each piece of data is stored, what it relates to or which business rules…
Many system projects do not fail because of technology. They fail because the team and the client understood the requirements differently. Clients often describe their problem mixed with a solution they have already decided on, and requirement documents are…
A great deal of office time still goes on gathering figures, building tables and charts, writing reports and preparing management slides every month, even though today's AI tools can analyse data and create Office files directly. Most users still get results…
The questions managers ask most often are about the future: how much will we sell next month, how much stock should we hold, which customers should get which promotion, and which customers are about to leave. Many organisations still answer by taking last…
Customer text is one of the most valuable and least used sources of data: product reviews, social media comments, chats with admins and open-ended survey answers. Thai text is harder to analyse than English because words are not separated by spaces, and it is…
As systems grow to many services, IT operations and service desk teams run into the same problems. One fault sets off dozens of alerts at once, tickets arrive without the right category, the same issue gets solved again because nobody can find the last fix,…
RAG systems built on vector search alone answer well when the answer sits in a single passage, but they often miss when a question has to connect several documents, such as which product models a customer uses that are affected by the latest notice, or when…
Calling an LLM API and getting an answer back takes only a few lines of code, but building an application that works in practice is another matter. Developers have to deal with answers in unpredictable formats, runaway costs, rate limits, data the model does…
Many organisations want staff to ask questions of their databases in plain language instead of waiting for the data team to write SQL every time. Today's LLMs write SQL far better than before, but once they are connected to a real database the same problems…
LINE Official Account is the main channel Thai customers use to contact shops and businesses, yet admins struggle to keep up with questions about prices, stock, order status and the same queries over and over. Older bots that reply by keyword or intent can…
Most SOC teams are not short of data. They are buried in alerts that must be opened one at a time, switching screens to look up IPs or hashes, rewriting queries for every hunt and spending hours turning incidents into reports. AI and LLMs can take a lot of…
Many customers still pick up the phone when something is urgent, yet call centres struggle to answer in peak hours and staff repeat the same answers all day. The latest voice AI speaks Thai far more naturally and replies almost instantly, but building a voice…
Visual inspection is everywhere in business: spotting defective parts on a production line, counting stock on shelves, counting people entering a store, or checking that staff wear their protective equipment. These jobs take a lot of people, are tiring and…
Once staff in every department start using AI, organisations tend to hit the same problems. Each team signs up for a different service and holds its own API keys, nobody knows the total cost, customer data or confidential documents can be sent out by…
Good prompts and RAG solve a lot of problems, but some tasks need more. You may want a model that always answers in your organisation's format, uses domain terms correctly, classifies Thai documents accurately, or lets a small in-house model replace a large…
Getting a chatbot or RAG system to answer well on a developer's laptop does not take long. Keeping it answering well, consistently, in production is another matter. A small prompt edit quietly makes some answers worse, a model upgrade multiplies the bill, and…
Every organisation has documents that someone re-keys every day: invoices, tax invoices, receipts, application forms and contracts, often arriving as scanned PDFs or phone photos. Traditional OCR struggles with Thai and has no idea which number is the net…
