Thailand's Pathumma Connect Expands to Agentic AI for Five Government Agencies

·37 views

Thailand's NECTEC (National Electronics and Computer Technology Center) announced on September 15, 2026, the evolution of its Pathumma language model ecosystem into Pathumma Connect, an agentic AI platform enabling multi-step task automation within a single conversation. The platform covers seven domains including agriculture, government, water, tourism, culture, education, and enterprise, with five pilot agencies: the Department of Provincial Administration, Land Department, FDA, Revenue Department, and Rights and Liberties Protection Department. Pathumma Connect builds on an earlier centralized AI chatbot launched on August 6, 2026, by OPDC, NSTDA, and DGA, and acts as an integration layer linking existing agency chatbots rather than replacing them. While the platform supports on-premise deployment to keep data within agencies, all Pathumma model variants are built on foreign base models including Alibaba's Qwen and OpenAI's Whisper, meaning Thai sovereignty applies at the data level rather than the foundational model level.

Read the full story at DEV Community

This is an AI-generated summary. ShortSingh links to the original source for the complete article.

Discussion (0)

Cekura, YC F24 Startup, Hiring Forward Deployed Engineer in US

Cekura, an AI startup backed by Y Combinator's F24 batch, has posted an open position for a Forward Deployed Engineer based in the United States. The job listing was shared on Y Combinator's official company jobs board. The role appears to be focused on hands-on technical deployment work, a common function at early-stage AI companies. The posting attracted no comments or upvotes on Hacker News at the time of publication.

0 comments Read more at Hacker News

ProgrammingDEV Community ·

SoundScript Library Lets .NET Apps Generate Audio Dynamically from App State

A .NET library called SoundScript, targeting .NET 10, enables developers to generate audio procedurally from application state rather than relying on static WAV file libraries. Instead of maintaining separate audio files for every event variation, developers define musical rules — including tempo, dynamics, and motifs — that map directly to runtime conditions. For example, a warning sound's intensity can automatically scale with a severity level, or a game's background tempo can increase as a player advances through levels. The library compiles a simple text-based script describing musical intent and renders it into a WAV file on the fly. This approach reduces asset management overhead in games and interactive applications where sound needs to vary based on changing runtime data.

0 comments Read more at DEV Community

ProgrammingDEV Community ·

Silent JS Bugs Skewed Months of Analytics on a Live Product Search Site

A developer running OneFindMe, a multilingual AliExpress product search engine, discovered a cluster of long-standing JavaScript bugs only after installing a session-recording tool — despite all automated checks showing green. A flawed HTML-entity escaping method in inline click handlers caused syntax errors for product titles containing apostrophes, silently breaking favourite, share, and analytics tracking on roughly a third of every results page. Because the underlying product links remained intact, no sales were directly lost, but click-through rate data collected over months was systematically undercounted, corrupting product decisions made on that data. A second bug referenced a renamed CSS class that no longer existed, rendering two buttons completely inert, a fact only made visible when session recordings showed a user clicking the same dead button five times in 26 seconds before abandoning the session. The incident highlights that passing automated checks does not confirm a working user experience, and that client-side errors which leave no server-side trace can only be reliably caught through direct page observation.

0 comments Read more at DEV Community

ProgrammingDEV Community ·

SoundScript Library Lets .NET Apps Generate Audio from JSON Data

A .NET package called SoundScript enables developers to convert structured JSON data into WAV or MIDI audio files without building a dedicated audio engine. The library, version 13.0.0 targeting .NET 10, works by letting the application map its own JSON schema to SoundScript source code, which then handles compilation and rendering. Developers can link business logic variables — such as alert severity or application state — to musical parameters like dynamics and note sequences. The tool maintains a clear separation between application data and audio rendering, keeping business rules within the application layer. SoundScript is available via NuGet and is positioned for use cases where audio output needs to respond dynamically to changing application state.

0 comments Read more at DEV Community