Blog

Engineering, product updates, and behind-the-scenes.

EngineeringMarch 24, 20264 min read

How We Made Tripplet More Stable in March

We quietly shipped a round of stability and security improvements to Tripplet's auth system this week. Password reset tokens, rate limiting, and error handling all got tightened up. Here's what we changed and why it matters.

Read more
Models5 min read

Introducing Taipei 3.1, Majuli 3.1, and Suzhou 3.1

Our three models just got a major upgrade. Taipei 3.1 brings deeper reasoning with extended thinking. Majuli 3.1 cuts response times by 40%. Suzhou 3.1 produces richer creative output across writing, code, and image prompts. Here's what changed and why.

March 5, 2026
Engineering8 min read

How We Built the Code Workspace

Tripplet's Code workspace lets you describe an app in natural language and get working files in seconds. Under the hood, it's a chat-driven code generation pipeline with live preview, multi-file editing, and one-click deploy. We walk through the architecture decisions.

February 28, 2026
Product4 min read

Extended Thinking: When and Why to Use It

Extended Thinking lets Tripplet's models spend more time reasoning before responding. It's not always faster, but for complex problems — math, multi-step logic, code architecture — it produces significantly better results. We explain how the mechanism works and when to toggle it on.

February 22, 2026
Engineering7 min read

Inside Our Image Generation Pipeline

Generating images from text requires more than just calling a diffusion model. We built a pipeline that handles prompt enhancement, style consistency, aspect ratio control, and automatic quality scoring. This post covers the end-to-end flow from user prompt to final image.

February 15, 2026
Company6 min read

Why Tripplet Is Open Source

We released Tripplet under the Unlicense — anyone can use, modify, and ship it. This wasn't an obvious decision for an AI product. We share our reasoning, the tradeoffs we considered, and how open source has shaped our development process and community.

February 8, 2026
Product4 min read

Video Generation Is Here

You can now generate short videos from text prompts in Tripplet. We support multiple aspect ratios, durations up to 10 seconds, and various visual styles. This post covers the capabilities, limitations, and what's coming next for AI video.

February 1, 2026
Engineering6 min read

Smart Model Routing: Picking the Right Model Automatically

Not every question needs the most powerful model. We built a routing system that analyzes your prompt's complexity and picks the optimal model — balancing speed and quality in real time. Here's how the classifier works.

January 25, 2026
Product5 min read

How Tripplet Searches the Web

When a conversation requires current information, Tripplet can search the web, pull relevant sources, and synthesize the results into its response. We explain the search pipeline, source ranking, and how we present citations.

January 18, 2026