Our Blogs | Opik by Comet

Understanding Your Claude Code Spend: What’s Actually Driving the Cost

I’ve been spending time looking at how teams are actually using Claude Code, and one thing keeps coming up: most…

Read


Pretraining: Breaking Down the Modern LLM Training Pipeline

LLM training shapes everything from what a model knows to how it reasons and responds. So, understanding how models are…

Read


Major Releases: Auto-Optimize Multi-Step Agents, Annotate & Score Entire Chatbot Convos

When multiple steps in an agentic system are contextually related, logging and evaluating individual LLM calls doesn’t tell the whole…

Read


AI Assisted Coding with Cursor AI and Opik

How AI can help you move beyond vibe coding and become an effective AI engineer faster than you think Dear…

Read


Release Highlights: Discover Opik Agent Optimizer, Guardrails, & New Integrations

As LLMs power more complex, multi-step agentic systems, the need for precise optimization and control is growing. In case you…

Read


Announcing Opik’s Guardrails Beta: Moderate LLM Applications in Real-Time

We’ve spent the past year building tools that make LLM applications more transparent, measurable, and accountable. Since launching Opik, our…

Read


From Observability to Optimization: Announcing the Opik Agent Optimizer Public Beta

At Comet, we’re driven by a commitment to advance innovation in AI, particularly in the realm of LLM observability. Our…

Read


Major Releases: MCP Server & Google Agent Dev Kit Support

We’ve just rolled out two major updates in Opik, Comet’s open-source LLM evaluation platform, that make it easier than ever…

Read


How Contributing to Open Source Projects Helped Me Build My Dream Career in AI

6 years ago, I decided to open-source my Python code for a personal project I was working on, which led…

Read


LLM Evaluation Complexities for Non-Latin Languages

Large language models (LLMs) have revolutionized natural language processing, yet most development and evaluation efforts have historically centered around Latin-script…

Read


SelfCheckGPT for LLM Evaluation

Detecting hallucinations in language models is challenging. There are three general approaches: The problem with many LLM-as-a-Judge techniques is that…

Read