Read our latestState of AI development report– explore trends, usage, and emerging patterns!Read the results →
Read our latestState of AI development report
Book a Demo
ABOUT THE AUTHOR
Anita Kirkovska
Founding Growth Lead

An AI expert with a strong ML background, specializing in GenAI and LLM education. A former Fulbright scholar, she leads Growth and Education at Vellum, helping companies build and scale AI products. She conducts LLM evaluations and writes extensively on AI best practices, empowering business leaders to drive effective AI adoption.

Articles by
Anita Kirkovska
View All
Model Comparisons
GPT-4.5 vs Claude 3.7 Sonnet
February 28, 2025
Guides
GPT 4.5 is here: Better, but not the best
February 27, 2025
Model Comparisons
Claude 3.7 Sonnet vs OpenAI o1 vs DeepSeek R1
February 25, 2025
8 min
Customer Stories
How RelyHealth Deploys Healthcare AI Solutions 100x Faster
February 20, 2025
8 min
Guides
How can agentic capabilities be deployed in production today?
February 18, 2025
Guides
The Six Levels of Agentic Behavior
February 13, 2025
5 min
Customer Stories
How Revamp Reliably Runs 15M+ LLM Executions in Production
February 10, 2025
5 min
Model Comparisons
Analysis: OpenAI o1 vs DeepSeek R1
January 30, 2025
5 min
Guides
Claude 3.7 Sonnet: Can It Actually Reason?
January 30, 2025
5 min
Guides
Breaking down the DeepSeek-R1 training process—no PhD required
January 24, 2025
10 min
Guides
What to do when an LLM request fails
December 16, 2024
5 min
Model Comparisons
Llama 3.3 70b vs GPT-4o
December 10, 2024
10 min
Product Updates
Native support for SambaNova inference in Vellum
December 9, 2024
2 min
LLM basics
AI Development Survey: Help us build the ultimate AI changelog
November 25, 2024
2 min
Product Updates
Announcing Native Support for Cerebras Inference in Vellum
October 24, 2024
4 min
Customer Stories
How Glowing Personalized Hospitality Experiences with AI
October 1, 2024
Guides
OpenAI o1: Prompting Tips, Limitations, and Capabilities
September 13, 2024
Model Comparisons
Analysis: OpenAI o1 vs GPT-4o vs Claude 3.5 Sonnet
December 17, 2024
Guides
How to Become the Best Prompt Engineer in 2024
September 11, 2024
Customer Stories
How Woflow Decoupled AI Updates for 50% Faster Delivery — Without the Infra Stress
September 10, 2024
Guides
Understanding Logprobs: What They Are and How to Use Them
September 3, 2024
Guides
GPT-5: What should we expect?
August 30, 2024
Customer Stories
How this EdTech Company Made AI Development 10x Faster with Vellum
August 28, 2024
Guides
The 6 Stages for Successful AI Implementation
August 20, 2024
Customer Stories
How Vellum Helped Odyseek Build Smarter AI Faster
August 16, 2024
Guides
GraphRAG: Improving RAG with Knowledge Graphs
August 2, 2024
Model Comparisons
Llama 3.1 405b vs Leading Closed-Source Models
July 26, 2024
Model Comparisons
Evaluation: Llama 3.1 70B vs. Comparable Closed-Source Models
July 24, 2024
Model Comparisons
GPT-4o Mini v/s Claude 3 Haiku v/s GPT-3.5 Turbo: A Comparison
July 19, 2024
Guides
Agentic Workflows in 2025: The ultimate guide
July 11, 2024
Model Comparisons
Claude 3.5 Sonnet vs GPT-4o
June 25, 2024
Guides
Building an AI Agent for SEO Research and Content Generation
May 29, 2024
Model Comparisons
Analysis: GPT-4o vs GPT-4 Turbo
May 14, 2024
Model Comparisons
Llama 3 70B vs GPT-4: Comparison Analysis
May 8, 2024
Customer Stories
Rentgrata's Test Driven Journey to a Production-Ready Chatbot
May 2, 2024
Guides
10 LangChain Alternatives in 2024
December 12, 2024
Guides
LlamaIndex vs LangChain Comparison
May 1, 2024
Guides
RAG vs Fine-Tuning: How to Choose the Right Technique?
April 30, 2024
Guides
Tutorial: Setting Up OpenAI Function Calling with Chat Models
April 23, 2024
Customer Stories
How Autobound Achieved a 20x Faster End-to-End LLM Iteration Cycle
April 11, 2024
Model Comparisons
Claude 3 Opus vs GPT-4: Task Specific Analysis
April 8, 2024
Customer Stories
Redfin's Test Driven Development Approach to Building an AI Virtual Assistant
April 9, 2024
Customer Stories
Suggestic's Collaborative Journey to Faster AI Development
April 1, 2024
Guides
How to Count Tokens Before you Send an OpenAI API Request
March 27, 2024
Guides
Getting Started with Prompt Chaining
March 26, 2024
Guides
RAG vs Long Context?
March 20, 2024
Guides
How to Evaluate Your RAG System?
March 8, 2024
Guides
LLM Benchmarks: Overview, Limits and Model Comparison
September 11, 2024
Guides
How can I get GPT-3.5 Turbo to follow instructions like GPT-4?
February 15, 2024
Customer Stories
How Lavender cut latency by half for 90K monthly requests in production
February 13, 2024
Guides
Prompt Engineering Guide for Claude Models
February 2, 2024
Customer Stories
How Codingscape improved time-to-market for their AI apps
February 1, 2024
Guides
How can I use LLMs to classify user intents for my chatbot?
January 11, 2024
Guides
Four LLM hallucinations and ways to fix them
January 1, 2024
Guides
3 Strategies to Reduce LLM Hallucinations
January 3, 2024
Guides
Zero-Shot vs Few-Shot prompting: A Guide with Examples
December 21, 2023
Guides
Classifying Customer Tickets using Gemini Pro
December 20, 2023
Model Comparisons
Best Model for Text Classification: Gemini Pro, GPT-4 or Claude2?
December 13, 2023
Guides
Tree of Thought Prompting: What It Is and How to Use It
November 30, 2023
Guides
User Confidence in OpenAI vs. Alternative models/providers
November 28, 2023
Guides
First impressions with the Assistants API
November 16, 2023
Guides
The ABC’s of Multimodal AI: Models, tasks and use-cases
November 6, 2023
Guides
Automatic data labeling with LLMs
November 2, 2023
Customer Stories
How Narya's team uses Vellum for auto data labeling & deployments
October 25, 2023
Guides
Chain of Thought Prompting (CoT): Everything you need to know
September 11, 2024