Temporal vs Jenkins, Git Actions, and Terraform

Here's a diagram comparing where each tool sits and what actually makes Temporal different from the CI/CD and IaC tools: The core distinction is what happens when something fails mid-run. Jenkins and GitHub Actions are CI/CD pipeline tools. They react to an event (a push, a PR, a schedule), run a defined sequence of steps … Continue reading Temporal vs Jenkins, Git Actions, and Terraform

Prompt evaluation

# Load env variables and create client from anthropic import AnthropicVertex client = AnthropicVertex(region="global", project_id="<YOUR PROJECT ID>") model = "claude-sonnet-4@20250514" # Helper functions def add_user_message(messages, text): user_message = {"role": "user", "content": text} messages.append(user_message) def add_assistant_message(messages, text): assistant_message = {"role": "assistant", "content": text} messages.append(assistant_message) def chat(messages, system=None, temperature=1.0, stop_sequences=[]): params = { "model": model, "max_tokens": 1000, … Continue reading Prompt evaluation

Claude on Google Cloud

Making the API Request Your server communicates with Vertex using either Anthropic's SDKs or Google's official Vertex SDKs. Anthropic provides official SDKs for Python, TypeScript, Go, and Ruby. Every request must include these key fields: API Key    - Identifies your request to Anthropic Model    - Name of the specific model to use Messages    - List containing the user's … Continue reading Claude on Google Cloud

Claude with Amazon Bedrock

How Chat Applications Work Imagine you're building a web app with a simple chat interface. A user types "Define quantum computing" and clicks send. Here's what actually happens: The user sees a clean interface, but there's a whole system working behind the scenes to generate that response. The Request Flow When a user submits text, … Continue reading Claude with Amazon Bedrock

claude model family

Claude offers three core model families - Opus, Sonnet, and Haiku - each optimized for different priorities, plus Claude Fable 5, a new model tier that sits above Claude Opus. All of these models share Claude's core capabilities - they can handle text generation, coding, image analysis, and other tasks. The key difference is how … Continue reading claude model family

Ollama

Ollama is a free, open-source framework used to run Large Language Models (LLMs) directly on your own computer   How to Install  https://ollama.com https://ollama.com/download https://docs.ollama.com/integrations   ollama serve Error: listen tcp 127.0.0.1:11434: bind: address already in use To start with lets use  Gemini model Use 270Million parameters https://ollama.com/search?q=gemma3 ollama --help Large language model runner Usage: … Continue reading Ollama

Temporal a runtime execution platform for developer

Temporal a reliable runtime for durable function execution developer platform temporal --version temporal version 1.7.2 (Server 1.31.1, UI 2.49.1) temporal server start-dev Temporal CLI 1.7.2 (Server 1.31.1, UI 2.49.1) Temporal Server: localhost:7233 Temporal UI: http://localhost:8233 Temporal Metrics: http://localhost:52731/metrics  brew install temporal http://localhost:8233/namespaces/default/workflows http://localhost:52731/metrics mkdir /tmp/temporal-democd /tmp/temporal-demopython3 -m venv .venvsource .venv/bin/activatepip install temporalio httpx git clone … Continue reading Temporal a runtime execution platform for developer

TypeScript in AI

TypeScript is explicitly designed as a statically typed superset of JavaScript. TypeScript is used for both client-side and server-side development Python and TypeScript are the two primary languages used to write Model Context Protocol (MCP) servers and applications Python: Highly utilized for AI integrations and data engineering. Features FastMCP for rapid server creation. TypeScript / … Continue reading TypeScript in AI

Prisma ORM vs Drizzle ORM (Object-Relational Mapper)

Prisma ORM is connected to LLMs as both a target for AI code generation and through direct integrations like AI coding agents and Model Context Protocol Drizzle ORM is related to Large Language Models (LLMs) primarily through AI-assisted code generation, type-safe AI integrations, and Retrieval-Augmented Generation (RAG) pipelines Prisma provides a high-level, schema-driven abstraction that … Continue reading Prisma ORM vs Drizzle ORM (Object-Relational Mapper)