2026
- January 9 - Deploying Real-Time Solana Data Streams on Cloudflare Containers with LaserStream
- January 10 - DeFiTuna: On-Chain Limit Orders on Solana
- January 18 - Building Long-Running TTS Pipelines with LangGraph: Orchestrating Long-Form Audio Generation
- January 25 - Agentic Job Pre-Screening with LangGraph + DeepSeek: Auto-Reject Fake “Remote” Roles
- February 3 - Evals for Workflow-First Production LLMs: Contracts, Rubrics, Sampling, and Observability
- February 5 - Schema-First RAG with Eval-Gated Grounding and Claim-Card Provenance
- February 7 - AI Observability for LLM Evals with Langfuse
- February 8 - AI-Powered Skill Extraction with Cloudflare Embeddings and a Vector Taxonomy
- February 8 - Agent Skills spec + Mastra integration
- February 10 - AI-Driven Company Enrichment with DeepSeek via Cloudflare Browser Rendering
- February 11 - OpenRouter Integration with DeepSeek
- February 11 - Langfuse Features: Prompts, Tracing, Scores, Usage
- February 12 - LangSmith Prompt Management
- February 13 - Streaming OpenAI TTS to Cloudflare R2
- February 13 - Building a Job Search Agent with Google ADK and Search Grounding
- February 16 - Production-Ready AI Job Classification in Python with LangChain and Cloudflare Workers AI
- February 17 - Building an Automated Architecture Reviewer with Claude Opus 4.6
- February 20 - Concurrent AI Agents on CF Workers — Three-Level Rig Patterns
- February 21 - Trigger.dev Deep Dive: Background Jobs, Queue Fan-Out, MCP, and Agent Skills
- February 23 - BMAD Method + Langfuse + Claude Code Agent Teams in Production
- February 24 - How I Built a UX Team with Claude Code Agent Teams
- February 25 - The Agent That Says No: Why Verification Beats Generation
- February 25 - Why Do AI Agents Keep Making the Same Mistakes?
- February 25 - How We Built an Agent That Edits Its Own Instructions
- February 25 - We Built a Strategic Brain for Our AI Pipeline. Here's What It Learned.
- February 25 - Your Linter Can't Trace Execution Paths. This Agent Can.
- February 25 - 5 Meta-Tools, 0 Ad-Hoc Edits: Structured Code Repair with AI Agents
- March 1 - Two Paradigms of Multi-Agent AI: Rust Parallel Agents vs Claude Code Agent Teams
- March 2 - Pixel-Perfect UI with Playwright and Figma MCP: What Actually Works in 2026
- March 3 - Claude Code Doesn't Index Your Codebase. Here's What It Does Instead.
- March 4 - Forget Elite DORA Scores. Your Platform’s Job is to Make Slow Teams Less Slow.
- March 7 - Eval Driven Development
- March 8 - The Research on LLM Self-Correction
- March 9 - The Two-Layer Model That Separates AI Teams That Ship from Those That Demo
- March 11 - From Research Papers to Production: ML Features Powering a Crypto Scalping Engine
- March 15 - LLM as Judge: What AI Engineers Get Wrong About Automated Evaluation
- March 16 - The Case Against Mandatory In-Person Work for AI Startups
- March 17 - DeepEval for Healthcare AI: Eval-Driven Compliance That Actually Catches PII Leakage Before the FDA Does
- March 18 - LlamaIndex Embeddings for Healthcare RAG: From PDF to pgvector in Production
- March 20 - CrewAI's Genuinely Unique Features: An Honest Technical Deep-Dive
- March 22 - Red Teaming LLM Applications with DeepTeam: A Production Implementation Guide
- March 23 - Synthetic Evaluation with DeepEval: A Production RAG Testing Framework
- March 23 - Multi-Modal Evaluation for AI-Generated LEGO Parts: A Production DeepEval Pipeline
- March 26 - How Novelty Drives an RL Web Crawler
- March 28 - ScrapeGraphAI Qwen3-1.7B: Fine-Tuned Web Extraction Model and 100k Dataset
- March 29 - TurboQuant: 3-Bit KV Caches with Zero Accuracy Loss
- March 31 - Fine-Tune Qwen3 with LoRA for AI Cold Email Outreach
- April 1 - Building a ZoomInfo Alternative with Qwen and MLX: Local Buyer Intent Detection
- April 7 - Multi-Probe Bayesian Spam Gating: Filtering Junk Before Spending Compute