Articles by Grizzly Peak Software

Groq API free tier limits in 2026: exact RPM, RPD, TPM, and TPD for every model including Llama 3.3, Llama 4 Scout, and Whisper.

Two malicious LiteLLM versions hit PyPI for a few hours. They tried to steal your API keys. Here's what happened and what to do about it.

I tested Skywork's agentic AI workspace. It one-shotted an SEO audit of my site. Here's the honest review and what engineers should know.

Most "agentic AI" content is hand-wavy architecture diagrams. This covers the agent loop, tool design, memory patterns, and MCP with working code.

Skip the PhD. A working developer's roadmap to AI in 2026: LLMs, agents, MCP, RAG, and the projects that actually build real skills.

Contentful's free tier ran out. I migrated 200 articles to self-hosted PostgreSQL in two hours with Claude Code. Here's the full playbook.

My AI publishing pipeline got a book flagged on Amazon. Here's how I added content risk assessment and why every agentic workflow needs quality gates.

OpenClaw has 247K stars. Its creator started with a simple agent loop. You should too. Build the fundamentals before adopting the framework.

Rome's road network, provincial governance, and currency debasement mirror the same failures we build into software. The parallels are uncomfortable.

Five senior engineers, zero decisions. Here's why elite teams stall and four frameworks that actually break the deadlock.

Your AI writes fast. It also writes JWT bugs, hardcoded secrets, and SQL injection. Here's what the scanners actually found.

Five products, no employees, under $1K/month. Here's the exact stack, AI tooling, and philosophy behind running it all solo.

AI delivery pipelines need governance for accountability and compliance. Add traceability, approval gates, and audit trails without crushing velocity.

80+ books, 70 audiobooks, one AI-assisted pipeline. Here's why the "AI content is slop" argument confuses the tool with the operator.

Five-layer guardrail architecture for AI document extraction pipelines that fabricate data instead of failing visibly.

After 40+ years in software, here are the engineering skills AI has devalued and the ones worth doubling down on right now.

REST APIs weren't built for AI agents. MCP servers are the semantic layer that lets AI discover and invoke your tools. Here's why adoption is inevitable.

Build a local-first MCP documentation server so your AI coding assistant actually knows your codebase, APIs, and team conventions.

I built an AI chatbot that diagnoses car problems and generates repair content. Here's what I learned about trust, accuracy, and domain-specific AI.

Six months of tracked hours and output reveal where AI tooling actually boosts solo developer productivity and where it quietly costs you time.