Read. Try. Keep what helps.
Find a clear explanation, a reusable template or a tool to help you move forward. Our current collection focuses on practical AI, career skills and learning at work.
The reading shelf
57–64 of 108 guides
For developers2 minDevelopers and security engineers
Understand direct and indirect prompt injection, why it's hard to fully prevent, and layered defences for real applications.
Read guide
For developers2 minDevelopers
What makes an LLM application an agent, how tool calling works, and the guardrails agents need before they touch real systems.
Read guide
For developers2 minDevelopers
Techniques for dependable structured output: schemas, provider features, validation, retries, and graceful failure.
Read guide
For developers2 minSoftware developers
How to get useful code from AI assistants — context, small steps, tests, and review — without shipping bugs or security holes.
Read guide
For developers2 minDevelopers and engineering leads
Practical levers — model choice, prompt size, caching, batching, and routing — to control LLM spend, measured against your evaluation set.
Read guide
For developers2 minBeginners heading into AI
A focused Python learning path for people heading into data or AI work — core language, data libraries, APIs — without drowning in theory.
Read guide
For developers2 minEngineering teams
A pre-launch checklist covering evaluation, safety, privacy, observability, cost, and fallbacks for LLM-powered features.
Read guide
For developers2 minDevelopers and product teams
A decision guide for when to improve prompts, add retrieval, or fine-tune a model — based on the problem you're actually solving.
Read guide
A plain-text task, context, format and constraints template, with a practice example and an answer checklist.
Learning files published for each webinar. Share feedback or skip it to get the kit.
Explore your next step, prepare your application and practise for interviews. Each tool explains its current capabilities.
