AI

Practise AIF-C01 with 40 independently authored questions and sourced explanations, then review missed answers across five exam domains.

Study AIP-C01 with 40 independently authored generative AI scenarios, source-linked explanations and focused retries for missed answers.

Write one function definition for several LLM providers, with nested JSON Schema parameters and clear checks for strict-mode changes.

Check whether an LLM fine-tuning run fits your GPUs, with per-GPU memory estimates and batch or sequence limits for full training and adapters.

Estimate how many concurrent LLM sequences fit in GPU memory at a chosen context length, accounting for weights and tensor parallelism.

Count LLM tokens and check room for replies in your context window with exact o200k_base or cl100k_base counts calculated in your browser.

Estimate LLM training FLOPs, GPU-hours and rental budget from model size and token count using your GPU performance and price assumptions.

Check whether a local LLM fits your GPU or Mac and estimate text generation speed from its weight format and planned context length.

Estimate monthly LLM API cost from token use, caching and retries with budget checks plus same-workload model price comparisons.

Add an MCP server to your AI client's configuration while protecting existing server entries and masking private values by default.

Split text into retrieval chunks in your browser and inspect actual overlap with source offsets that keep each chunk traceable.

Compare self-hosted GPU costs with hosted API pricing for the same token workload, including capacity needs and hardware payback.

Create or check an llms.txt file with curated links and line-specific findings, using local imports that never fetch the listed pages.