WholeTech Picks|WholeTechFable GuideTexas Coworking
The Toolbox · Working references

Tools for going past the chat box

Official model documentation, prompt-engineering reading, and the open-source tooling that turns one-off prompts into repeatable workflows. For the annotated reading list on prompting itself, see the Source Shelf.

Drawer 1 of 3

Official model documentation

Each vendor's primary reference — the place to check capabilities, limits, and prompting recommendations straight from the maker.

Anthropic docs

docs.anthropic.com

API reference and prompting documentation for the reasoning-focused model family.

OpenAI API docs

platform.openai.com/docs

API reference, guides, and the prompt engineering section for GPT-class models.

Google AI / Gemini docs

ai.google.dev

Developer docs for Gemini — the model behind our ask box — including multimodal prompting.

xAI Grok docs

docs.x.ai

API documentation for the Grok model family.

Mistral docs

docs.mistral.ai

Documentation for Mistral's hosted and open-weight models.

Perplexity API docs

docs.perplexity.ai

Docs for the web-grounded, citation-first Sonar models.

Cohere docs

docs.cohere.com

Enterprise-oriented documentation: RAG, structured outputs, and grounding.

drawer 2
Drawer 2 of 3

Prompt engineering reading

The shortest reliable reading list. The full annotated version lives on the Source Shelf.

Prompt Engineering Guide (DAIR.AI)

promptingguide.ai

Community-maintained technique reference, tied back to the research.

Learn Prompting

learnprompting.org

Free, structured open course from basics to advanced techniques.

Anthropic prompt engineering guide

docs.anthropic.com

The vendor's prompting playbook — roles, examples, chain-of-thought.

OpenAI prompt engineering guide

platform.openai.com/docs

Six strategies with worked examples for GPT-class models.

drawer 3
Drawer 3 of 3

Open source & tools

When a prompt becomes a workflow, these are the workbenches.

Hugging Face

huggingface.co

The open model hub — models, datasets, and spaces.

OpenAI Evals

github.com/openai/evals

Framework for evaluating model (and prompt) performance systematically.

PromptFoo

github.com/promptfoo/promptfoo

Test harness for prompts: compare variants across models before you ship one.

LangChain

langchain.com

Framework for building LLM applications — chains, agents, retrieval.

Filing note

The Ask 'em AI way

Start at the desk with a real question, learn the patterns in the prompt guide, and reach for these tools when a prompt you keep retyping deserves to become a workflow.

Vetted & shelved

Catalog
Live