Cheat sheet · Build products
Choosing an LLM and AI stack cheat sheet
Opens with creditsA quick-revision companion to the Choosing an LLM and AI stack roadmap: a decision chart for which model fits which job, the cost and context arithmetic, a dated price and context snapshot, an open-weight vs API checklist and a per-layer stack picker. Skim it before you choose, and again at every quarterly review.
Curated by Tauseef Fayyaz10 chapters75 concepts125 glossary termsChapters
10 chapters · 75 concepts
1Start from the taskDescribe the job before you look at models: its task family, its requirements and what a wrong answer costs. Then build a shortlist from leaderboards and decide with your own data.7 concepts
- 1Task familiesFive common kinds of LLM work: chat, coding, research, data analysis and workflow automation.
- 2Model requirements cardSix lines written before any testing: quality (and the cost of a wrong answer), speed, volume, context size, tools and privacy.
- 3Which model for which jobA starting point for each kind of job: which tier to test first and when to step up or down.
- 4The cheapest model that is good enoughThe model to ship is the cheapest and fastest one that clears your quality bar for this task, not the smartest one available.
- 5Model tiersProviders sell a family in sizes: a top tier (most capable, slowest), a middle workhorse and a small, cheap, fast tier.
- 6LeaderboardsPublic rankings of models.
- 7Dated snapshotsEvery table of model names, prices or context windows is a photograph of one day.
7 in this chapterOpen this chapter2Reasoning and qualityWhen thinking harder pays off: reasoning models and effort settings, why errors compound over many steps, instruction following, and the simple sum that says when a bigger model is worth it.7 concepts
- 1Reasoning modelA model that writes hidden working before its final answer.
- 2Reasoning tokensThe tokens a model spends thinking before its visible answer.
- 3Effort and thinking settingsA request setting that controls how much a model reasons: Anthropic calls it effort, OpenAI reasoning effort, Gemini a thinking setting.
- 4Compounding errorsIn a task with many steps, per-step accuracy multiplies: 95% per step over 10 steps is about 60% overall.
- 5Instruction followingHow faithfully a model obeys your format, length, language, tone and must-not rules, including many turns into a conversation.
- 6Price plus cost of errorsTotal cost per request = model price + (error rate x cost of one wrong answer).
- 7BenchmarksFixed public test sets with a published score per model, for coding, maths, knowledge and agent tasks.
7 in this chapterOpen this chapter- Speed and costPrices are per million tokens; your bill is per task. The arithmetic, the speed numbers that matter, small models and the two big discounts.8 conceptsOpens with credits
- Snapshot: prices and context, October 2026Read on 7 October 2026 from each provider's own page, in US dollars per million tokens at standard rates. Review every quarter: these numbers change often.6 conceptsOpens with credits
- Context and memoryHow much a model can read at once, what a full window costs, how to keep chat history under control, and when retrieval beats a bigger window.6 conceptsOpens with credits
- Tools and agentsWhat to check when a feature calls functions, returns JSON or runs as an agent: tool calling quality, strict output, MCP support and reliability over many steps.5 conceptsOpens with credits
- Privacy and deploymentWho sees your data, which licence you accept and which rules you follow depend on where the model runs. The terms to read, the options and a checklist to choose.10 conceptsOpens with credits
- The rest of the stackThe layers around the model, a sensible default for each and when to switch: hosting, embeddings, document and web extraction, frameworks, vector storage and observability.11 conceptsOpens with credits
- Run your own comparisonWhere the decision is made: a golden set from real data, a rubric, code checks before model judges, three models side by side and a dated decision record.6 conceptsOpens with credits
- Production choicesKeeping the choice right after launch: routing easy and hard requests, fallbacks, avoiding lock-in, pinning versions and a quarterly review.9 conceptsOpens with credits
- 11Glossary, A to ZEvery concept in the sheet and the smaller terms it uses, in one list.125 terms
About this sheet
Models, hosting and tools for your use case.
Related on Sefism
Picked from the other libraries by shared topics.
Roadmaps
See allBest practices
See all- Best Practices for AI Coding AssistantsHow to get reliable code from AI coding assistants and agents: instruction files, task prompts, verification, review, security, dependencies and session hygiene.
- Best Practices for Building LLM AppsHow to build LLM apps and agents that hold up in production: prompts, evals, prompt injection, tool permissions, cost, logging and privacy.
- Prompt Engineering Best PracticesHow to write prompts that work the same way on the hundredth input as on the first: clear instructions, structure, examples, reasoning, output control and testing.
Checklists
See all- RAG Production ChecklistA RAG production checklist: chunking, embeddings, hybrid search, reranking, per-user permissions, citations, evals, re-indexing and cost, with how to verify each check.
- LLM Evaluation ChecklistAn LLM evaluation checklist: success criteria, eval datasets, code and model graders, judge calibration, agent evals, safety tests and production monitoring, with how to verify each check.
- AI Feature Launch ChecklistAn AI feature launch checklist: use case fit, evals, UX for errors, disclosure, human override, abuse filters, rate limits, cost caps, prompt privacy, monitoring and rollback.
Project structures
See all- GenAI RAG app (FastAPI) project structureFor developers turning a "chat with your documents" demo into an app people can rely on. A FastAPI backend where every layer has a home: ingestion workers, retrieval, prompts as versioned files, model clients with fallbacks and cost caps, guards, evals that gate CI, and tracing, so a wrong answer can be traced to the step that caused it.
- AI agent with an MCP server project structureFor developers who want to give AI assistants safe access to their own data or API. A TypeScript MCP server built on the official SDK, organised by feature (tasks, projects) with each feature owning its tools, resources and prompts, served over stdio for local hosts and Streamable HTTP with OAuth for remote ones, plus a small agent and the evals that prove a model can use it.
- Machine learning project project structureFor students and analysts whose model works in a notebook and now needs to be reproducible, reviewable, served and watched. It starts from the Cookiecutter Data Science v2 layout (immutable raw data, numbered notebooks, a real Python package) and grows into versioned data with DVC, typed parameters, data validation with pandera, experiment tracking and a model registry with MLflow, a FastAPI prediction service, drift monitoring and, for a team, scheduled retraining, model cards, fairness checks and shadow deployment.
Career questions
See all- Which AI tools do employers expect junior developers to know in 2026?Employers rarely require a specific brand. They expect you to use an AI coding assistant well (in the editor and in the terminal), to review and test what it produces, to call an LLM API in a small feature, and to explain when you would not use AI. Pick one assistant, learn it properly, and show judgement in your projects.
- Is it bad that I rely on ChatGPT or Cursor and cannot write code from scratch?Using AI tools is fine and increasingly expected. Being unable to write, debug or explain code without them is a real risk, because interviews, reviews and production incidents test exactly that. Keep the tools, but rebuild the ability to think and code independently first.
- How do I use AI to become a better engineer instead of becoming dependent on it?Decide the job AI does before you open it. Use it as a tutor, reviewer and sparring partner that explains and challenges, not a vending machine that hands you finished code. Attempt first, ask second, and always be able to explain and defend what you ship.
Cheat sheets
See all- Coding with AI tools cheat sheetClaude Code, Cursor, Copilot, used well.
- Prompt Engineering cheat sheetPrompt anatomy, few-shot examples, chain of thought, structured output, long context, prompts for code and study, and testing prompts.
- AI engineering cheat sheetBuild products on LLMs and generative AI.
Work with me
Stuck on something specific?
Writing only gets you so far. If you want an answer to your situation rather than the general case, book a session and we will work through it together. Sessions are free for approved Sefism members, and a few slots open each week.
- 1:1 Mentorship
- Fresh Graduate Mentorship
- Career Guidance
Brand deals, promos and partnerships: tauseeffayyaz@gmail.com