llms.txt
Compare with other sites' llms.txt files →# learningto/pass
> Free, interactive interview preparation for software engineering candidates, built around Google-style coding interviews. Visual-first explanations of data structures and algorithms, runnable Python challenges with real test cases, and optional AI feedback. No paywall, no ads, no trial.
learningto/pass (https://learningto.co) is for anyone preparing for technical interviews, especially candidates who learn visually and want to go from zero to interview-ready. All learning content is free to use without an account. A free account (GitHub, Google, X, or email) is only needed to save progress across devices, view the full progress report, and use AI-powered code feedback.
## AI engineer track
New track for AI engineer interviews: what prompting and context windows, retrieval-augmented generation, agents, evaluation, fine-tuning, cost, and production reliability actually look like at production scale. A track hub lists the concept pages; each concept pairs a readable explanation with an interactive simulation (a runnable RAG pipeline where the chunk-size knob decides whether the model answers from evidence or invents it), prediction-then-reveal framing, follow-up chains that go as deep as an interviewer would, and a transfer question the reader has not seen.
- AI engineer track hub: https://learningto.co/learn/ai
- What Is RAG? Search, Then Answer: https://learningto.co/learn/ai/concepts/ai-rag-architecture
- Search First or Retrain the AI Model?: https://learningto.co/learn/ai/concepts/ai-finetune-decision
- Why an AI Chatbot Confidently Gets It Wrong: https://learningto.co/learn/ai/concepts/ai-rag-failure-modes
- RAG System Design in Production (topic page with a tunable RAG pipeline simulation): https://learningto.co/learn/rag-systems
- RAG System Design practice with graded Python challenges (hybrid retrieval rank fusion, recall@k, retrieval-mismatch detection): https://learningto.co/practice/rag-systems
- Semantic Search & Document QA (practice with graded Python challenges): https://learningto.co/practice/ai-fundamentals
- LLM Evals & Judge Calibration (topic page where you grade 10 agent traces against a human and an LLM judge): https://learningto.co/learn/evals-calibration
- What Is an AI Eval? Measuring Chatbot Quality: https://learningto.co/learn/ai/concepts/ai-eval-calibration
- LLM Evals practice with graded Python challenges (judge agreement, pass@k vs pass^k, eval-set contamination): https://learningto.co/practice/evals-calibration
- AI Agents: Loops, Tools, and Stopping (topic page where you watch agent runs tick up cost and decide when to hit emergency stop): https://learningto.co/learn/agents-behavior
- When Should an AI Agent Stop Working?: https://learningto.co/learn/ai/concepts/ai-agent-verification
- AI Agents practice with graded Python challenges (loop detection, tool-error triage, horizon cost budgets): https://learningto.co/practice/agents-behavior
- Inference Economics & Latency (topic page with a cache/latency/cost budget you tune live against an SLO and a monthly ceiling): https://learningto.co/learn/inference-economics
- What Your AI Messages Cost, and Why They Wait: https://learningto.co/learn/ai/concepts/ai-inference-economics
- Inference Economics practice with graded Python challenges (cache hit rate, latency budget split, truncation cost): https://learningto.co/practice/inference-economics
- Guardrails & Prompt Injection (topic page where you place guards on a pipeline's trust boundaries and run injection payloads through your configuration): https://learningto.co/learn/guardrails-injection
- Prompt Injection: When Fetched Text Lies: https://learningto.co/learn/ai/concepts/ai-guardrails-injection
- Guardrails & Prompt Injection practice with graded Python challenges (trust-boundary classification, instruction tripwire, tool-argument validation): https://learningto.co/practice/guardrails-injection
- Prompting & Context Windows (topic page where you rerun the same 8 support questions under three prompts and watch parse rates, verdicts and token cost change): https://learningto.co/learn/prompting-context
- What Is a Prompt? Words In, Answers Out: https://learningto.co/learn/ai/concepts/ai-prompting-context
- Prompting & Context Windows practice with graded Python challenges (prompt swap audit, context window packing, few-shot format consistency): https://learningto.co/practice/prompting-context
- Fine-Tuning: When, and Why (topic page where you price the prompt, retrieval and fine-tune paths for four support-desk scenarios and commit your route): https://learningto.co/learn/finetuning-decision
- Fine-Tuning: What Changes When a Model Learns: https://learningto.co/learn/ai/concepts/ai-finetuning
- Fine-Tuning practice with graded Python challenges (route the request, adapter cost estimate, training data audit): https://learningto.co/practice/finetuning-decision
- Serving AI Reliably (topic page where you triage four production alerts, name the cause, and choose the action before the scorecard counts it): https://learningto.co/learn/ai-observability
- When an AI Feature Breaks in Production: https://learningto.co/learn/ai/concepts/ai-serving-reliability
- Serving AI Reliably practice with graded Python challenges (incident triage order, p95 rollback math, fallback chain planner): https://learningto.co/practice/ai-observability
## How the app works
Each topic has two pages:
- Learn (https://learningto.co/learn/{topic}): visual, step-by-step explanations of the concept from first principles, with diagrams and worked examples.
- Practice (https://learningto.co/practice/{topic}): coding challenges solved in Python. Code runs in the browser with real test cases, so learners get instant pass/fail feedback. Static hints are free; AI-generated hints and AI code review (rating, complexity analysis, suggestions) require a free account.
Other pages:
- Learning Path (https://learningto.co/path): a skill tree that suggests what to study next based on progress. It has a SWE tree and, on the same page, an AI engineering tree covering the nine AI topics and their prerequisites.
- Playground (https://learningto.co/playground): interactive data structure visualizations for exploring behavior.
- Progress (https://learningto.co/progress): readiness score, per-topic mastery, and challenge history. Requires a free account.
Progress is scored as an "interview readiness" percentage. Solving challenges raises mastery per topic; 80% overall readiness is treated as interview-ready.
## Topics
- [Arrays & Strings](https://learningto.co/learn/arrays-strings)
- [Linked Lists](https://learningto.co/learn/linked-lists)
- [Stacks & Queues](https://learningto.co/learn/stacks-queues)
- [Hash Tables](https://learningto.co/learn/hash-tables)
- [Binary Trees](https://learningto.co/learn/binary-trees)
- [Graphs](https://learningto.co/learn/graphs)
- [Heaps / Priority Queues](https://learningto.co/learn/heaps)
- [Tries](https://learningto.co/learn/tries)
- [Sorting](https://learningto.co/learn/sorting)
- [Binary Search](https://learningto.co/learn/binary-search)
- [Recursion & Backtracking](https://learningto.co/learn/recursion-backtracking)
- [Dynamic Programming](https://learningto.co/learn/dynamic-programming)
- [BFS & DFS](https://learningto.co/learn/bfs-dfs)
- [Greedy Algorithms](https://learningto.co/learn/greedy)
- [Big-O Notation](https://learningto.co/learn/big-o-notation)
- [System Design Basics](https://learningto.co/learn/system-design-basics)
Each topic's practice page follows the same URL pattern: https://learningto.co/practice/{topic-id}
## Key facts
- Everything is free. There is no paid tier, no trial, and no credit card.
- Accounts are optional and exist only for progress sync and AI feedback. Supported sign-in methods: GitHub, Google, X, and email with password.
- Python code runs entirely in the user's browser via WebAssembly (Pyodide). No code is uploaded or executed on a server.
- The interface is designed for desktop and laptop screens; mobile visitors can browse but the code editor works best on a larger screen.
- The site is a single-page application at https://learningto.co with a sitemap at https://learningto.co/sitemap.xml
## Visual concept index
Plain-English, visual explanations of the math behind each algorithm concept. Free, no signup, each has an interactive demo.
- Math for Coding Interviews (hub): https://learningto.co/learn/visual
- Big-O notation: https://learningto.co/learn/visual/big-o-definition
- O(n) linear time: https://learningto.co/learn/visual/linear-complexity
- O(1) constant time: https://learningto.co/learn/visual/constant-complexity
- Logarithms: https://learningto.co/learn/visual/logarithm-halving
- O(n log n): https://learningto.co/learn/visual/nlogn-complexity
- Exponential time 2^n: https://learningto.co/learn/visual/exponential-growth
- Quadratic time O(n squared): https://learningto.co/learn/visual/quadratic-growth
- Summation 1 through n: https://learningto.co/learn/visual/summation-series
- Modulo, the remainder: https://learningto.co/learn/visual/modular-arithmetic
- Orders of magnitude: https://learningto.co/learn/visual/order-of-magnitude
- Probability basics: https://learningto.co/learn/visual/probability-basics
- Recursion call stack: https://learningto.co/learn/visual/recursion-call-stack
- Decision trees and backtracking: https://learningto.co/learn/visual/decision-tree
- Memoization: https://learningto.co/learn/visual/memoization-math
- DP tables: https://learningto.co/learn/visual/dp-table-filling
- BFS vs DFS (queue vs stack): https://learningto.co/learn/visual/queue-vs-stack-traversal
- Greedy local vs global optimum: https://learningto.co/learn/visual/local-vs-global-optimum
- Binary search sorted invariant: https://learningto.co/learn/visual/sorted-invariant
- Array index arithmetic: https://learningto.co/learn/visual/index-arithmetic
- Linked list pointers: https://learningto.co/learn/visual/pointer-following
- Stacks and queues (LIFO and FIFO): https://learningto.co/learn/visual/lifo-fifo-ordering
- Hash functions: https://learningto.co/learn/visual/hash-function-concept
- Binary tree height: https://learningto.co/learn/visual/tree-levels
- Graph theory basics: https://learningto.co/learn/visual/graph-theory-basics
- Graph complexity O(V+E): https://learningto.co/learn/visual/graph-representation-math
- Heap array indexing: https://learningto.co/learn/visual/heap-array-indexing
- Tries as paths through a tree: https://learningto.co/learn/visual/string-as-path