AI for software engineers
Big AI ideas,
explained in two minutes.
Short, clear explainers on how modern AI works, written by a software engineer for software engineers. Every topic comes with a 2-minute video and a page you can read, save and share.
Latest videoKnowledge cutoff: why AI models don't know what happened yesterday
- 99explainers
- 16/90MCP episodes
- 4new videos a day
LatestKnowledge cutoff: why AI models don't know what happened yesterday
All topics
Knowledge cutoff: why AI models don't know what happened yesterday
What an LLM's knowledge cutoff is, why the real cutoff often differs from the reported one, and how developers give a model the present.
MCP A to Z · Ep 16MCP errors: protocol errors vs tool errors (isError)
In the 2026-07-28 MCP spec, a tool call can fail in two ways. Here's the difference between protocol errors and tool execution errors, and which one the model should see.
AI ExplainedRetries and idempotency for agent tool calls
How to let an AI agent retry a failed tool call without booking, charging or emailing twice, using idempotent operations and idempotency keys.
AI ExplainedSelf-consistency: ask an LLM many times, then take the vote
How self-consistency sampling works, why voting over several reasoning paths makes a model more accurate, what it costs, and how to use it in your own app.
AI ExplainedContinuous batching: how LLM servers keep the GPU full
Why static batching wastes GPU time on LLM inference, how iteration-level scheduling fixes it, and how chunked prefill and memory management fit in.
MCP A to Z · Ep 15MCP capabilities: how both sides say what they support
In the 2026-07-28 MCP spec, clients declare capabilities on every request and servers declare theirs in server/discover. Here are the fields, the rules and the new extensions map.
AI ExplainedSycophancy in LLMs: when AI tells you what you want to hear
Why AI assistants agree with users even when they're wrong, what the research and OpenAI's GPT-4o rollback showed, and how to test your own app for it.
AI ExplainedFlashAttention: faster attention, same answer
Why attention is limited by memory traffic on GPUs, how FlashAttention's tiling keeps the work in fast on-chip memory, and what FlashAttention-2 and -3 added.
MCP A to Z · Ep 14MCP server/discover: learning what a server can do
In the 2026-07-28 MCP spec, server/discover returns a server's supported versions, capabilities and identity in one request. Here's what it returns and when to call it.
AI ExplainedQuery rewriting and HyDE: better questions, better retrieval
Why user questions often miss the right documents in RAG, how Rewrite-Retrieve-Read and step-back prompting reshape the query, and how HyDE searches with a fake answer.
AI ExplainedRetrieval metrics: recall@k, MRR and nDCG for RAG
How to measure whether your RAG retrieval finds the right documents, with precision and recall at k, mean reciprocal rank and nDCG, plus a worked example.
AI ExplainedLogprobs: how sure was your LLM about that answer?
What token log probabilities are, how to turn them into percentages, how to request them, and four practical ways developers use them.
AI ExplainedMatryoshka embeddings: one vector, many sizes
How Matryoshka Representation Learning trains embeddings you can cut short, what OpenAI and Hugging Face measured, and how to truncate them safely.
MCP A to Z · Ep 13MCP _meta: what every MCP request carries in 2026-07-28
In stateless MCP, every request carries its protocol version, client capabilities and client info in _meta. Here are the keys, the errors and the rules.
AI ExplainedPositional encoding (RoPE): how Transformers know word order
Why Transformers need positional encoding, how the original sine waves worked, how RoPE rotates queries and keys, and how models stretch past their trained length.
AI ExplainedRate limits and token budgets: why your LLM app gets a 429
How LLM API rate limits work (requests, input and output tokens, token buckets, spend caps) and how to stay under them with retries, backoff and budgets.
AI ExplainedSlopsquatting: when AI invents a package and attackers claim it
How attackers register the package names AI coding tools hallucinate, what the research found, and the checks that keep you safe.
MCP A to Z · Ep 12Stateless MCP: what changed in the 2026-07-28 spec
The 2026-07-28 MCP revision makes every request self-contained. Here's what went away (sessions, callbacks, resumability) and what replaced it.
AI ExplainedTool search for large tool sets: give agents thousands of tools
Why loading every tool definition hurts agents, and how tool search with defer_loading lets a model discover only the tools a task needs.
AI ExplainedAgentic browsers: when your browser clicks and buys for you
How AI browsers with agent modes work, why indirect prompt injection makes them risky, and how users and builders can limit the damage.
AI ExplainedFill-in-the-middle: how code autocomplete sees both sides
How fill-in-the-middle (FIM) training lets code models use the code above and below your cursor, from the 2022 paper to Code Llama, StarCoder2 and Ollama's suffix.
MCP A to Z · Ep 11MCP's old initialize handshake, and why it was retired
How legacy MCP connections opened with initialize, negotiated a version and capabilities, and what the stateless 2026-07-28 revision does instead.
AI ExplainedPrompt versioning: ship prompts like code
Track every prompt change as a version, ship it by moving a production label, roll back in seconds, and compare versions in traces and evals.
AI ExplainedLLM API gateways: one door to every model
What an LLM gateway between your apps and model providers gives you: one endpoint, virtual keys and budgets, cost tracking, retries, fallbacks and caching.
MCP A to Z · Ep 10MCP Inspector: watch your MCP server's protocol live
How to run the MCP Inspector against a local or remote server, call tools from a form, read the JSON-RPC transcript, and switch between legacy and modern protocol eras.
AI ExplainedPII redaction for LLM apps: mask it in, restore it out
Keep names, emails and card numbers out of your prompts. Detect personal data, swap it for placeholders, keep the mapping, and restore the real values in the answer.
AI ExplainedSWE-bench explained: how coding agents get graded
What a SWE-bench score really measures, why SWE-bench Verified exists, and why contamination led to SWE-Bench Pro. How to read a coding benchmark score.
MCP A to Z · Ep 09Add your first MCP server to Claude, Claude Code, Cursor or VS Code
The one config shape every MCP client shares, and exactly where it goes in Claude Desktop, Claude Code, Cursor and VS Code, with the one key name that differs.
AI ExplainedLong context vs RAG: paste it all, or retrieve it?
Million-token context windows can hold thousands of pages. When to paste everything into the prompt, when to retrieve only what matches, and how to combine both.
AI ExplainedText-to-SQL: ask your database in plain English
Text-to-SQL lets an LLM turn a plain-English question into a SQL query. How it works, what the BIRD and Spider benchmarks show, and how to run it safely.
AI ExplainedTop-p vs top-k sampling: what the knobs actually cut
Top-k, top-p (nucleus) and min-p sampling all cut the long tail of unlikely tokens. How each one decides where to cut, and why a fixed k fits badly.
AI ExplainedAI code review: a model on your pull requests
AI code review tools read your diff and comment on the changed lines. What they catch, how Copilot and Claude fit in, what Google measured, and why a person still decides.
AI ExplainedHybrid search: BM25 plus vectors, merged with RRF
Vector search understands meaning but misses exact strings; BM25 does the opposite. Hybrid search runs both and merges them with Reciprocal Rank Fusion.
AI ExplainedSynthetic data: training AI on data a model wrote
Synthetic data is training and test data generated by a model. How Self-Instruct, Alpaca and phi-1 used it, and why model collapse means you still need real data.
MCP A to Z · Ep 08Who runs MCP? Governance, SEPs and the deprecation policy
MCP lives at the Agentic AI Foundation. How its maintainers decide, how a SEP moves from draft to final, and how long deprecated features stay in the spec.
AI ExplainedBatch APIs: cut your LLM bill in half by waiting
Batch APIs run LLM requests in the background at 50% of the normal price. How they work, their limits, and which jobs to move to a batch.
AI ExplainedDiffusion models: how AI turns static into a picture
Diffusion models learn to remove noise, then generate images by starting from pure static and denoising step by step. How training, sampling and guidance work.
AI ExplainedSemantic caching: same meaning, same answer
Users ask the same question a hundred ways. Semantic caching matches questions by meaning, returns the saved answer, and skips the LLM call. How to tune it safely.
MCP A to Z · Ep 07stdio vs Streamable HTTP: the two MCP transports
MCP messages travel over stdio for local servers or Streamable HTTP for remote ones. How each works in the 2026-07-28 spec, and the rules to get right.
MCP A to Z · Ep 06How MCP is versioned
MCP versions aren't 1.0 or 2.0, they're dates. What each version from 2024-11-05 to 2026-07-28 changed, and how clients and servers agree on one. Episode 6.
AI ExplainedRLHF: reinforcement learning from human feedback
A small model beat one a hundred times bigger, thanks to human feedback. How RLHF works step by step, why it can cause sycophancy, and newer methods like DPO.
AI ExplainedSpeculative decoding: faster LLMs, same output
A small model can make a big one faster with exactly the same output. How speculative decoding drafts tokens and verifies them in one pass, and when it helps.
AI ExplainedThe KV cache: why the first token is slow
Why is the first token slow but the rest stream out fast? The KV cache. How prefill and decode work, how much memory the cache uses, and how PagedAttention helps.
MCP A to Z · Ep 05JSON-RPC 2.0 in MCP
Every MCP message is plain JSON-RPC 2.0. Requests, responses and notifications, ids, error codes and resultType, explained. Episode 5 of MCP from A to Z.
AI ExplainedRAG chunking strategies
Your RAG app has the answer but keeps retrieving the wrong paragraph. Often the problem is chunking. Fixed-size, recursive, semantic and contextual chunking compared.
AI ExplainedRerankers: put the best result first
Your search found the right document but ranked it ninth. Rerankers read the query and each document together to reorder results. Bi-encoders vs cross-encoders explained.
AI ExplainedVoice agents: AI you talk to
Two seconds of silence and a voice bot already feels broken. How voice agents work: chained vs speech-to-speech, turn detection, barge-in and latency.
AI ExplainedAgent sandboxing and permissions
Your coding agent ran a command you never read. What stopped it from wiping your home folder? Permissions decide what it may do; a sandbox limits what it can do.
AI ExplainedBackground coding agents
Assign a ticket before lunch, and a pull request is waiting when you're back. How background coding agents work in cloud sandboxes, and how to use them well.
AI ExplainedC2PA and AI watermarks
Is this photo real, or did AI make it? Content credentials record where a file came from; watermarks hide a signal inside it. How C2PA and SynthID work, and their limits.
MCP A to Z · Ep 04From tool calls to MCP: what the protocol adds
Your LLM can already call functions. So why does MCP exist? What MCP adds on top of plain tool calls: discovery, schemas, change notifications and auth. Episode 4.
MCP A to Z · Ep 03MCP tools vs resources vs prompts
Every MCP server offers the same three primitives: tools, resources and prompts. What matters is who decides to use each one. Episode 3 of MCP from A to Z.
AI ExplainedSpec-driven development with AI agents
You ask an agent for a feature and it builds something else. Spec-driven development writes the spec first, then lets agents turn it into code. Spec Kit and Kiro explained.
AI ExplainedStreaming LLM responses
Your AI app goes silent for 20 seconds, then dumps a wall of text. Streaming sends the answer piece by piece. How server-sent events work, and the gotchas.
AI ExplainedVibe coding vs agentic engineering
Two developers ship the same app with AI. One can explain every line, the other can't. The difference between vibe coding and agentic engineering, and when to use each.
AI ExplainedGraphRAG: RAG with a knowledge graph
Ask a normal RAG app for the main themes in your data and it misses the big picture. GraphRAG builds a knowledge graph and community summaries first. How it works.
MCP A to Z · Ep 02MCP host vs client vs server
Everyone says MCP client and server, but there's a third role in charge: the host. Who does what in MCP, and why servers can't see your whole conversation. Episode 2.
AI ExplainedModel routing: the right model for each request
Your app sends every question to the biggest, priciest model, even "what's 2+2?". Model routing sends easy requests to small models and hard ones to strong models.
AI ExplainedVector databases: search by meaning, fast
A million documents, one question. Vector databases find the nearest embeddings fast with approximate search like HNSW and IVF. How they work, and when you need one.
AI ExplainedOpen-weight vs open-source AI models
Lots of AI models are called open, but most aren't open source. What open weights give you, what the OSI's Open Source AI Definition requires, and how to check.
AI ExplainedPrompt caching: pay less for repeated prompts
Your agent resends the same long prompt every turn, and you pay for it every time. Prompt caching reuses the identical start of the prompt at a fraction of the price.
AI ExplainedStructured outputs: guaranteed JSON from LLMs
You asked for JSON and got JSON plus a friendly sentence that broke your parser. Structured outputs use constrained decoding so the answer always matches your schema.
MCP A to Z · Ep 01What problem does MCP solve? The N×M problem
Three AI apps and four tools need twelve custom integrations. MCP turns N×M connectors into N+M. Episode 1 of MCP from A to Z.
AI ExplainedMCP vs UTCP: two ways to give agents tools
MCP wraps your tool in a server. UTCP describes your existing API in a JSON manual so agents call it directly. The differences, and when to pick each.
AI ExplainedMultimodal models: AI that sees and hears
Send an AI a photo of your fridge and it suggests dinner. How multimodal models turn images and audio into tokens, from ViT and CLIP to LLaVA.
AI ExplainedSmall language models (SLMs)
Bigger isn't always better. Small language models with a few billion parameters are catching up, and they're cheaper, faster and can run on your phone.
AI ExplainedDistillation: big teacher, small student
How do you fit a big model's smarts into your phone? Distillation trains a small student model to copy a big teacher. How it works, and its limits.
AI ExplainedFine-tuning vs RAG: which one do you need?
Your AI doesn't know your company's docs. Fine-tune it, or use RAG? Short answer: RAG for knowledge, fine-tuning for behavior. Here's what the research says.
AI ExplainedLoRA: cheap fine-tuning for big models
Fine-tuning a giant model sounds expensive. LoRA freezes the original weights and trains two small matrices instead. How it works, and why adapters are so handy.
AI ExplainedQuantization: running big models on small hardware
A 70B model needs about 140 GB of memory. Quantization stores each weight in fewer bits so it fits on one GPU or a laptop, usually with little quality loss.
AI ExplainedAgent tracing: see every step your agent takes
Your agent gave a wrong answer. Which step went wrong? Tracing records every model call and tool call as spans in a tree, so you can debug speed, cost and mistakes.
AI ExplainedMixture of Experts (MoE)
DeepSeek V3 has 671 billion parameters, but each token uses only 37 billion. How Mixture of Experts models route tokens to a few experts, and the trade-offs.
AI ExplainedTemperature, top-p and top-k
Same prompt, same model, different answer every time. Why? Temperature. How sampling works, what top-p and top-k do, and why Claude's newest API dropped them.
AI ExplainedTransformers and attention, explained
ChatGPT, Claude and Gemini all share one idea from 2017: the transformer. How attention works, what queries, keys and values do, and why long prompts cost more.
AI ExplainedAGENTS.md and CLAUDE.md
Your coding agent keeps running the wrong test command because nobody told it the right one. AGENTS.md is a README for agents. Here's what to put in it.
AI ExplainedLLM evals: tests for AI apps
You changed one line in your prompt. Is your AI app better or worse? Without evals you're guessing. How to build tasks, trials and graders that tell you.
AI ExplainedLLM guardrails: checks around your AI app
Your support bot promised a customer a full refund. Who let it? Guardrails are checks on input, output and tool calls that catch problems before they cause damage.
AI ExplainedLLM-as-a-judge
Your chatbot wrote 10,000 answers today. Who grades them? Another model. How LLM-as-a-judge works, its biases, and how to check the grader.
AI ExplainedAgent memory: how AI agents remember
You told your agent your name yesterday, and today it asks again. How short-term and long-term agent memory work, and how to build memory safely.
AI ExplainedAgent-ready websites with llms.txt
Can AI agents actually understand your website? llms.txt is one markdown file that tells them what's worth reading. Here's the format and how to add it.
AI ExplainedComputer-use agents: AI that uses your screen
What if AI could use a computer like you do? Computer-use agents look at the screen, then click and type. How they work, where they fail, and how to run them safely.
AI ExplainedContext engineering for AI agents
Your agent got worse the longer it worked? It's usually the context, not the model. How to choose what goes into the window on every step.
AI ExplainedPrompt injection: how AI agents get hijacked
Your AI agent reads a web page and gets hijacked. What prompt injection is, why models fall for it, and the defenses that limit the damage.
AI ExplainedAI hallucinations: why models make things up
Why does AI sometimes state false things with total confidence? What hallucinations are, why training rewards guessing, and practical ways to cut them down.
AI ExplainedEmbeddings: meaning you can measure
How does AI know "dog" and "puppy" mean almost the same thing? Embeddings turn text into vectors, so similar meanings land close together.
AI ExplainedReasoning models: AI that thinks before it answers
Some AI models stop and think before answering. How reasoning models work, what thinking tokens cost, how to set the effort, and when to use them.
AI ExplainedContext window: the model's working memory
Why does a long AI chat forget the beginning? Meet the context window: everything a model can see at once, measured in tokens, and why bigger isn't always better.
AI ExplainedDon't store JWTs in localStorage
Any script on your page can read localStorage, so one XSS bug can steal your users' tokens. Store auth tokens in HttpOnly, Secure, SameSite cookies instead.
AI ExplainedHuman-in-the-loop for AI agents
Would you let an AI agent refund customers on its own? Human-in-the-loop pauses the agent before risky actions so a person can approve, edit or reject.
AI ExplainedTokens: how AI actually reads text
AI models don't read words, they read tokens. What a token is, why 100 tokens is about 75 words, and how tokens set both your bill and your limits.
AI ExplainedFunction calling: how AI uses tools
Language models only write text. Function calling lets them ask your code to run a tool, like a weather API, and answer with real data.
AI ExplainedMulti-agent systems
When one AI agent gets overloaded, give it a team. How a lead agent splits work across specialist subagents, and what it costs in tokens.
AI ExplainedAI agent vs chatbot
A chatbot answers. An agent acts: it plans, uses tools and checks each result until the job is done. Here's the difference, and when you need each.
AI ExplainedLocal AI: run a model on your own laptop
Your laptop can run its own AI model, fully offline. How local AI works, why 4-bit quantization makes it fit, and where cloud models still win.
AI ExplainedA2A: the Agent2Agent protocol
MCP connects an agent to tools. A2A connects agents to each other, so agents built by different teams and vendors can find each other and share work.
AI ExplainedAgent Skills and SKILL.md
Agent Skills are folders of instructions, scripts and resources that an AI agent loads only when a task needs them. Here's how SKILL.md and progressive loading work.
AI ExplainedAX: agent experience
We design for user experience and developer experience. AX, agent experience, is designing products that AI agents can use well. Here's what that means in practice.
AI ExplainedMCP: the Model Context Protocol
MCP is an open standard that connects AI apps to tools and data. Build a connector once, and any MCP-compatible AI app can use it. Here's how it works.
AI ExplainedRAG: retrieval-augmented generation
Models only know what they were trained on. RAG looks up the right facts from your own documents first, then has the model answer from them.
No topic matches that yet. Got an idea for one? Tell me in the comments.