ClyepClyep (pronounced “clip”) explains AI and machine learning in short videos. Every video keeps its versions, so you can see what changed and watch any earlier cut. How it works
UpdatedAgents
MCP Explained
The Model Context Protocol from first principles: why AI apps and tools need a shared standard, how to build and connect a server, and how to use MCP with agents, real APIs and remote servers.
13 episodes Updated51 min
NewAgents
Building AI Agents
Build a coding agent from scratch in plain Python, one capability per episode: the loop, tools, skills, subagents and verification, then test it on a public benchmark.
5 episodes New45 min
UpdatedRetrieval and knowledge
Learn Knowledge Graphs
Knowledge graphs from the ground up: what an ontology declares, how a system decides that two records are one thing, and when a graph beats vector search in front of an LLM.
12 episodes Updated1 hr 15 min
-
AI leadershipBuilding an AI Team: A Practical Playbook -
LLMsContinuous Batching: Dynamic Request Scheduling for LLM Inference -
AI leadershipForward Deployed Engineering: What It Is, What It Isn't, and When It Matters -
LLMsPrompt Caching Explained: Why Prefixes Matter -
LLMsDiffusion Language Models Explained: The Shift to Parallel Generation -
LLMsKV Cache and RadixAttention: How LLM Servers Avoid Redundant Computation -
LLMsMercury 2: The Fastest Reasoning Language Model -
AI toolingProduct Demo: Workflow Automation with n8n
Recently updated
New videos and new versions of existing ones.- Skills, Building AI Agents episode 5 v1 New
- Tools, Building AI Agents episode 4 v2 Updated The write tool is now explained where its code is opened. The previous version skipped it as already seen, which left the one tool the schema section used as its example never walked through. The video now also says why grep is worth its own tool when bash can already run grep: it skips cache folders and stops at fifty matches, so the model's context does not fill up. Other changes are pacing.
- The Loop, Building AI Agents episode 3 v4 Updated Pacing improvements through the walk of agent.py and the ending. The narration is unchanged.
- A Task That Outlives the Call, A2A Explained episode 12 v1 New
- One Agent, Many Agents, A2A Explained episode 10 v2 Updated Re-recorded with the closing attribution card, which the first cut left out, and with the spotlight back on scene six.
- Where A2A Meets MCP, A2A Explained episode 9 v2 Updated Re-recorded with the closing attribution card, which the first cut left out.
- Plug In Your First Server, MCP Explained episode 5 v2 Updated One line re-voiced, where the OpenAI client is built from the env file, so it reads more clearly. Nothing else changes.
- Trusting a Server Is a Decision, MCP Explained episode 11 v2 Updated Scene two's closing line now names the host's three decisions directly; the signpost to the code moves to scene three.