Tools
See how the tools around the model actually move: agents, MCP, and workflow builders.
Sessions
Go in order. Each session is one idea you can drag, step and break.
01Coding agents
1 live · 4 comingTools that read and change your code.
Interactive
LiveA coding agent's loop
Watch search, edit, and a check repeat until the test passes.
Open session →
Interactive
Coming soonTerminal coding agents
Agents like Claude Code that run commands, edit files and run tests.
Interactive
Coming soonRules and context files
AGENTS.md, rules and memory files that steer an agent.
Interactive
Coming soonReviewing agent changes
Diffs, tests and sandboxes before you trust the output.
Interactive
Coming soonBackground and cloud agents
Hand off a task and get a pull request back.
02Protocols and tool servers
2 live · 2 comingStandard ways to plug tools into models.
Already live in other tracks: Call a tool, then answer
Interactive
LiveMCP: tools the model can call
A server lists tools. The app forwards the one the model picks.
Open session →
Interactive
LiveBuilding an MCP server
Expose your own data and actions to any MCP client.
Open session →
Interactive
Coming soonTurning an API into tools
Generate tool definitions from an OpenAPI spec.
Interactive
Coming soonAgent-to-agent protocols
How agents from different vendors hand work to each other.
03Workflow builders
1 live · 3 comingVisual and code-first automation.
Already live in other tracks: One item through a workflow
Interactive
LiveAn n8n workflow, node by node
Cross a threshold and see the run switch from email to Slack.
Open session →
Interactive
Coming soonZapier and Make
No-code automation, and where it runs out.
Interactive
Coming soonLangGraph
Agents as graphs of steps with saved state.
Interactive
Coming soonTemporal
Code-first durable workflows that survive crashes.
04Model APIs and SDKs
1 live · 4 comingCalling models from your code.
Interactive
Coming soonModel provider APIs
OpenAI, Anthropic and Gemini: messages, tools and streaming compared.
Interactive
Coming soonAI SDKs
Vercel AI SDK and friends: one interface over many providers.
Interactive
Coming soonLangChain and LlamaIndex
What frameworks give you, and what they hide.
Interactive
Coming soonOllama and local runtimes
Run open models on your laptop behind a local API.
Interactive
LiveModel routers
OpenRouter-style services: one key, many models, automatic fallback.
Open session →
05Data and retrieval tools
0 live · 3 comingWhere embeddings and documents live.
Already live in other tracks: Embeddings and similarity search
Interactive
Coming soonVector databases
pgvector, Pinecone, Qdrant and Weaviate compared.
Interactive
Coming soonSearch engines
Elasticsearch and OpenSearch for keyword and hybrid search.
Interactive
Coming soonDocument parsers
Getting clean text and tables out of PDFs and slides.
06LLMOps tools
0 live · 4 comingTracing, evals and prompts in production.
Already live in other tracks: Evals: is the new prompt better?
Interactive
Coming soonTracing tools
Langfuse, LangSmith and similar: see every call and its cost.
Interactive
Coming soonEval tools
promptfoo, Braintrust and friends: run test sets on every change.
Interactive
Coming soonGuardrail tools
Libraries that check inputs and outputs against rules.
Interactive
Coming soonPrompt management
Store, version and roll out prompts outside your code.
07CI tools
1 live · 1 comingAutomation around your repository.
Already live in other tracks: A CI/CD pipeline, stage by stage
Interactive
LiveGitHub Actions on every push
Follow a workflow file from the push event to the job log.
Open session →
Interactive
Coming soonAI checks in CI
Run AI review and eval suites on every pull request.
In production
Tools you can use
21 technologies across 6 live sessions. Same names in any language — pick a session to see how the idea maps to the real world.
Services, platforms, protocols and standards — not one stack.
Coding agents loop: read context, edit files, run checks — similar products share the same shape.
MCP is the wire format between an app and a tool server — any language can implement either side.
Official SDKs make writing MCP servers quick.
Webhook-driven automation with branching is a category — n8n is one open-source option.
Routers and gateways put many providers behind one API.
Event-triggered YAML pipelines are the norm across CI products; the keywords change, the model doesn't.
- GitHub ActionsPlatform
Workflows in .github/workflows, triggered by repository events.
GitHub ↗ - actions/runnerSoftware
The open-source runner; self-host it on your own machines.
GitHub ↗ - actions/cacheSoftware
Cache dependencies between runs to cut install time.
GitHub ↗ - actSoftware
Run your workflows locally in containers before pushing.
GitHub ↗
Roadmap
Coming soonA step-by-step path through the track, with sessions and practice at each stage.
- Stage 1
Coding agents
- Stage 2
MCP and protocols
- Stage 3
Workflow builders
- Stage 4
Model APIs and data tools
- Stage 5
LLMOps
Projects
Coming soonBuild something real to lock in the skill.
- Connect one MCP tool
- An n8n flow with a branch
- A GitHub Action that runs tests