learn-summit-2023-talks
Skill1 starsChanged 5 months agoMITView on GitHub
Applies AI Engineer Summit 2023 main-stage playbooks for RAG, agents, interfaces, local LLMs, fine-tuning, product velocity, TypeChat/Pydantic, LangChain observability, and the discipline of AI engineering (Swyx, Willison). Use when grounding team practice in summit talks, shipping RAG/agents, or onboarding to AI engineering; or when the user says "summit 2023 talks", "1000x AI engineer", "production RAG Jerry Liu", "open questions Willison".
In this repository51 other files it gives its agents.
- architect-enterprise-aiSkill
- author-agent-skillsSkill
- build-agent-harnessesSkill
- build-aiewf-2024-ragSkill
- build-generative-mediaSkill
- build-multimodal-productsSkill
- build-rag-search-stacksSkill
- build-robotics-aiSkill
- build-with-deepmindSkill
- build-with-microsoft-aiSkill
- build-with-openaiSkill
- deploy-public-sector-aiSkill
- design-agent-skillsSkill
- evaluate-with-braintrustSkill
- lead-ai-engineering-teamsSkill
- lead-ai-transformationSkill
- learn-summit-2023-remoteSkill
- navigate-aie-europe-2026Skill
- navigate-aiewf-2024-keynotesSkill
- observe-ai-productionSkill
- operate-agent-memorySkill
- operate-legal-ai-agentsSkill
- operate-openclaw-agentsSkill
- optimize-llm-inferenceSkill
- plan-sovereign-aiSkill
- price-ai-productsSkill
- run-aiewf-2024-evalsSkill
- run-llm-evalsSkill
- run-summit-2023-workshopsSkill
- secure-ai-agentsSkill
- ship-ai-as-pmSkill
- ship-aiewf-2024-agentsSkill
- train-llms-locallySkill
- architecture-reviewSkill
- chat-failure-auditSkill
- create-a-skillSkill
- cross-model-reviewSkill
- cto-weekly-reviewSkill
- friction-auditSkill
- ig-carouselSkill
- pdf-reportSkill
- raise-prSkill
- reel-editSkill
- research-reportSkill
- ship-checkSkill
- spec-grounded-designSkill
- state-lifetime-decisionSkill
- ste100Skill
- scroll-engineeringSkill
- ui-uxSkill
- verify-like-a-userSkill
The file
Files
Learn Summit 2023 talks
Action playbook from twenty-two AI Engineer Summit 2023 talks. Do not summarize talks — pick a workflow and execute it.
Supporting files:
- workflows.md — workflows A–N
- source-index.md — src-NNN → learnings
Optional deliverables: {SKILL_OUTPUT_DIR}/learn-summit-2023-talks/
Step 0 — Pick workflow
What is the user trying to do?
├─ Define AI engineering career / 1000x leverage → A [src-018, src-002, src-022]
├─ Production RAG + vectors + wild deployments → B [src-006, src-015, src-017]
├─ Agents + context-aware reasoning → C [src-019, src-005]
├─ Domain fine-tuning / adaptation → D [src-009]
├─ Local / private LLM deployment → E [src-010]
├─ Viral AI product / growth lessons → F [src-001, src-011, src-003]
├─ LLM system building blocks (product) → G [src-004]
├─ Interfaces & abstraction ladder → H [src-008, src-021]
├─ Type-safe LLM I/O (Pydantic / TypeChat) → I [src-014, src-013]
├─ Data platform AI pivot → J [src-020]
├─ Multimodal APIs (see/hear/speak/draw) → K [src-016]
├─ Reactive / streaming AI apps → L [src-007]
├─ Open questions & yearly retrospectives → M [src-012]
└─ Move fast without breaking prod → N [src-011]Open workflows.md for steps and deliverables.
Install
cp -r skills/learn-summit-2023-talks ~/.claude/skills/
cp -r skills/learn-summit-2023-talks ~/.cursor/skills/Source: playlists/ai-engineer-summit-2023-talks/.
Cross-cutting rules
| Rule | Source |
| AI engineering ≠ prompting; systems wrap non-AGI models | [src-018 @ 5:53] |
| Naive RAG fails in production — plan retrieval + eval | [src-006 @ 2:58] |
| Ask: impossible new builds vs faster builds (Willison) | [src-012 @ 1:01] |
| Structured outputs reduce integration risk | [src-014], [src-013] |
| Agents need product-grade interfaces, not chat-only | [src-019], [src-021] |
Output to user
- Name workflow (A–N) and artifact
- Save under
./skill-outputs/learn-summit-2023-talks/when requested
Invocation examples
@learn-summit-2023-talks production RAG checklist from Jerry Liu
framework for open questions in our AI roadmap
pydantic vs typechat for our API layerDoes it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

