The map
The AI Engineering Skills Map is the spine of this deskAndrew Ng’s four skills — wrap, eval, ground, ship — are how this board is filed. If you are building an AI app, start here, not with a model card.
Latent Space5d agoEditorial
Setting type
Claude Computing
Pulling labs, repos, and the catch-up path…
Harnesses, graphs, loops, APIs you call this week — tagged with Ng’s application skills. Not a training desk. New here is the decoder. Starting a project this week? Catch up is the four-skill map — not more news.
The map
The AI Engineering Skills Map is the spine of this deskAndrew Ng’s four skills — wrap, eval, ground, ship — are how this board is filed. If you are building an AI app, start here, not with a model card.
Latent Space5d agoEditorial
Skipping permissions is the whole product question for coding agents. Read this as a security and UX harness, not a feature list.
Simon Willison2d agoLive
The craft
Harness engineering is the new self-improvement storyLilian Weng’s map of recursive improvement is not sci-fi: it is loops, evals, and the wrapper around the model. If you only watch model cards, you will miss the job.
Lilian WengJul 4Editorial
Cookbooks for building AI apps: context, harness, graphs, cloud.
Wrap
Wrap GLM-5.3-Flash this week: 1M-context API, not a lab you train atCall it through Z.ai or Baseten — long-context wrap, MIT weights as a swap. Cookbook for the endpoint, not a training drop.
Z.ai4d agoEditorial
Context
Effective context engineering for AI agentsWindow, packing, routing: what belongs in context this turn. A lab you run on the wrap, not a model-card internals note.
Anthropic EngineeringEditorial
Graph
LangGraph persistence: checkpointed loops you can resumeDurable graphs, not a chatbot demo. This is the lab for threads that survive a crash in production.
LangChainEditorial
Eval
Trace the agent loop: OpenAI observability you ship withEval in the wrap: traces and integrations for agents you already call, not a training-lab dashboard.
OpenAIEditorial
App
Next.js App Router: a streaming AI app with the AI SDKBuild the chat UI and the route handler this week. Cloud lab for shipping an application, not wiring a network.
Vercel AI SDKEditorial
Wrap
Call Bedrock Converse in your app this weekWrap the AWS API — messages, tools, streaming — inside the product. Not a VPC lab.
AWSEditorial
Cloud
Deploy a Python ADK agent to Cloud Run this weekGCP lab: Vertex/ADK as an agent app on Cloud Run. Ship the product, not a TPU blog.
Google CloudEditorial
Cloud
Hosted agent on Azure AI Foundry: quickstartFoundry lab: stand up a hosted agent as an application in Azure, not a networking diagram.
Microsoft LearnEditorial
Cloud
MCP client on Cloudflare WorkersPut the harness on the edge: Workers talking MCP. A lab you take this week, not a training run.
CloudflareEditorial
Cloud
OpenAI Agents SDK in a Modal sandboxCloud lab: run the coding-agent harness in Modal, not on a training cluster. Wrap, eval, ship.
ModalEditorial
Harness
Effective harnesses for long-running agentsLoops, tools, permissions: the wrapper you ship around the model. Take this workshop before you write another agent from a model drop.
Anthropic EngineeringEditorial
Graph
Agentic RAG with LangGraph: retrieve inside the loopGraph lab you run this week: checkpointed retrieval, not a paper on embedding-model science.
LangChainEditorial
Cloud
WorkflowAgent on Vercel: a serverless harnessCloud lab: durable agent workflows on Vercel serverless, not a model-drop ticker.
Vercel AI SDKEditorial
MCP
Code execution with MCP: tools without stuffing the windowHarness lab: let the agent write code against MCP instead of packing every tool schema into context.
Anthropic EngineeringEditorial
Harness, loops, graphs, MCP, permissions, evals as acceptance.
Harness
Managed agents: decouple the brain from the handsAnthropic’s engineering note on splitting the planner from the tools is the production version of a harness. Same idea whether you like Claude or not.
Anthropic EngineeringEditorial
Clone-to-ship: RAG, eval harnesses, agent wrappers. Not train-a-model.
Repo
run-llama/llama_indexThe default RAG data framework: ingest, index, retrieve. Grounding before you wrap an agent.
GitHub9h ago52k ★Live
Repo
deepset-ai/haystackWatchlist posts for people building AI apps. Originals, not architecture notes.
X
No /dev/kvm, so the agent shipped a GitHub ActionHarness permissions are the product: the agent shipped a CI sandbox because it lacked /dev/kvm.
Simon Willison / X10d agoLive
X
Codex locked-use locked a Mac keychain — twicebrowser-use’s Mac harness is the app on the laptop in front of you: Accessibility, a computer-use loop, tool permissions.
browser-use/macos-harnessEditorial
Paper
WikiSkill: compile agent experience into persistent skillsA harness pattern, not a training run: turn traces into a wiki the next loop can actually reuse.
arXiv 2608.274542d agoEditorial
Paper
RedEvoAgent: red-team the execution harness, not the promptProduct-shaped red teaming: agents attacking the loop you ship, not unsafe-text evals on a chatbot.
arXiv 2608.274392d agoEditorial
Paper
Persona vs execution: govern the hands, not the voicePersona-Execution Separation is the audit story for agents at work: a character in the window, a separate, logged loop that actually acts.
arXiv 2608.274272d agoEditorial
Weng’s 2023 LLM Powered Autonomous Agents post is how a generation learned planning, memory, and tools. Read it before the new jargon.
Lilian WengJun 23Editorial
If your agent cannot checkpoint, it is a demo. This is the open-source default for state, retries, and human-in-the-loop.
langchain-ai/langgraphEditorial
LangChain’s deepagents repo is what “just add an agent” looks like when someone actually ships the planning loop and the filesystem.
langchain-ai/deepagentsEditorial
Model Context Protocol is how you plug GitHub, a browser, or a database into many clients. Learn it as an interface, not a brand.
MCP Python SDKEditorial
Stanford’s DSPy treats pipelines as code with optimizers. The anti-magic stance: if you cannot eval it, you cannot improve it.
stanfordnlp/dspyEditorial
Hugging Face’s barebones library is a philosophy: first-class code-acting agents, not a 40-file framework. Steal the idea even if you don’t vendor it.
huggingface/smolagentsEditorial
Agent Development Kit is how Google wants you to build, eval, and deploy agents. Worth knowing even if you never ship on Vertex.
google/adk-pythonEditorial
Official, lightweight, and opinionated about handoffs. Read it as a reference implementation of loops, not as the only way.
openai/openai-agents-pythonEditorial
A hosted harness, not a new model. The news is that “deep agent” is becoming a product category.
LangChain3d agoLive
Anthropic’s production MCP path: admins provision connectors through the identity provider. This is how you ship tools at a customer, not a demo OAuth loop.
Anthropic6d agoEditorial
Deep dive into self-improving evaluators in LangSmith, motivated by the rise of LLM-as-a-Judge evaluators plus research on few-shot learning and aligning human preferences.
LangChain3d agoLive
Pipelines for retrieval and eval, not a chatbot skin. How you ship grounding in production.
GitHub21h ago26k ★Live
Repo
promptfoo/promptfooEval harness for prompts and agents. Red-team and regression the wrapper, not the weights.
GitHub29m ago25k ★Live
Repo
vibrantlabsai/ragasGrounding is the underweight skill on this board: get the right facts in, then wrap. Not a chatbot story.
GitHubFeb 2416k ★Live
Repo
sandbaseai/deepseek-harness-handbookAgent-first DeepSeek Harness handbook: 173 source-backed runtime, plugin, MCP, sandbox, evaluation, troubleshooting, multilingual, and 74-resource Awesome ecos… Clone-to-ship: RAG, eval, or an agent wrapper.
GitHub4m ago91 ★Live
Repo
Zleap-AI/SAGA new SOTA for RAG — an original retrieval architecture and an open-source knowledge base for humans and agents. Clone-to-ship: RAG, eval, or an agent wrapper.
GitHub14m ago2.4k ★Live
Repo
openai/codexOpenAI’s terminal coding agent. Watch it as a harness, not as a mascot.
GitHub3h ago120k ★Live
Repo
OpenHands/OpenHandsAn open coding agent with a real workspace. The other pole from a one-file CLI.
GitHub2h ago86k ★Live
Repo
letta-ai/lettaStateful agents with memory that lasts longer than a context window. Grounding that survives the next call.
GitHub6d ago24k ★Live
Repo
furkankly/zoetropeWatch a Claude Code session as a live flow graph. Read the harness, don’t guess what the agent just did.
GitHub5d ago663 ★Live
Repo
headroomlabs-ai/headroomCompress tool outputs, logs, files, and RAG chunks before they reach the LLM. Clone-to-ship: RAG, eval, or an agent wrapper.
GitHub9m ago68k ★Live
Repo
context-labs/whipA fast coding-agent harness in Go. Clone-to-ship: RAG, eval, or an agent wrapper.
GitHub6m ago184 ★Live
Coding-agent sandbox vs OS keychain: a production harness footgun.
swyx / X4d agoLive
X
Ramble into the window: voice as contextContext engineering by voice: more bits in the window without typing the spec.
Andrej Karpathy / XJul 21Live
Drew Breunig: model cost stopped papering over a weak harness. Context and routing are the job again.
Drew Breunig7d agoEditorial
Lovable’s CTO on shaping the build: ship tools, not another consumer app. MCP is the interface.
Latent Space5d agoEditorial
Simon Willison’s CLI upgraded to OpenAI Python 3.x and httpx2. The adapter you call through, not a cookbook and not a new model.
Simon Willison8d agoEditorial
Graph
Ng graph engineering: loops into working graphs (2h)Agentic knowledge graphs as app craft: first agent, how loops work, freeze them into graphs. Not a training lecture.
Anatoli Kopadze / X3d agoEditorial
Loop
Loops vs graphs: agent owns the path, or you draw the nodesLoop while the work is messy. Freeze it into a graph once the pipeline repeats. Same company brain either way.
Annatar.md / X6d agoEditorial
Loop
Karpathy: agents → loops → graphs as the app craftThe lecture is wrap/eval/ship: loops and graphs you run, not how a lab pretrains a model.
virgilxbt / X6d agoEditorial
Harness
Claude Code ELI5 skill: MCP and harness as a pageA skill that draws the wrapper: MCP runtime and harness, not a model card. Install it on a real ticket.
GoFly / X5d agoEditorial
Graph
Memory vs graphs: a pile vs a routeMemory is continuity. The graph is who may retrieve and write back. Routing, not a bigger embedding store.
Lunar / X5d agoEditorial
Graph
Ng’s agentic knowledge graphs course (1h)Persistent context for agents you ship: build the graph, then the multi-agent system. Not a grind thread.
Swati Gupta / X4d agoEditorial
Course
Hugging Face agents course: ship an agent, freesmolagents, LlamaIndex, LangGraph, then a project with evals. Catch up already files the lab; this is the pointer.
Ren / X3d agoEditorial
Harness
How to design an agent harness: work inside the system of recordAgents share data and policy with humans in one continuously updated view, with an audit trail. Harness design, not a valuation hook.
Yarchi / X3d agoEditorial
FDE
No-BS FDE guide: wrap and ship in the customer’s stackForward-deployed craft: you are in the account building the AI app. Not a salary-in-30-days thread.
Rahul / XAug 1Editorial
Stack
Vibe-code stack: Next.js, Vercel, Convex, Clerk, StripeSoftware fundamentals for shipping an AI app this week. The wrap layer, not an audience-growth thread.
Alex Finn / XAug 4Editorial
Course
Free company AI courses: Anthropic, Google, Meta, NVIDIA, Microsoft, OpenAIA Catch up pointer to vendor wrap/eval/ship courses. Not a second lab on this board.
Parag Pawar / XAug 7Editorial
FDE
12 FDE projects: enterprise deploy constraintsMulti-tenant, SSO, customer RAG with permissions, on-prem deploy. The FDE job, not a tutorial binge.
Suraj Sharma / XAug 9Editorial
Claude
Full Claude Course: practical Claude for shipping an appWrap Claude, add tools, ship a real project. Practical course, not a hustle bait.
Jobescape / XAug 11Editorial
Learn how startups use GPT-5.6 to build faster, more cost-efficient AI agents with smarter model selection and new Responses API capabilities.
OpenAIAug 13Live
X
An LLM cliché highlighter, 38 patterns inA working eval for slop, not a vibe check.
Simon Willison / X2d agoLive
X
Stop testing models with a pelican on a bicycleEvals leaving toy SVG tests: long-horizon generation with a real budget.
Andrej Karpathy / XAug 2Live
Glean CEO Arvind Jain explains why model routing helps control AI costs for organizations, and how human feedback loops at scale improve its routing systems.
Latent Space11d agoLive
The Anthropic plugin for llm now tracks SDK 1.x. Upgrade the wrap layer this week so Claude calls keep compiling.
Simon Willison6d agoEditorial
Course
Become an AI engineer: LLM apps, APIs, context, tools, deployWrap, RAG, tool-use, evals, then ship. A six-month app-builder path, not a lab-training syllabus.
Rahul / XAug 11Editorial
Preview Ultrafast, a new OpenAI API service tier that runs GPT-5.6 Sol up to 14× faster.
OpenAIAug 13Live
Models keep absorbing the harness into their weights — soon, it will be a harness for human attention rather than for the model.
Latent Space8d agoLive