WWDC26: Run local agentic AI on the Mac using MLX | Apple

You are helping me turn one specific YouTube video into real, durable learning.

Source video:
- Title: WWDC26: Run local agentic AI on the Mac using MLX | Apple
- URL: https://www.youtube.com/watch?v=wykPErJ8M-8
- Topic: Agent Architecture
- My current learning frame: Install MLX LM, serve a small tool-calling model on localhost, connect Open Code or Xcode's locally hosted provider (port 8080) to it, and have the agent build then iteratively fix a tiny SwiftUI app entirely offline.
- Why this matters: New playlist item from Apple Developer; queued for transcript-backed review, topic mapping, and a practical learning artifact.

Transcript anchors from this exact video:
- 0:23 / Evidence 1: "from research prototypes to everyday productivity tools. But before we talk about agents, let's look at what we had before. Here's a chat experience you're familiar with. You send a prompt to the language model, the model sends..."
- 2:34 / Evidence 2: "demos, including building a SwiftUI app from scratch and fixing a bug in Xcode. Let's start with the stack. The stack that powers local agentic AI on the Mac has four layers. Let me walk you through each..."
- 5:43 / Evidence 3: "out of your hardware and addresses the key challenges of running agents locally. The first challenge is prompt processing. In an agentic workflow, every time the model receives tool output, it has to process all that new context..."
- 7:33 / Evidence 4: "join a batch in progress without waiting for the current one to finish. The result is that your sub-agents don't stall waiting in a queue. They all get served concurrently, which keeps the entire agentic workflow moving. Finally,..."
- 9:51 / Evidence 5: "to writing the code. Using an agent means we don't need to copy anything or even build the project. The agent writes the file, then builds the app fixing any errors it encounters along the way. And here..."
- 12:29 / Evidence 6: "Finally, it writes a fix, and we can now build and run our app. This shows how a locally running agent can integrate with your existing development workflow in Xcode, reading project files, understanding build errors, and making..."

Video-aware target:
- Prompt lane: Local model/runtime
- Mechanism to extract: Identify why the local setup works or fails for this specific agent task, not whether local models are generally good.
- Artifact to produce: A local model/runtime fit sheet with hardware constraints, model choice, endpoint setup, task benchmark, and fallback rule.
- Artifact must include: hardware; runtime; model/quantization; endpoint; agent integration; benchmark/fallback

Your task:
1. Use the transcript anchors above as the primary source packet. If you add outside context, label it clearly as outside context and keep it secondary.
2. Create a source-check table with columns: timestamp, claim, transcript support, what the demo proves, confidence, and what still needs verification.
3. Extract the actual teachable mechanism from the video: Identify why the local setup works or fails for this specific agent task, not whether local models are generally good. Do not invent claims that are not supported by the title, lesson frame, or transcript anchors.
4. Build a reusable learning artifact: A local model/runtime fit sheet with hardware constraints, model choice, endpoint setup, task benchmark, and fallback rule.
5. Include:
   - a plain-English definition of the core idea
   - a diagram or structured model using this sequence: Task -> Hardware -> Model/quantization -> Runtime endpoint -> Agent tool loop -> Benchmark task -> Fallback
   - answers to these source questions: What machine/runtime is shown? | What task exposes the model limit? | What setup change improves the loop?
   - 3 concrete examples that apply the video idea to real agentic work, such as Ollama or LM Studio coding endpoint; MLX Apple Silicon runner; DGX-backed Hermes session
   - 2 failure modes the video helps prevent, chosen from the transcript evidence and these likely risks: using a local model like ChatGPT; ignoring latency/context limits; no benchmark task
   - a checklist for the next real workflow, focused on: task fit, runtime setup, latency/context, tool loop, fallback
   - one practical exercise with a clear done signal: Choose one real coding task and specify the pass/fail benchmark for a local model.
6. Add a "learning transfer" section: what changes in my workflow tomorrow if I actually learned this?
7. Add a "source check" section that cites which transcript anchor supports each major takeaway.

Quality bar:
- Make this specific to "WWDC26: Run local agentic AI on the Mac using MLX | Apple", not a generic Agent Architecture essay.
- Tie each harness element to a transcript anchor that names a tool, state boundary, permission, model behavior, or verification step.
- Prefer operational examples, failure modes, and reusable artifacts over broad definitions.
- Call out uncertainty instead of smoothing over weak evidence.
- Avoid these generic drifts: local-model ideology; hardware specs without workflow fit; benchmarks unrelated to the actual task.
- If evidence is weak or missing, stop and say what transcript segment or timestamp needs review instead of guessing.
- Finish with a concise artifact I could paste into my learning app.