Agent Architecture / Foundation

How I Keep Up with AI Without Drowning in It (Free Skill)

This video explains how to build a personalized AI signal engine that deduplicates and filters items deterministically, lets Jev make obvious keep-or-drop decisions, and escalates uncertain or retained items to an LLM for deeper reasoning and digest preparation. A build-signal-engine skill turns the user's deliberately chosen sources and interests into a tested six-stage implementation whose profile can be explicitly revised over time.

Cole MedinWatchTranscript found

Quick learning frame

Read this before watching.

A model becomes useful when it is wrapped in a harness: tools, state, permissions, memory, routing, and verification.

New playlist item from Cole Medin; queued for transcript-backed review, topic mapping, and a practical learning artifact.

Skill you build: The ability to design and evaluate a staged signal pipeline that preserves personal relevance while measuring how deduplication, deterministic rules, Jev, and an LLM affect volume, accuracy, and cost.

Watch for the shift from claim to mechanism. The learning value is the point where the transcript reveals a repeatable action, tool boundary, context move, review habit, or artifact.

Concept diagram

Where this video fits.

01User intent
02Model role
03Tool surface
04State and memory
05Verification loop
06Reusable operating rule

Deep lesson

Turn this video into working knowledge.

3,306 cleaned transcript words reviewed across 908 timed caption segments.

Thesis

How I Keep Up with AI Without Drowning in It (Free Skill) teaches a practical agent harness move: This video explains how to build a personalized AI signal engine that deduplicates and filters items deterministically, lets Jev make obvious keep-or-drop decisions, and escalates uncertain or retained items to an LLM for deeper reasoning and digest preparation. A build-signal-engine skill turns the user's deliberately chosen sources and interests into a tested six-stage implementation whose profile can be explicitly revised over time.

The goal is not to remember the video. The goal is to extract the operating principle, tie it to timestamped evidence, test how far the claim transfers, and make something reusable.

1:15

Define Personal Signal

“it's just the things that I care about. And I've made this system very accurate over time. So this filter truly is taking out the fluff for me and helping me hone in on what's going to make...”

The engine is designed to summarize what matters to one person's content and coding workflows, not to cover all AI news. The user deliberately defines sources, interests, filters, and decision questions, then refines the generated profile and asks the agent to implement changes; the running engine does not automatically learn from that profile. Write five concrete keep criteria and five drop criteria, then express them as explicit profile changes an agent could implement rather than assumptions the engine should learn on its own.

7:11

Route in Stages

“doesn't really need. That's one of the reasons I like using Apify because for all the runs that I have here, as it's pulling from my different sources, it automatically returns markdown that is optimized for the agent,...”

The funnel first deduplicates centrally and removes stale, low-engagement, or boilerplate content with deterministic rules; Jev then handles obvious keep-or-drop decisions, while uncertain or retained items reach an LLM for deeper memory-based reasoning and digest preparation. A Jev-only experiment reduced accuracy, while one reported 864-post run cost about $0.03 for Jev and $0.42 for surviving Haiku calls; those costs vary with source volume and text length. Diagram the funnel and define a counter for duplicates, deterministic drops, Jev drops or keeps, LLM escalations, final digest items, and cost at each model stage.

9:50

Build and Refine

“follow the instructions in the readme in my skills repository. I'll link to this in the description. If you're using Claude Code, I have a Claude Code plugin to make it so incredibly easy to bring this into...”

The skill interviews the user about goals, missed updates, sources, connection methods, and filters, then builds in six tested stages instead of one-shotting the system: one source end to end, the remaining data layer, deterministic filters, Jev and LLM decisions, digest formatting, and scheduling. It produces an at-a-glance profile that the user can edit in natural language and hand back to the agent for deliberate implementation. Start with one source, test it through the complete funnel, then review the generated profile and write one explicit source or decision-rule revision for the agent to implement.

01

User intent

Start with this video's job: This video explains how to build a personalized AI signal engine that deduplicates and filters items deterministically, lets Jev make obvious keep-or-drop decisions, and escalates uncertain or retained items to an LLM for deeper reasoning and digest preparation. A build-signal-engine skill turns the user's deliberately chosen sources and interests into a tested six-stage implementation whose profile can be explicitly revised over time. Treat "User intent" as the outcome you are trying to make visible, not a topic label. Anchor it to 1:15, where the video says: “it's just the things that I care about. And I've made this system very accurate over time. So this filter truly is taking out the fluff for me and helping me hone in on what's going to make...”

02

Model role

Use "Model role" to locate the part of the agent harness mechanism the video is demonstrating. Ask what changes in your real setup if this claim is true. Anchor it to 7:11, where the video says: “doesn't really need. That's one of the reasons I like using Apify because for all the runs that I have here, as it's pulling from my different sources, it automatically returns markdown that is optimized for the agent,...”

03

Tool surface

Turn "Tool surface" into the reusable artifact for this lesson: A one-page agent harness map with tool boundaries, state ownership, and proof signals. This is where watching becomes something you can inspect and reuse.

04

State and memory

Use "State and memory" as the application surface. Decide whether the idea touches a browser flow, a local file, a model choice, a source document, a UI, or a review step.

05

Verification loop

Use "Verification loop" to prove the lesson. The evidence should connect back to the video title, transcript anchors, and a concrete output, not a generic best-practice claim.

06

Reusable operating rule

Use "Reusable operating rule" to carry the idea forward: save the prompt, checklist, diagram, or operating rule that would make the next agent run better.

Example

Source-backed artifact packet

Convert the video into a scoped artifact request that includes the transcript claim, mechanism, acceptance criteria, and proof. The output should be a one-page agent harness map with tool boundaries, state ownership, and proof signals..

Example

Agent harness proof brief

Separate what the speaker claims, what the demo actually proves, and what still needs outside verification before you adopt the agent harness pattern.

Example

Teach-back module

Transform the lesson into a definition, a User intent -> Model role -> Tool surface -> State and memory -> Verification loop -> Reusable operating rule diagram, one misconception, one practice exercise, and a check-for-understanding question.

Do not learn it wrong
  • Treating the title as the lesson without checking what the transcript actually says.
  • treating model choice as architecture
  • ignoring tool permissions
  • missing verification evidence
  • Letting the lesson drift into generic agent definitions.
  • Letting the lesson drift into model leaderboard claims.
  • Letting the lesson drift into tool list without operating boundaries.

Transcript-derived moments

Use timestamps to study the actual video.

Quality check

Do not count this as learned until these are true.

01

State the transcript-backed claim in your own words: This video explains how to build a personalized AI signal engine that deduplicates and filters items deterministically, lets Jev make obvious keep-or-drop decisions, and escalates uncertain or retained items to an LLM for deeper reasoning and digest preparation. A build-signal-engine skill turns the user's deliberately chosen sources and interests into a tested six-stage implementation whose profile can be explicitly revised over time.

02

Explain the practical stakes without hype: New playlist item from Cole Medin; queued for transcript-backed review, topic mapping, and a practical learning artifact.

03

Map the idea onto the User intent -> Model role -> Tool surface -> State and memory -> Verification loop -> Reusable operating rule sequence and name the weakest link.

04

Produce the artifact and include the evidence that proves it: A one-page agent harness map with tool boundaries, state ownership, and proof signals.

Put it into practice

Give this grounded prompt to Codex or Claude after watching.

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

Source video:
- Title: How I Keep Up with AI Without Drowning in It (Free Skill)
- URL: https://www.youtube.com/watch?v=2i_ZyqDmtio
- Topic: Agent Architecture
- My current learning frame: Prototype one source through normalization, deduplication, deterministic filters, Jev, and LLM escalation, then record how many items each stage removes or advances, each model's cost, and one deliberate profile revision before adding more sources.
- Why this matters: New playlist item from Cole Medin; queued for transcript-backed review, topic mapping, and a practical learning artifact.

Transcript anchors from this exact video:
- 1:15 / Evidence 1: "it's just the things that I care about. And I've made this system very accurate over time. So this filter truly is taking out the fluff for me and helping me hone in on what's going to make..."
- 3:17 / Evidence 2: "GitHub and archive and Hacker News. But, something that I've started to use recently is Appify. It is a single platform that allows me to very easily connect my agents to thousands of different sources, like YouTube and..."
- 5:27 / Evidence 3: "the first couple of stages. And you can use a cheaper model for this. Like Haiku, especially with the new Haiku 5.5, you can have a lot of reasoning capability for super cheap. But, I still don't want..."
- 7:11 / Evidence 4: "doesn't really need. That's one of the reasons I like using Apify because for all the runs that I have here, as it's pulling from my different sources, it automatically returns markdown that is optimized for the agent,..."
- 9:50 / Evidence 5: "follow the instructions in the readme in my skills repository. I'll link to this in the description. If you're using Claude Code, I have a Claude Code plugin to make it so incredibly easy to bring this into..."
- 12:10 / Evidence 6: "through a six-stage process to build out everything. So, we're not just trying to one shot it. We're having it split up into bite-size pieces of work and it's going to test after every single one of them."
- 13:41 / Evidence 7: "engine is not reading this every time it runs, but whenever you want to change something, you can just update it here in natural language and then tell the agent to implement those changes. So, there you go."

Video-aware target:
- Prompt lane: Agent harness
- Mechanism to extract: Identify what surrounding harness makes the model more useful than chat alone.
- Artifact to produce: A one-page agent harness map with tool boundaries, state ownership, and proof signals.
- Artifact must include: model role; tools; state/memory; permission boundary; verification proof

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 what surrounding harness makes the model more useful than chat alone. Do not invent claims that are not supported by the title, lesson frame, or transcript anchors.
4. Build a reusable learning artifact: A one-page agent harness map with tool boundaries, state ownership, and proof signals.
5. Include:
   - a plain-English definition of the core idea
   - a diagram or structured model using this sequence: User intent -> Model role -> Tool surface -> State and memory -> Verification loop -> Reusable operating rule
   - answers to these source questions: What does the video claim the agent can do? | What surrounding system makes that claim plausible? | What proof is shown instead of merely asserted?
   - 3 concrete examples that apply the video idea to real agentic work, such as a repo-editing harness; a local research assistant; a recurring refresh agent
   - 2 failure modes the video helps prevent, chosen from the transcript evidence and these likely risks: treating model choice as architecture; ignoring tool permissions; missing verification evidence
   - a checklist for the next real workflow, focused on: tool boundaries, state ownership, done signal, recovery path
   - one practical exercise with a clear done signal: Map one current coding workflow as a harness and mark the first missing proof signal.
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 "How I Keep Up with AI Without Drowning in It (Free Skill)", 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: generic agent definitions; model leaderboard claims; tool list without operating boundaries.
- 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.

Misconceptions

What to stop believing.

A better model automatically makes a better agent.

The model matters, but harness design determines whether the system can act safely and repeatably.

More tools always help.

Every tool increases surface area. Strong agents have the right tools with clear permissions.

Memory means saving everything.

Useful memory is compressed, curated, and tied to future decisions.

Practice studio

Learning only counts when you make something.

01

Transcript evidence map

Separate what the video actually says from what you already believe about the topic.

3 source-backed takeaways with timestamps, confidence, and a transfer note.
02

One useful artifact

Apply the video to a real workflow and produce a one-page agent harness map with tool boundaries, state ownership, and proof signals..

A reusable artifact with a done signal and one verification step.
03

Agent harness teach-back card

Explain the agent harness mechanism to someone who has not watched the video yet.

A 90-second explanation, one diagram, one example, and one misconception to avoid.

Recall check

Answer first, then reveal — without rewatching.

How are the signal engine's interests and filters refined over time?

Why does the pipeline use Jev before—but not instead of—the LLM?

Why does the skill build one source end to end before adding the rest?

Source shelf

Use the video as a doorway, then verify with primary sources.

DocsOpenAI Agents SDK: agents

Read this for the basic object model: instructions, tools, handoffs, guardrails, and structured outputs.

openai.github.io/openai-agents-python/agents/
DocsOpenAI Agents SDK: tracing

Use this to understand why observability is part of agent architecture.

openai.github.io/openai-agents-python/tracing/
DocsOpenAI Agents SDK: guardrails

Good follow-up for thinking about boundaries, tripwires, and tool-level checks.

openai.github.io/openai-agents-python/guardrails/
DocsOpenAI Agents SDK: handoffs

Explains delegation between specialized agents and what context gets forwarded.

openai.github.io/openai-agents-python/handoffs/
ReadingModel Context Protocol

Useful for understanding how external tools and context servers become part of the agent environment.

modelcontextprotocol.io/introduction
PodcastLatent Space: The AI Engineer Podcast

Best ongoing podcast lane for agent tooling, AI engineering, codegen, infra, and model shifts.

www.latent.space/podcast
PodcastPractical AI podcast archive

Older but still useful practical conversations on agents, AI engineering, and production concerns.

changelog.com/practicalai/