These AI Agents Talk to EACH OTHER Across Terminals!
This video demonstrates Nico's 'intercom' Pi extension, which lets four separately-launched terminal agent sessions (different models, different assigned roles) discover and message each other as flat peers to stress-test a video pitch instead of relaying through one boss agent.
Eric Michaud12 minTranscript found
Quick learning frame
Read this before watching.
Creative automation uses agents to accelerate production while keeping human taste in story, pacing, selection, and critique.
New playlist item from Eric Michaud; queued for transcript-backed review, topic mapping, and a practical learning artifact.
Skill you build: Setting up a flat, peer-to-peer multi-agent 'war room' across separate terminal sessions where named, role-specialized agents critique and reach consensus on an idea.
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.
01Brief
02Source
03Generation
04Selection
05Edit
06Taste Review
Deep lesson
Turn this video into working knowledge.
2,783 cleaned transcript words reviewed across 798 timed caption segments.
Thesis
These AI Agents Talk to EACH OTHER Across Terminals! teaches a practical creative automation move: This video demonstrates Nico's 'intercom' Pi extension, which lets four separately-launched terminal agent sessions (different models, different assigned roles) discover and message each other as flat peers to stress-test a video pitch instead of relaying through one boss agent.
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.
0:57
Peers vs sub-agents
“completely flat. The reason this matters is you can put different agents with different specialties, even different models in the same room working towards one common task. And they can stress test an idea and you're not bottlenecked...”
Intercom is structurally different from sub-agents: sub-agents are hierarchical delegation under one boss agent, whereas intercom agents are flat peers messaging each other directly with no parent, so no single agent's perspective bottlenecks the outcome. Write a two-column comparison of 'sub-agent delegation' vs 'intercom peer chat' and note which of your own tasks need judgment (peers) versus execution (delegation).
4:01
Name the sessions
“responsibilities and different models, okay? So, let's change Debbie to Grok 4.1 fast. Let's change Diane to GLM 5.1. Change Jack to Gemini 3.1. Let's keep Pat here at GPD 5.5. Obviously, you can use whichever models you...”
Each terminal session must be given a distinct name (Pat Boone, Debbie, Jack, Diane) so the other Pi agents can discover and ping each other by name instead of by generic randomly-generated IDs. Open four split terminal panes, launch Pi in each, and explicitly name every session, then run a prompt like 'use intercom to list active sessions and ping each one' to confirm discovery works.
8:11
Engineer friction
“that's like super not helpful. You need friction and you need conflict. These agents need to know that they're working together, sure, but like somebody needs to be there to break the idea and we all need to...”
The setup doesn't auto-improve output; without an explicitly-assigned skeptic and a 'work toward a better output' mandate, agents just nod at each other, and watch for temporary leadership loops and slow models (GLM 5.1 lagged) bottlenecking consensus. Assign distinct roles (critic, researcher, pitch, consensus-reviewer), pick models of comparable speed, and keep final approval yourself rather than letting the panel run on autopilot.
01
Brief
Start with this video's job: This video demonstrates Nico's 'intercom' Pi extension, which lets four separately-launched terminal agent sessions (different models, different assigned roles) discover and message each other as flat peers to stress-test a video pitch instead of relaying through one boss agent. Treat "Brief" as the outcome you are trying to make visible, not a topic label. Anchor it to 0:57, where the video says: “completely flat. The reason this matters is you can put different agents with different specialties, even different models in the same room working towards one common task. And they can stress test an idea and you're not bottlenecked...”
02
Source
Use "Source" to locate the part of the creative automation workflow the video is demonstrating. Ask what changes in your real setup if this claim is true. Anchor it to 4:01, where the video says: “responsibilities and different models, okay? So, let's change Debbie to Grok 4.1 fast. Let's change Diane to GLM 5.1. Change Jack to Gemini 3.1. Let's keep Pat here at GPD 5.5. Obviously, you can use whichever models you...”
03
Generation
Turn "Generation" into the reusable artifact for this lesson: A creative workflow board with critique criteria and review checkpoints. This is where watching becomes something you can inspect and reuse.
04
Selection
Use "Selection" 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
Edit
Use "Edit" 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
Taste Review
Use "Taste Review" to carry the idea forward: save the prompt, checklist, diagram, or operating rule that would make the next agent run better.
Example
Source-backed work packet
Convert the video into a scoped task that includes the transcript claim, target workflow, acceptance criteria, and proof. The output should be a creative workflow board with critique criteria and review checkpoints..
Example
Claim vs. demo brief
Separate what the speaker claims, what the demo actually proves, and what still needs outside verification before you adopt the workflow.
Example
Teach-back module
Transform the lesson into a definition, a mechanism 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.
Letting the prompt drift into generic advice that could apply to any video in the playlist.
Copying the tool setup without identifying the operating principle that transfers to your own stack.
Skipping the artifact, which means the learning never becomes operational or inspectable.
Do not count this as learned until these are true.
01
State the transcript-backed claim in your own words: This video demonstrates Nico's 'intercom' Pi extension, which lets four separately-launched terminal agent sessions (different models, different assigned roles) discover and message each other as flat peers to stress-test a video pitch instead of relaying through one boss agent.
02
Explain the practical stakes without hype: New playlist item from Eric Michaud; queued for transcript-backed review, topic mapping, and a practical learning artifact.
03
Map the idea onto the Brief -> Source -> Generation -> Selection -> Edit -> Taste Review sequence and name the weakest link.
04
Produce the artifact and include the evidence that proves it: A creative workflow board with critique criteria and review checkpoints.
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: These AI Agents Talk to EACH OTHER Across Terminals!
- URL: https://www.youtube.com/watch?v=-we7iVySwkM
- Topic: Creative Automation
- My current learning frame: Spin up four named Pi terminal sessions with the intercom extension, assign one critic, one researcher, one pitch-writer, and one consensus-reviewer across different models, and have them debate whether one of your own content ideas is worth pursuing.
- Why this matters: New playlist item from Eric Michaud; queued for transcript-backed review, topic mapping, and a practical learning artifact.
Transcript anchors from this exact video:
- 0:57 / Evidence 1: "completely flat. The reason this matters is you can put different agents with different specialties, even different models in the same room working towards one common task. And they can stress test an idea and you're not bottlenecked..."
- 4:01 / Evidence 2: "responsibilities and different models, okay? So, let's change Debbie to Grok 4.1 fast. Let's change Diane to GLM 5.1. Change Jack to Gemini 3.1. Let's keep Pat here at GPD 5.5. Obviously, you can use whichever models you..."
- 6:19 / Evidence 3: "your peers in this room. Your job is to review the consensus and confirm that each agent is happy with the final output. So, we're going to say yes to all of these. Grok 4.1 fast is deprecated."
- 8:11 / Evidence 4: "that's like super not helpful. You need friction and you need conflict. These agents need to know that they're working together, sure, but like somebody needs to be there to break the idea and we all need to..."
- 10:55 / Evidence 5: "Control-alt-t instead of clicking the split, right? So, I could theoretically just do this like four times, and spin up my agents that way, but I'm going to actually get like a hotkey, like a button for the..."
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, what the demo proves, confidence, and what still needs verification.
3. Extract the actual teachable claims from the video. Do not invent claims that are not supported by the title, lesson frame, or transcript anchors.
4. Build a reusable learning artifact: A creative workflow board with critique criteria and review checkpoints.
5. Include:
- a plain-English definition of the core idea
- a diagram or structured model using this sequence: Brief -> Source -> Generation -> Selection -> Edit -> Taste Review
- 3 concrete examples that apply the video idea to real agentic work
- 2 failure modes the video helps prevent
- a checklist I can use the next time I run Codex or Claude
- one practical exercise with a clear done 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 "These AI Agents Talk to EACH OTHER Across Terminals!", not a generic Creative Automation essay.
- Prefer operational examples, failure modes, and reusable artifacts over broad definitions.
- Call out uncertainty instead of smoothing over weak evidence.
- If evidence is weak, 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.
Creative AI removes the need for taste.
It increases the need for taste because output volume explodes.
The best prompt is enough.
References, critique, iteration, and post-production matter just as much.
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 creative workflow board with critique criteria and review checkpoints..
A reusable artifact with a done signal and one verification step.03
Teach-back card
Explain the lesson 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 does Intercom differ structurally from sub-agents, and why does that difference matter for the kind of work it's good at?
When setting up the four terminal sessions, what specific step is required for the Pi agents to find each other, and why?
The presenter warns that this setup doesn't automatically produce a better output. What two failure modes does he call out, and what must you do to avoid the agents just agreeing?
Source shelf
Use the video as a doorway, then verify with primary sources.
