lol another vibe coder who just discovered ChatGPT
▲ 2▼replyshare
Started coding at 12… to buy more LEGO.
Then I found digital things: infinite LEGO.
The only limits were time and knowledge.
I never wanted to code. I wanted to build.
Code was always a means to an end.
April 2025 · where a lot of you are right now
I started with Claude Code in a terminal. $ claude
1Unix has a CLI for everythingno API? there's a CLI. Beats driving a GUI.
2Labs train models on the terminalreinforced on tool calls
3Model + harness evolve togetherharness = the agent loop + everything around it
But
The TUI is a terrible place to spend your whole day.
→ SDKs + desktop apps (Codex, Claude): same local CLIs, no terminal
The terminal's biggest problem
10 terminals. 10 agents. 0 saved sessions.
$ claude_
$ claude_
$ claude_
$ claude_
$ claude_
$ claude_
$ claude_
$ claude_
$ claude_
$ claude_
AgentGrid v1
infinite canvas
save + reload the layout
agents spawn + message peers
same session, not a new one
Bottleneck #1 · not tokens
Seeing + steering many agents at once.
agent-gridwebsitemobileresearch
AgentGrid · every agent on one canvas · tabs per project · switch in a clickMUTED · press M
How to start
Talk to one agent.
on the canvas, if you want to look
YOU
COORDINATORthe one agent
TEAMiOS attachments
researchbuildreviewreviewtwo model families
TEAMusage report
+ more teams
A confession
I reviewed ~1,000 PRs by hand.
Then I noticed I'd stopped finding anything.
The factory
You describe it. The factory ships it.
01
DESCRIBE
you tell the Coordinator
02
TICKET
it files the issue
03
TEAM
a new team takes it
04
DRAFT PR
the team builds it
05
2× REVIEW
two model families
06
AUTO-MERGE
when CI is green
The Coordinator checks it all, on a loop.
the bug, on my phone
Message Coordinator
dictated it
sent from the phone
the ticket
the team
draft PR
the PR
the reviewers
review: Claude ✕
review: Codex ✕
re-review: two ✓
merged · 10:38 pm
2h 37m
cost, on every PR
A day in my factory · two modes
10:30co-founder standup→Granola summary→agents start building
MODE 1 · FIRE-AND-FORGET
anything I notice
customer requests
agents merge + deploy
MODE 2 · EXPLORE TOGETHER
UX storyboards
research · architecture
talked through on a walk
“We have more tickets than agent capacity.”
Mac Mini · 24/7phone in my pocket|136 merges in our repo on Oct 29
Bottleneck #1: tokens
Tokens were my bottleneck.
19 harnessesswitch harness on the same transcript, manually
2Auto-switch harnesswhen one runs out
3Multiple accountsauto-switch accounts as they run out
4Usage reportspend over time, across accounts, ask the AI about it
The leak I found
3 Codex accounts. Empty in < 1 day.
Astra instead of Sol5×
Fast mode on everything2×
= more tokens than needed10×
→ Sol by default. Fast mode off.
Bottleneck #2: compute
Native apps: heavy builds. Agents wait on the machine.
How I found it: kept asking the agent “what's the biggest bottleneck?” …and watched Activity Monitor.
Every agent booted its own simulator (media indexing spiked the CPU)
→
A warm simulator pool, reused via a queue
Spotlight indexed every new worktree (CPU + RAM spikes)
→
Exclude worktrees from Spotlight
One machine wasn't enough
→
Mac mini + cloud credits (AWS · Azure · GCP)
Next: run agents on any hardware you have, or on our cloud.
Tokens will be the bottleneck again.
The dividend: time
I finally had time to build this.
The unlock ladder · my blockers
TOKENS ✓unlocked
COMPUTEmy blocker now: distributed cloud
SELF-EVOLVING AGENTSthe factory fixes its own blockers
HARDWAREslow to iterate: point factories at it
next → Shan Liu, 4:10: “I Built a Self-Improving Agent”
Your factory, tomorrow morning
0
Download AgentGrid · agentgrid.sh
1
Open your project (or start one), describe the problem
2
It files the GitHub issue (automatic)
3
It spins up a team: one builder, two reviewers from different model families
4
Let it work: gates → commit → merge
5
Loop: every 10 min, check for new issues
Start tonight
Download AgentGrid.
This week we onboard every one of you.
slides, recipe + talk to me:
agentgrid.sh/michael
Thank you
@yagudaev
→ ␣ PgDn next build / slide ← PgUp previous Home / End first / last slide 1-9 ⏎ type a number + Enter to jump t slide number + timer r reset timer n speaker notes p / 0 demo: play-pause / restart m video: mute / unmute (starts muted) v demo slide: switch variant A / B f fullscreen ? this help
AgentGrid
