okikusan-public / articles / From editor to agent management — Google Antigravity 2.0 marks the arrival of the Agent OS
JA EN
← articles
CONTENTS6 sections
  1. 01From editor to agent management
  2. 02Four pillars
  3. 03Not a specialist worker
  4. 04New comparison axes
  5. 05The next battlefield
  6. 06Individual & enterprise fit
  7. Summary
AGENT OS / 2026

From editor to agent management — Google Antigravity 2.0 marks the arrival of the Agent OS

Antigravity 2.0 is not an AI-IDE update. It is the moment the centre of gravity in developer experience shifts from "the editor" to "agent management." The Desktop / CLI / SDK / integration funnel together stop being a "specialist worker" like Claude Code / Codex / Grok Build, and start looking like an Agent OS.

The old axis "which model is smarter" is no longer enough. Harness design, permission boundaries, context, scheduled execution, and human review — these five decide developer productivity now. The next battlefield of AI coding, laid out.

Antigravity 2.0 Agent OS Agent Harness Google Gemini AI agent 2026.05.20 · 6 min read
FIG.0 — AGENT OS STACK
Antigravity 2.0 as an Agent OS: MODEL → AGENT HARNESS → four interfaces (Desktop / CLI / SDK / AI Studio×Android×Firebase)
At the centre, AGENT HARNESS (Antigravity) binds the MODEL with four interfaces (Desktop / CLI / SDK / integration funnel). "Same harness, different UIs." The axis moves from "which model is smarter" to harness design + permission boundaries.
▍ THE PROMISE

Antigravity 2.0 is not an editor — it is an Agent OS. It is not in the same layer as Claude Code / Codex / Grok Build (the specialist workers); it is the layer that binds Desktop / CLI / SDK / API together. The next battlefield of AI coding is not inside the editor — it is how you orchestrate, supervise, and continuously run agents.

▍ SOURCES
▍ TERMS — definitions and premises (set up first)

Aligning the vocabulary and editorial lens up front, before they recur in later sections. Detailed discussion lives in each section.

Agent harness
The "execution rig" wrapped around the model. In Karpathy's Agent = Model + Harness formulation, this is the Harness side. Concretely, the runtime that binds:
  • System prompt / role definition (how the model is told to behave)
  • Tools (function calling) — file I/O, Bash, web fetch, external systems via MCP, etc.
  • Memory / state — conversation history, file locations, prior decisions
  • Permissions and guardrails — read-only or write-capable, does Bash require approval, etc.
  • Feedback loops — retry on error, output verification, sub-agent spawning
Concrete examples:
  • Claude Code's harness = CLI agent loop + built-in tools + project permissions + ToolUse/ToolResult pipeline
  • Cursor's harness = editor integration + Apply mechanism + codebase index
  • Antigravity's harness = local app server + agent harness runtime + Skill-pack attachment mechanism
In short: "a smart model with a sloppy harness is useless," "the same model with a different harness behaves completely differently." The harness is the layer that decides actual agent behaviour.
Agent OS layer / Specialist worker layer
The central axis of this piece. Agent OS layer = shares one harness across multiple UIs / permissions / scheduler / agent orchestration (Antigravity, Hermes, Copilot Studio). Specialist worker layer = invoked to do the work (Claude Code, Codex CLI, Grok Build). "Agent OS" is not Google's official term — it is community framing and this article's editorial lens (see also the terminology note in §03).
Subagent
A child agent spawned dynamically by a parent agent — used for parallel execution and role division. Antigravity 2.0's launch demo built an OS from scratch with 93 subagents running in parallel (see VOICES below).
Skill
A pluggable capability pack you attach to an agent. Antigravity's Android Skills / Firebase Skills add a specific domain's APIs and conventions to the agent harness (see §2-4).
App server (shared backend)
A shared local backend inside the Antigravity install. Both the Desktop UI and the CLI binary call the same app server, which drives the agent harness underneath (see §2-2).
The five comparison axes
How this article evaluates AI coding platforms — (1) harness design / (2) permission boundaries / (3) context / (4) scheduled execution / (5) human review. "Which model is smarter" no longer covers it (see §04).
▍ TL;DR
§ 01 SHIFT

From editor to agent management — where the centre of gravity moved

For the past two years, the AI-coding story has revolved around "the editor." GitHub Copilot, then Cursor, then Claude Code, Codex CLI, Grok Build. Every step refined "AI writes code inside the editor."

Antigravity 2.0 nudges that axis itself. The four pillars of this release:

Lined up, this is not "the editor getting stronger." The centre of gravity has shifted to "how do you bind agents and run them." From "one task in one editor" to "many tasks running in parallel, managed centrally."

▍ Read as "AI IDE update," it looks small

Feature-by-feature it reads as a scatter — "dynamic subagents added," "scheduled tasks added," "SDK shipped." Bundled, it becomes "the same harness, exposed through four UIs". That is the shape of an Agent OS roadmap, not an IDE roadmap.

§ 02 PILLARS

The four pillars — Desktop / CLI / SDK / integration funnel

>2-1Desktop app — the command center

A command bridge for running many agents in parallel. Dynamic subagents (spawn and retire children on the fly), scheduled tasks (cron-style runs), and per-project permission scopes. The feel shifts from "one task in one editor" to "many tasks running at once, all in view."

>2-2Antigravity CLI — different UI, same harness

Successor to Gemini CLI. A lightweight UI for terminal people, but the key is that it shares the same agent harness as Desktop. The CLI isn't a separate product — it's a different interface to the same base. Agents you compose in Desktop behave identically from the CLI.

FIG.2-2 — SHARED HARNESS
Inside an Antigravity local install, both DESKTOP (GUI) and CLI (Go binary, $ ag run) front-ends arrow into the same LOCAL APP SERVER (agent harness: agent definitions / permissions / scheduler / tools · skills), which then makes all model calls to Gemini 3.5 Flash API (cloud)
The outer dashed box is the local Antigravity install. Inside, Desktop (GUI) and CLI (Go binary) share the same roof — both arrow into a single LOCAL APP SERVER (the agent harness itself: agent definitions / permissions / scheduler / tools · skills). That's why a job composed in Desktop is callable from the CLI as-is. All model calls converge at the Gemini 3.5 Flash API below.
▍ Note: what 'sharing the same harness' actually means

It is not two competing apps. It is one local installation that ships Desktop UI, CLI binary, and a shared local app server (the agent harness itself) together. @karthickdotxyz describes it as "Same tools and app server as Antigravity 2.0."

What that gives you:
You don't need both running — Desktop or CLI, either one is complete on its own
Configs, agent definitions, permissions, scheduled tasks are shared — a job set up in Desktop is callable from the CLI as-is
CLI fits CI / headless servers; Desktop fits interactive development. Natural separation by use case.

(The exact behaviour of the local app server — whether it runs as a daemon, only when Desktop is open, etc. — is not in the public docs yet. The description here is inferred from @karthickdotxyz's wording.)

>2-3SDK — embed the harness into your own product

Google's agent harness is now something you embed into your own workflow or product. This stops being "a tool that makes AI write code" and starts being "a platform for building and operating AI agents." The code you write with the SDK runs on your own PC / server / CI runner — Google does not host it for you; it lives inside your process as part of your product. Antigravity could become a component that runs inside other companies' products, not just Google's IDE.

FIG.2-3 — SDK EMBED
YOUR APPLICATION (Slack bot / Internal dashboard / Datadog auto-fix backend / Custom backend) imports the ANTIGRAVITY SDK (agent harness as library, client = Antigravity(...) / result = client.run(prompt, context)), which RUNS IN YOUR PROCESS — local PC / your server, VM, container / CI runner — a 3-layer architecture
Top tier = your application (Slack bot, internal dashboard, Datadog-alert auto-remediation backend, etc.) imports / calls the Antigravity SDK. Middle tier = the SDK exposes the agent harness as a library (client = Antigravity(...) / result = client.run(prompt, context)). Bottom tier = the SDK runs in your own process (local PC / your server, VM, container / CI runner) — Google does not host the runtime for you. The agent stops being "a hosted service you call" and becomes "a component you import."
▍ CLI vs SDK — what's the actual difference?

Both run on local machines or on servers. The real distinction is the primary use case each is designed for:

CLI = an interactive front designed for a human (or shell script) to drive an agent directly — you type antigravity chat / antigravity run and get a result back
SDK = a library designed for your program to drive the agent via function calls — fits Slack bots, internal dashboards, Datadog-alert auto-remediation backends

Strictly, you can also call the CLI from a program by shelling out (subprocess.run("antigravity ...")). But shelling out comes with costs: (a) process startup overhead / (b) brittle text-output parsing / (c) no types / (d) streaming and structured events are awkward. The SDK assumes that use case from the start — typed responses, long-lived connections, streaming, structured events.

It is the same shape as AWS CLI vs boto3 (the AWS Python SDK). You can shell out aws s3 ls from Python, but boto3.client("s3") is the proper path. For Antigravity, both ultimately drive the same Google agent harness — but the SDK is the path optimised for programmatic consumption.

>2-4AI Studio × Android × Firebase integration

Less "three products wired together at the UI layer," more "Antigravity sits in the middle as the harness, with AI Studio (entry) and Android / Firebase (exit) bolted on via a shared harness and Skills." Concretely:

So Google's "vertical integration" play is re-engineered not at the UI layer but at the harness and Skill (attachable capability packs) layer. The mechanism for compressing idea → build → verify → ship is implemented as agent infrastructure, not as more editor features.

FIG.3 — INTEGRATION BRIDGES
Antigravity 2.0 as the central harness, with AI Studio on the left (UPSTREAM — Export to Antigravity preserves the full agent conversation) and Android / Firebase on the right (DOWNSTREAM — Android Skills / Firebase Skills add domain capability packs). The three integration bridges around the central harness.
At the centre, Antigravity 2.0 is the agent harness. From the upstream side, AI Studio hands off the full agent conversation (chat / config / code) via "Export to Antigravity"state is preserved on the way in. On the downstream side, Android and Firebase arrive as Skills (attachable capability packs) that teach the agent SDK / Gradle / Firestore / Functions conventions. Integration lives at the harness and Skill layer, not at the UI.
youtube.com / Google
Antigravity 2.0 — official launch video (YouTube)
Google's IO 2026 walkthrough of Antigravity. See the four pillars above — Desktop / CLI / SDK / integration funnel — in actual motion.
Watch on YouTube →
§ 03 LAYER

Not a "specialist worker" — Antigravity sits at the Agent OS layer

▍ Terminology note on 'Agent OS'

The phrase "Agent OS" used throughout this piece is not Google's official terminology. Right after the Antigravity 2.0 launch, @grok on X called it "the emerging Agent OS category," and @arsh_goyal framed it as a "centralized Agent Manager." This article borrows that framing to describe a specific structural pattern: a single harness shared across multiple UIs (Desktop / CLI / SDK / integration funnel), with permissions, scheduling, and sub-agent orchestration unified at one layer. We use the OS metaphor as an editorial lens, not as a brand or product category claimed by Google.

Lining up Antigravity 2.0 with Claude Code / Codex CLI / Grok Build and asking "which one's best" misses the point. They live at different layers.

>3-1Specialist worker layer vs Agent OS layer

▍ Specialist worker layer
called to do the work
Claude Code Codex CLI Grok Build Cursor Agent
Strong at instant reasoning, code generation, file operations
▍ Agent OS layer
orchestrates and supervises
Hermes (OSS) Microsoft Copilot Studio Google Antigravity 2.0
Bind multiple UIs, parallel execution, permissions, shared harness

With Antigravity 2.0, a Google-native "Agent OS-class" product joins the front line. Inside Google, Workspace Studio sits closed within Workspace as the "Workspace-internal Agent OS"; Antigravity targets a cross-cutting Agent OS for the dev context.

>3-2"VS" framing breaks across layers

"Antigravity 2.0 vs Claude Code" is a layer violation. As Antigravity expands via the SDK inside other companies' products, the natural composition becomes "Antigravity-on-top, calling Claude Code / Codex CLI / Grok Build as workers." The right peers to compare with are Hermes / Copilot Studio — same Agent OS layer.

FIG.4 — LAYER STACK / Agent OS calls specialist workers
Two-tier stack: the Agent OS layer (Antigravity 2.0 / Hermes / Copilot Studio) calls and orchestrates the specialist worker layer below (Claude Code / Codex CLI / Grok Build / Cursor Agent). Compare peers within a layer, compose across layers.
Top tier — the Agent OS layer (Antigravity 2.0 / Hermes / Copilot Studio) — "calls / orchestrates" the bottom tier, the specialist worker layer (Claude Code / Codex CLI / Grok Build / Cursor Agent). The right pattern is peer comparison within a layer, composition across layers — not head-to-head VS framing across layers.
▍ Direct comparison with Hermes / Copilot Studio

Within the Agent OS layer:
Hermes = OSS / individual-tilted / multi-model / 22 gateways / Obsidian integration / domain-agnostic (works outside coding too)
Microsoft Copilot Studio = M365 territory / enterprise permissions / Power Platform integration / business-workflow focused
Google Antigravity 2.0 = Google-native / AI Studio × Android × Firebase vertical integration / software-engineering specialised (officially "Built for developers for the agent-first era")

The scope difference matters: sitting at the same Agent OS layer does not mean the same role. Hermes is a domain-agnostic general harness; Copilot Studio is for business workflows; Antigravity is purpose-built for software-engineering work. The question is "which domain do you want to orchestrate agents in" — that's what decides the choice between them.

§ 04 AXIS

New comparison axes — "which model is smarter" is no longer enough

My read: what Antigravity 2.0 actually changed is not "another AI coding tool entered the market" but the comparison axis itself. Reading the four pillars from §02 (Desktop / CLI / SDK / integration funnel) as a structure, each pillar embeds a design decision that the old axis "which model is smarter" simply cannot capture:

So if you unpack the structure of Antigravity 2.0 honestly, the five axes — harness / permission boundary / context / timing / review — surface naturally. They are the axes that show up the moment you ask "what is an Agent OS the union of?"

▍ This is my own view — why these 5 axes

The five design axes used below (harness / permission boundary / context / timing / review) are not a standard framework published by Google, IDC, Forrester, or anyone else — they are my (the author's) editorial synthesis of what I think actually matters. My reasoning for picking these specific 5 (and not 3 or 7):

  • harness — with model IQ commoditising, harness design is what determines an agent's actual behaviour. The next battleground after "which model is smarter."
  • permission boundary — when agents act autonomously, permission scope decides the blast radius (read / write / exec / against what).
  • context — same model + same IQ produces wildly different output depending on context given. I wrote a separate piece on this.
  • timing — manual / hook / cron agents are different beasts. Antigravity 2.0 making scheduled tasks first-class is evidence this matters.
  • review — human-in-the-loop verification load is the productivity bottleneck. Also standard vocabulary in AI safety.

The individual terms (harness / permission etc.) have currency across the industry, but bundling these 5 as "the evaluation axes that matter" is my judgement. Someone proposing a different cut would be perfectly reasonable.

What Antigravity 2.0 really points to is a demand to update the axis itself.

FIG.1 — AXIS MAP
Before/After: 2023-2025 single-axis evaluation (model IQ) shifts to 2026+ five-axis design surface (harness / permission / context / timing / review) — the Agent OS era pentagon
Old axes: which model is smarter, which editor is fastest, context window size. New axes: harness / permission boundary / context / scheduling / review. Compare Agent OS design, not raw model strength.

Side-by-side, what changes per axis between the editor era and the Agent OS era is unmistakable:

Axis Editor era (~2025) evaluation Agent OS era (2026 →) evaluation
harness Editor's completion speed / UX (Cursor vs Claude Code vs Codex — which feels faster / nicer) Which tools, memory, permissions, feedback loops you wrap around the model. Same model, different harness → different behaviour entirely.
permission Largely a non-question — one developer typing at the keyboard, manual control everywhere Autonomous agents run, so Project / User / Agent-scoped permissions define blast radius (read / write / exec against which resources)
context Context window size (how many tokens fit — a "quantity" axis) What you actually pull in and hand the agent (docs / code / issues / ops logs / diff rationale — a "quality" axis, plus Skill packs)
timing Does completion appear at the moment a human is typing? (synchronous / immediate only) Manual / hook / cron / scheduled tasks — when do agents fire? (Async / parallel / 24-7 included)
review Humans read before and after writing code (human-led, AI assists) How far do you trust auto-executed agent output, and where does a human gate it? (Minimising verification load)

Footnote: the old axis "which model is smartest" (GPT-5 / Claude Opus / Gemini / grok-4.3) no longer stands on its own — same model with different harness and context produces wildly different output, so model IQ alone has collapsed as a comparison axis.

These five decide developer productivity itself. Smarter models with sloppy harnesses just automate Slop (the "don't automate Slop" principle applies here too).

▍ The Harness Engineering through-line

The Harness Engineering thread from the previous post ("Don't build an AI that replays yesterday's spec") connects directly. By Karpathy's framing — Agent = Model + Harness — Antigravity 2.0 reads exactly as Google's first-party Harness-supply platform.

§ 05 BATTLEFIELD

The next battlefield of AI coding is not inside the editor

The conclusion is simple. The next battlefield of AI coding is not inside the editor — it is how you orchestrate, supervise, and continuously run agents.

FIG.2 — BATTLEFIELD TIMELINE
AI-coding battlefield timeline: 2023 prompt → 2024 context → 2025 editor → 2026+ Agent OS
A staircase timeline of battlefields. 2023 prompt → 2024 context → 2025 editor → 2026+ Agent OS. Antigravity 2.0 sits at this inflection point.

Past battlefields:

The next:

▍ "Orchestrate · supervise · continuously run"

Orchestrate = who is assigned what (permission boundary design)
Supervise = when and how humans step in for review (minimising verification load)
Continuously run = 24/7 via cron / webhook / hooks
None of these are editor-resident jobs. They are clearly Agent OS work.

▍ VOICES — use cases that surfaced in the first 48 hours

Snapshots from X in the 48 hours since launch — building a full OS from scratch, recreating the AlphaZero paper, code-analysis pipelines, scheduled parallel agents. The chatter is visibly shifting from "a specialist worker writes code" toward "a fleet of agents gets orchestrated."

A
Andreas
@andreasawires · 2026.05.20
Google's Antigravity 2.0 project, combined with Gemini 3.5 Flash agents, built a fully functioning operating system from scratch. 93 parallel sub-agents, 12 hours, 15K+ model requests, 2.6 billion tokens, under $1K in API credits.
View on X →
A
Andy Zhang
@andyzhang · 2026.05.20
I'm so proud of the @antigravity team for everything we've launched today. We introduced Antigravity 2.0, a desktop application to manage all of your agents. The team poured a lot of heart into this and I can't wait for you to try it alongside Gemini 3.5 Flash.
View on X →
V
Vahab Mirrokni
@mirrokni · 2026.05.20
Gemini 3.5 is indeed a great model. Apart from its efficiency and improved agentic evals, it's good for long-horizon complex tasks, e.g., built on this model, /teamwork agents in Antigravity created a full training of AlphaZero paper with self-play and all. Try it out!
View on X →
S
SHT4BHARAT
@SHT4BHARAT · 2026.05.20
93 AI agents just built a functional operating system framework from scratch in 12 hours. Total cost? Under $1K for 2.6 billion tokens. This live demo from #GoogleIO2026 just proved we are officially out of the chatbot era and deep into production-scale autonomous workflows.
View on X →
K
Karthick
@karthickdotxyz · 2026.05.20
Say hello to Antigravity CLI 🚀 🧑‍💻 - Written in Go for a snappy feel ✨ - Available with Gemini 3.5 Flash today 🤖 - Built for async workflows and subagents ⚒️ - Same tools and app server as Antigravity 2.0 Get started and install it today 👇
View on X →
Y
Yoshifumi Kawai
@neuecc · 2026.05.20
Antigravity 2.0の変化の方向性は当然っちゃあ当然。実際Cursor 3めっちゃ好ましかったですもの。そして一周回ってエージェントアプリはエージェントアプリで独立するので、コードはIDE(Visual Studio 2026)という使い分けになって、ワークフロー的にも更に好ましい。
View on X →
G
GptZone
@gptzone_net · 2026.05.20
Antigravity 2.0 no se debería evaluar como un autocompletado más agresivo. Se debería evaluar como un cambio de workflow. Si el agente puede trabajar en segundo plano, crear subagentes, gestionar proyectos con varias carpetas, usar permisos integrados y ejecutar tareas...
View on X →
ビームマンP ver40
@BeamManP · 2026.05.19
Gemini 3.5 Flashのヤバいところ: ついに音楽解析ができるようになってた!! 曲を食わせると、Aメロ・サビとかの区切りをめっちゃ正確に解析してくれる。MV作り序盤が激楽になる!!!!! (Google AI Studioで解析。参考資料はClaudeで作成)
View on X →
§ 06 FIT

How individuals and enterprises choose

▍ From here on, this is my personal view

The "individuals should X, enterprises should Y" guidance below is my personal recommendation, not an official line from Google, Microsoft, or Nous Research.

Fact-based (verifiable):
・ Hermes is OSS / multi-model / Obsidian integration / domain-agnostic
・ Antigravity 2.0 is vertically integrated into the Google ecosystem / software-engineering specialised
・ Microsoft Copilot Studio sits in the M365 territory / business-workflow focused

My personal view (where reasonable people will disagree):
"For individual developers, combine Hermes and Antigravity" — I say this because (1) Hermes' Obsidian / gateway integration fits individual knowledge work, and (2) Antigravity is optimal for Google-ecosystem development. This is extrapolated from my own workflow as an individual developer. Organisations may legitimately optimise differently.
"For organisations, mix across domains" — I say this because the requirements for business workflows (Copilot Studio), dev workflows (Antigravity), and individual knowledge work (Hermes) are too different to consolidate on one product. Counter-views exist ("just unify on Copilot Studio for ops simplicity"; "stay OSS-only on Hermes for transparency") and are perfectly reasonable.

Not a definitive answer — translate to your own context.

What changes between individual and team / enterprise use, axis-by-axis (§04 5 axes), makes the picking criteria explicit:

Axis Individual use Team / enterprise use
harness Each developer installs whichever harness they prefer locally (Claude Code / Hermes / Cursor / Antigravity) A standardised harness across the org / custom harness embedded via the Antigravity SDK into internal products
permission Mostly read / write against your own Mac and your own repos Hierarchical ACL across Project / User / Role; permission separation against internal systems; per-agent scope restrictions
context Your own Obsidian, your own git repos, your own Slack DMs — sources you personally hold Internal Confluence / shared GitHub orgs / company Slack / Linear & Jira / on-call runbooks — sources shared across many users
timing Interactive on your PC, or a light personal cron (stops the moment your Mac is asleep) Embedded via SDK in a shared server / CI runner / 24-7 environment. Runs outside business hours; ownership is explicit
review Personal self-check (read while you write) Code review / PR approval flow / audit logs / compliance checks — multi-stage gating required

Footnote: the concept of "harness" itself is neutral to individual vs team use — it's just the runtime wrapping the model. Team-readiness depends on the specific implementation: Claude Code / Hermes / Cursor are basically "local, per-individual"; Antigravity 2.0 splits the difference (Project permissions + SDK + Enterprise wording cover both individual and team); Copilot Studio is M365-native and assumes "team / business" from the start.

▍ Sharing a harness across a team = SDK is the only path

Antigravity's standalone Desktop / CLI is structurally built around "an app server pinned to one machine" (see FIG §2-2). Even if a team wants to share the same harness, agent definitions / Projects / scheduled tasks are bound to each local app server — sharing the config via git still leaves you with separate instances.

If you actually want a "shared" harness for a team, the realistic route is via the SDK (§2-3): embed it into an internal backend / shared server / CI runner so multiple users hit a single harness instance you operate. Until Google ships a hosted "Managed harness," "team harness as a service" is something you have to build yourself — that's the current constraint.

>6-1Individuals — Hermes and Antigravity in combination

OSS-leaning individuals still get great value from Hermes. Obsidian integration, multi-model routing, the gateway pack (Telegram / Discord / LINE / Slack) are Hermes-only as of now.

Google-ecosystem-leaning individuals are well-served by Antigravity. The integrated funnel from AI Studio prototype → Antigravity Desktop → Firebase ship is something Hermes can't reproduce.

The practical answer is both. Let Hermes orchestrate your tacit-thoughts pool dynamically; let Antigravity handle heavy Google-ecosystem dev work.

>6-2Enterprise — three Agent OSes, three contexts

For enterprises, the natural pattern is three Agent OSes split across "business," "dev," and "personal":

Selection is largely "which ecosystem are you anchored in." M365-centric → Copilot Studio. Google-centric → Antigravity + Workspace Studio. Treat business (Workspace/M365) and dev (Antigravity) as separate Agent OSes running together — that is the natural fit.

▍ The FDE / Applied Engineer role

The role of "pulling tacit knowledge / tacit thoughts out of the field and feeding them into the right harness" — across all three Agent OSes — is exactly the FDE / Applied Engineer sweet spot. The end of editor-only work is the same trend as the rise of people who bridge field × AI.

▍ THE WORLDVIEW — what comes after the editor is the Agent OS

"Which model is smarter" is no longer enough — the Agent OS design era is here

The Antigravity 2.0 release marks a turning point in how we compare AI-coding tools. From "comparing models inside editors" to five axes — harness design / permission boundaries / context / scheduling / review — comparing Agent OS designs.

Claude Code / Codex / Grok Build are specialist workers. Antigravity 2.0 / Hermes / Copilot Studio / Workspace Studio are Agent OSes. A "VS" framing across these layers no longer holds. The conversation must shift to within-layer comparison and across-layer composition.

  • Editor-only comparison is a generation behind (raw model strength is commoditising fast)
  • Agent OS design is the new differentiation (harness × permissions × context × scheduling × review)
  • "Orchestrate · supervise · continuously run" is the next battlefield

Individuals: combine Hermes and Antigravity. Enterprises: combine Copilot Studio / Workspace Studio / Antigravity across business, dev, and personal contexts. Productivity is decided not in the editor, but in the Agent OS design. The next phase of AI coding starts here.