ANTIGRAVITY LABJP
TAG

agent design

14 articles
Back to all tags
Related:
Antigravity12Multi-Agent3unattended ops2Workflow2AgentKit 2.02multi-agent2Manager Surface2Antigravity CLI1codesearch1regex1search design1regression testing1
Agents/2026-07-18Advanced

Treating Code Search as a Contract: Measuring the /codesearch Regex Default

Antigravity CLI 1.1.3 interprets /codesearch queries as regular expressions by default. I measured the gap between regex and literal matching across a 979-article repository and turned the results into three query rules and a drift harness.

Agents/2026-07-14Advanced

I Changed One Line in AGENTS.md and Broke the Agent — Regression-Testing the Instructions Themselves

Every time you edit the instructions you hand an agent — AGENTS.md, skill text — some other task quietly breaks. Here is a regression harness whose subject is the instructions, not the code: fixed tasks, deterministic assertions, and a way to wire it into unattended runs.

Editor/2026-07-02Advanced

Handing Off IDE Work to the Chat Agent: Passing Context Through a File After the Two-App Split

Since Antigravity 2.0 split into an IDE and a chat-style agent app, context you build up in one does not carry into the other. Here is a file-based approach that makes a single file in your repo the source of truth for handoff, with a schema, a validation script, and a way to pin it with a Guide skill.

Editor/2026-07-01Advanced

Faster Substring Search Changes How You Should Let Agents Explore Code

The 6/26 update made substring search noticeably faster. Rather than treating it as a comfort improvement, here is how to redesign the way agents explore code, budget context, and verify their targets, with measurements from indie development.

App Dev/2026-06-30Advanced

Running Xcode 27's Agent and Antigravity Side by Side: Designing the Work Boundary for iOS

With Xcode 27 bringing agentic coding into the IDE itself, iOS development now has two code-writing agents over one repository. Here is a practical design for keeping a single source of truth and splitting work across spec, implementation, and verification.

Agents/2026-06-15Advanced

Stop Letting Antigravity Agents Self-Report 'Done' — Completion Contracts and External Verification

An Antigravity agent reporting 'done' when the work was not actually finished is a failure mode I kept hitting. Moving the completion decision out of the agent and into code fixed it. Here is the contract, a three-layer verifier, and how it holds up under unattended, scheduled runs.

Agents/2026-05-06Advanced

Giving AI Agents an Aesthetic Sense — Building a UI Quality Evaluation Pipeline with Antigravity × Gemini Vision

Explore how to encode the vague judgment of 'is this UI good or bad' into code. Combines Antigravity with Gemini Vision to implement a complete pipeline — from screenshot capture to AI evaluation, improvement suggestions, automated fixes, and CI/CD integration.

Agents/2026-05-04Intermediate

Designing Antigravity's Architect / Builder Mathematically — Agent Design Through the Lens of Search, Classification, and Inference

Antigravity's Architect/Builder split looks suspiciously like the math behind search engines and classifiers. Here is a way to think about agent design using the language of weighting, candidate pruning, and probability — for more stable, reproducible agents.

Agents/2026-04-27Advanced

Building Multi-Agent Systems with AgentKit 2.0 in Antigravity — A Production Implementation Guide

AgentKit 2.0 dropped the barrier to multi-agent systems sharply. After implementing three different agent-coordination patterns in Antigravity, here's the design playbook covering decisions, traps, and production operation.

Agents/2026-04-24Intermediate

Implementing Antigravity's A2A Protocol — Practical Patterns for Agent-to-Agent Conversation

A hands-on guide to Antigravity's A2A (Agent-to-Agent) protocol. Walks through the minimal two-agent setup and three real-world patterns — fire-and-forget, bidirectional confirmation, and scatter-gather — with runnable samples.

Agents/2026-04-23Advanced

Production Multi-Agent Systems with Antigravity AgentKit 2.0: Patterns, Failure Modes, and What the Demos Don't Show

AgentKit 2.0 makes multi-agent systems look effortless in demos, but running them in production is a different problem. This guide covers Planning vs. Fast mode, three real orchestration patterns, and the failure modes — infinite loops, cost blowouts, prompt injection — that bite on day one.

Agents/2026-04-09Advanced

Building a Multi-Agent System in Antigravity — Manager Surface, Role Delegation, and Gemma 4

One agent trying to do everything hits a ceiling. Designing and implementing multi-agent systems on Antigravity's Manager Surface: role delegation, three architectural patterns, and pairing with Gemma 4.