Boost deep reasoning (/boost)
Section titled “Boost deep reasoning (/boost)”The /boost slash command activates an on-demand multi-agent reasoning
pipeline designed for challenging software engineering tasks. When standard
single-turn coding assistance falls short on complex bugs, race conditions, or
intricate refactoring, /boost breaks down the problem, delegates focused
workstreams to specialized subagents, and independently verifies solutions
across iterative rounds.
Overview
Section titled “Overview”Modern software development involves problems spanning a wide spectrum of complexity:
- Everyday engineering: Interactive feature development, codebase navigation, refactoring, and general programming workflows where speed and versatility shine.
- Deep reasoning tasks: High-difficulty concurrency bugs, algorithmic optimization, subtle regressions, and multi-file architecture puzzles that benefit from multi-agent exploration and iterative verification.
- Long-horizon campaigns: Repository-scale migrations, large subsystem builds, and multi-day exploratory research.
/boost addresses the crucial middle ground: interactive, high-intensity
developer productivity. It delivers multi-agent deep reasoning directly
within your day-to-day coding sessions without requiring complex setup or
prolonged scoping interviews.
How Boost works
Section titled “How Boost works”When you invoke /boost, Antigravity initiates a three-phase multi-agent
reasoning pipeline that decouples strategy formulation from isolated execution
and verification:
Phase 1: Goal & strategy formulation
Section titled “Phase 1: Goal & strategy formulation”The Primary Orchestrator receives your prompt, inspects workspace context, and formulates an execution strategy. It breaks down complex engineering challenges into discrete, verifiable subtasks and determines which specialized workstreams are required.
Phase 2: Parallel execution & verification
Section titled “Phase 2: Parallel execution & verification”The Orchestrator dispatches focused subtasks to specialized subagents operating in clean, isolated scopes:
- Implementation workstreams: Construct candidate code solutions, apply refactoring, and generate unit tests.
- Investigation workstreams: Perform root-cause debugging, trace execution call graphs, and analyze unfamiliar dependencies without modifying files.
- Local verification: Subagents execute build targets and test suites locally to validate hypotheses before reporting results.
Phase 3: Synthesis & delivery
Section titled “Phase 3: Synthesis & delivery”Before presenting the final outcome, the reasoning pipeline aggregates findings and runs regression checks:
- The Orchestrator validates the combined solution against full test suites and edge cases.
- If an assertion fails, error diagnostics are fed back into the next iteration for automated correction.
- Once all tests and requirements pass, a concise summary with verified changes is delivered.
When to use /boost
Section titled “When to use /boost”The following table compares the three primary execution modes in Antigravity:
| Dimension | Default Agent | 🚀 Boost (/boost) | 👥 Teamwork (/teamwork-preview) |
|---|---|---|---|
| Primary focus |