This article is published in English.
Practical notes: Orchestrating with Antigravity: A Crescendo of Agents (Part 2)
Operable walkthrough of Practical notes: Orchestrating with Antigravity: A Crescendo of Agents (Part 2): contracts, checks, and drop-in code slots for teams shipping this pattern.
The following notes reconstruct a practical path around “Orchestrating with Antigravity: A Crescendo of Agents (Part 2)”. Emphasis stays on contracts, checks, and drop-in code placeholders rather than motivational framing. When working through the Overview stage, write down the contract first: required inputs, success signal, and what happens on partial failure. That checklist keeps later code changes honest. Document the happy path and the recovery path together. Retries, human gates, and dead-letter handling are part of the product, not later polish.
Parallel coding with git worktrees, Conductor++, and.. Agostina!
The Parallel coding with git stage works best when treated as a measurable surface. Capture one golden transcript, one failure case, and the rollback note before expanding scope. Prefer small, testable units over sprawling scripts. When a step fails, the failure should point at a single responsibility rather than a tangled pipeline. Keep graph state flat and typed. Nested blobs hide which node wrote which field and break resume after interrupts.
When it hit me
The When it hit me stage works best when treated as a measurable surface. Capture one golden transcript, one failure case, and the rollback note before expanding scope. Treat this stage as a contract between inputs and validated outputs. Name the artifacts, define success checks, and refuse silent partial completion. Keep graph state flat and typed. Nested blobs hide which node wrote which field and break resume after interrupts.
Let's build a hotel room booking app [..].
First, launch the Engineering Manager agent to ... into an artifact called 'architecture.md'.
Once the design is ready, launch three agents in parallel:
1. Test Manager: Write <SPECS> to 'architecture.md'.
2. Backend Engineer: Build an API based on <SPECS> .
3. Frontend Engineer: Build a web UI based on <SPECS> to interact with the API <details>.
[..] How to sync the 3 sub-agents [..]
Finally, spin up both components and a browser so I can test the live app.
Conductor++ stack: the “condutree” skill
The Conductor stack the condutree stage works best when treated as a measurable surface. Capture one golden transcript, one failure case, and the rollback note before expanding scope. Record timings and token or query cost next to functional results. Cost visibility early prevents surprise bills when the path moves from demo to shared environments. Keep graph state flat and typed. Nested blobs hide which node wrote which field and break resume after interrupts. The Conductor stack the condutree stage works best when treated as a measurable surface. Capture one golden transcript, one failure case, and the rollback note before expanding scope. Document the happy path and the recovery path together. Retries, human gates, and dead-letter handling are part of the product, not later polish.
Scaling up: Conductor++ multi-worktree multi-agent dev flow
For the Scaling up Conductor multi-worktree stage, define the inputs, the owner of the step, and the exit criteria before changing code. Operators should be able to re-run the step from a known checkpoint without guessing hidden state. Prefer small, testable units over sprawling scripts. When a step fails, the failure should point at a single responsibility rather than a tangled pipeline. Put human approval on edges that spend money or change production data. Compile-time wiring does not equal business completeness.
1. The preparation
For the 1 The preparation stage, define the inputs, the owner of the step, and the exit criteria before changing code. Operators should be able to re-run the step from a known checkpoint without guessing hidden state. Treat this stage as a contract between inputs and validated outputs. Name the artifacts, define success checks, and refuse silent partial completion. Put human approval on edges that spend money or change production data. Compile-time wiring does not equal business completeness.
2. The logic: parallelism without the chaos
For the 2 The logic parallelism stage, define the inputs, the owner of the step, and the exit criteria before changing code. Operators should be able to re-run the step from a known checkpoint without guessing hidden state. Record timings and token or query cost next to functional results. Cost visibility early prevents surprise bills when the path moves from demo to shared environments. Put human approval on edges that spend money or change production data. Compile-time wiring does not equal business completeness. For the 2 The logic parallelism stage, define the inputs, the owner of the step, and the exit criteria before changing code. Operators should be able to re-run the step from a known checkpoint without guessing hidden state. Document the happy path and the recovery path together. Retries, human gates, and dead-letter handling are part of the product, not later polish.
3. The execution: orchestration lifecycle
When working through the 3 The execution orchestration stage, write down the contract first: required inputs, success signal, and what happens on partial failure. That checklist keeps later code changes honest. Prefer small, testable units over sprawling scripts. When a step fails, the failure should point at a single responsibility rather than a tangled pipeline. Checkpoint after expensive steps. Resume should not re-bill the same LLM call when an operator retries a later node.
Case study: Project Benjamin (SRE on ADK steroids)
When working through the Case study SRE on stage, write down the contract first: required inputs, success signal, and what happens on partial failure. That checklist keeps later code changes honest. Treat this stage as a contract between inputs and validated outputs. Name the artifacts, define success checks, and refuse silent partial completion. Checkpoint after expensive steps. Resume should not re-bill the same LLM call when an operator retries a later node.
Integration & merge results
When working through the Integration merge results stage, write down the contract first: required inputs, success signal, and what happens on partial failure. That checklist keeps later code changes honest. Record timings and token or query cost next to functional results. Cost visibility early prevents surprise bills when the path moves from demo to shared environments. Checkpoint after expensive steps. Resume should not re-bill the same LLM call when an operator retries a later node. When working through the Integration merge results stage, write down the contract first: required inputs, success signal, and what happens on partial failure. That checklist keeps later code changes honest. Document the happy path and the recovery path together. Retries, human gates, and dead-letter handling are part of the product, not later polish.
$ just conductor-status
python3 conductor/bin/conductor-inspector . --open --short
🔍 Inspecting Conductor Workspace: /usr/local/google/home/ricc/git/adk-sre-benjamin
📦 Product: Initial Concept
STATUS | PROGRESS | RATIO | GHI | AGENT | CHANGED | TRACK ID | 🌳
==============================================================================================================================
NEW | ░░░░░░░░░░ | 0/25 | #23 | | 💻 15days | managed_agents_sandbox_20260616 |
NOT_READY | ░░░░░░░░░░ | 0/17 | #22 | | 💻 15days | mcp_streamline_abilities_20260616 |
NOT_READY | ░░░░░░░░░░ | 0/11 | #15 | | 💻 15days | migrate_tf_cb_logic_20260616 |
NOT_READY | ░░░░░░░░░░ | 0/9 | #21 | | 💻 15days | ai_engineering_practices_20260616 |
NOT_READY | ░░░░░░░░░░ | 0/9 | #19 | | 💻 15days | workspace_agent_installation_20260616 |
NEW | ░░░░░░░░░░ | 0/15 | #31 | antigravity| 🐙 16days | disable_mock_fallback_dev_20260616 |
==============================================================================================================================
TOTAL | | 0/86 | | | | 0 completed, 6 open (6 total) | 0 🌳
The workflow timeline (visual audit)
The The workflow timeline visual stage works best when treated as a measurable surface. Capture one golden transcript, one failure case, and the rollback note before expanding scope. Prefer small, testable units over sprawling scripts. When a step fails, the failure should point at a single responsibility rather than a tangled pipeline. Keep graph state flat and typed. Nested blobs hide which node wrote which field and break resume after interrupts.
Step 1: Initializing SRE tracks & worktrees
The Step 1 Initializing SRE stage works best when treated as a measurable surface. Capture one golden transcript, one failure case, and the rollback note before expanding scope. Treat this stage as a contract between inputs and validated outputs. Name the artifacts, define success checks, and refuse silent partial completion. Keep graph state flat and typed. Nested blobs hide which node wrote which field and break resume after interrupts.
./scripts/conductor-inspector /Users/ricc/git/adk-sre-benjamin --all
================================================================================
CONDUCTOR++ ACTIVE WORKTREES & TRACKS INSPECTION
================================================================================
[Track: telegram_incident_creation_20260603]
Worktree: .worktrees/issue-29-telegram-wizard
Branch: feature/issue-29
Agent: pinocchio
Status: AWAITING_HUMAN (Question: "Verify Telegram Token config?")
GHI URL: https://github.com/palladius/adk-sre-benjamin/issues/29
[Track: unified_incident_lifecycle_observability_20260607]
Worktree: .worktrees/issue-18-discord-warrooms
Branch: feature/issue-18
Agent: grazia
Status: RUNNING
GHI URL: https://github.com/palladius/adk-sre-benjamin/issues/18
================================================================================
Wait, the author, are GHI and Conductor tracks the same?
The Wait the author are GHI stage works best when treated as a measurable surface. Capture one golden transcript, one failure case, and the rollback note before expanding scope. Record timings and token or query cost next to functional results. Cost visibility early prevents surprise bills when the path moves from demo to shared environments. Keep graph state flat and typed. Nested blobs hide which node wrote which field and break resume after interrupts. The Wait the author are GHI stage works best when treated as a measurable surface. Capture one golden transcript, one failure case, and the rollback note before expanding scope. Document the happy path and the recovery path together. Retries, human gates, and dead-letter handling are part of the product, not later polish.
Step 2: Parallel worktree isolations
For the Step 2 Parallel worktree stage, define the inputs, the owner of the step, and the exit criteria before changing code. Operators should be able to re-run the step from a known checkpoint without guessing hidden state. Prefer small, testable units over sprawling scripts. When a step fails, the failure should point at a single responsibility rather than a tangled pipeline. Put human approval on edges that spend money or change production data. Compile-time wiring does not equal business completeness.
Step 3: Interactive polling & human steering
For the Step 3 Interactive polling stage, define the inputs, the owner of the step, and the exit criteria before changing code. Operators should be able to re-run the step from a known checkpoint without guessing hidden state. Treat this stage as a contract between inputs and validated outputs. Name the artifacts, define success checks, and refuse silent partial completion. Put human approval on edges that spend money or change production data. Compile-time wiring does not equal business completeness.
Step 4: The final green state
For the Step 4 The final stage, define the inputs, the owner of the step, and the exit criteria before changing code. Operators should be able to re-run the step from a known checkpoint without guessing hidden state. Record timings and token or query cost next to functional results. Cost visibility early prevents surprise bills when the path moves from demo to shared environments. Put human approval on edges that spend money or change production data. Compile-time wiring does not equal business completeness. For the Step 4 The final stage, define the inputs, the owner of the step, and the exit criteria before changing code. Operators should be able to re-run the step from a known checkpoint without guessing hidden state. Document the happy path and the recovery path together. Retries, human gates, and dead-letter handling are part of the product, not later polish.
Lessons learned & key takeaways
When working through the Lessons learned key takeaways stage, write down the contract first: required inputs, success signal, and what happens on partial failure. That checklist keeps later code changes honest. Prefer small, testable units over sprawling scripts. When a step fails, the failure should point at a single responsibility rather than a tangled pipeline. Checkpoint after expensive steps. Resume should not re-bill the same LLM call when an operator retries a later node.
Now, try It Yourself!
When working through the Now try It Yourself stage, write down the contract first: required inputs, success signal, and what happens on partial failure. That checklist keeps later code changes honest. Treat this stage as a contract between inputs and validated outputs. Name the artifacts, define success checks, and refuse silent partial completion. Checkpoint after expensive steps. Resume should not re-bill the same LLM call when an operator retries a later node.
Operational checklist
For the Operational checklist stage, define the inputs, the owner of the step, and the exit criteria before changing code. Operators should be able to re-run the step from a known checkpoint without guessing hidden state.
Keep configuration outside application code. Environment files, secret stores, and feature flags belong in one place operators can audit without reading the whole graph.
Put human approval on edges that spend money or change production data. Compile-time wiring does not equal business completeness.
Write a short runbook: how to rotate keys, how to drain the queue, how to roll back the last ingest.
Document the happy path and the recovery path together. Retries, human gates, and dead-letter handling are part of the product, not later polish.
Put human approval on edges that spend money or change production data. Compile-time wiring does not equal business completeness.
Before promoting the stack, freeze versions, capture a golden transcript for the critical path, and confirm rollback steps. Shared environments need rate limits, tenancy checks, and a clear owner for secret rotation. Prefer boring reliability over clever one-off demos.
Batch note for ea39e3715506: keep provider keys out of the repo, set a per-session token ceiling, and store transcripts next to the eval fixtures so later model swaps stay comparable.
The hardening note 0 stage works best when treated as a measurable surface. Capture one golden transcript, one failure case, and the rollback note before expanding scope. Keep configuration outside application code. Environment files, secret stores, and feature flags belong in one place operators can audit without reading the whole graph.
Hardening detail 0/770: measure wall time, error class, and token spend for this note, then decide whether to keep the change based on a fixed question set rather than anecdote.
For the hardening note 1 stage, define the inputs, the owner of the step, and the exit criteria before changing code. Operators should be able to re-run the step from a known checkpoint without guessing hidden state. Prefer small, testable units over sprawling scripts. When a step fails, the failure should point at a single responsibility rather than a tangled pipeline.
Hardening detail 1/770: measure wall time, error class, and token spend for this note, then decide whether to keep the change based on a fixed question set rather than anecdote.
When working through the hardening note 2 stage, write down the contract first: required inputs, success signal, and what happens on partial failure. That checklist keeps later code changes honest. Record timings and token or query cost next to functional results. Cost visibility early prevents surprise bills when the path moves from demo to shared environments.
Hardening detail 2/770: measure wall time, error class, and token spend for this note, then decide whether to keep the change based on a fixed question set rather than anecdote.
The hardening note 3 stage works best when treated as a measurable surface. Capture one golden transcript, one failure case, and the rollback note before expanding scope. Document the happy path and the recovery path together. Retries, human gates, and dead-letter handling are part of the product, not later polish.
Hardening detail 3/770: measure wall time, error class, and token spend for this note, then decide whether to keep the change based on a fixed question set rather than anecdote.
For the hardening note 4 stage, define the inputs, the owner of the step, and the exit criteria before changing code. Operators should be able to re-run the step from a known checkpoint without guessing hidden state. Treat this stage as a contract between inputs and validated outputs. Name the artifacts, define success checks, and refuse silent partial completion.
Hardening detail 4/770: measure wall time, error class, and token spend for this note, then decide whether to keep the change based on a fixed question set rather than anecdote.
When working through the hardening note 5 stage, write down the contract first: required inputs, success signal, and what happens on partial failure. That checklist keeps later code changes honest. Keep configuration outside application code. Environment files, secret stores, and feature flags belong in one place operators can audit without reading the whole graph.
Hardening detail 5/770: measure wall time, error class, and token spend for this note, then decide whether to keep the change based on a fixed question set rather than anecdote.
For the hardening note 0 stage, define the inputs, the owner of the step, and the exit criteria before changing code. Operators should be able to re-run the step from a known checkpoint without guessing hidden state. Treat this stage as a contract between inputs and validated outputs. Name the artifacts, define success checks, and refuse silent partial completion.
Hardening detail 0/789: measure wall time, error class, and token spend for this note, then decide whether to keep the change based on a fixed question set rather than anecdote.
When working through the hardening note 1 stage, write down the contract first: required inputs, success signal, and what happens on partial failure. That checklist keeps later code changes honest. Keep configuration outside application code. Environment files, secret stores, and feature flags belong in one place operators can audit without reading the whole graph.
Hardening detail 1/789: measure wall time, error class, and token spend for this note, then decide whether to keep the change based on a fixed question set rather than anecdote.