Source: https://internal-agents.com/agents/dropbox-nova # Dropbox — Nova Nova is Dropbox's internal service for running coding agents in its cloud. Engineers launch parallel sessions from a web UI, CLI, or API, and internal systems call agents inside automated workflows like CI triage and migrations. Callers attach validation commands that Nova runs after each attempt. > This entry describes supporting infrastructure that other work builds on. The catalog classifies it as a platform. The record also reports a workflow. - Approach type: Platform - Deployment stage: Scaled - Autonomy: Human in loop - Evidence strength: Detailed primary - Status: Internal - First reported year: 2026 - Work: Coding, CI triage, On-call, Maintenance - Interfaces: Web, Cli, Api, Slack - Invocation: Event driven, Interactive - Entry reviewed: 2026-09-15 ## Where people stay involved - **agent-assisted SDLC workflow → accepted change** — Unknown · Level unknown ## Overview ### Summary Nova is Dropbox's internal service for running coding agents in its cloud. Engineers launch parallel sessions from a web UI, CLI, or API, and internal systems call agents inside automated workflows like CI triage and migrations. Callers attach validation commands that Nova runs after each attempt. Fact · Reported · High confidence · `dropbox-nova--summary` Confidence reason: A linked first-party source states the claim. Evidence: - Supports · [1] [Introducing Nova, our internal platform for coding agents](https://dropbox.tech/machine-learning/introducing-nova-our-internal-platform-for-coding-agents) · [Preserved copy](https://github.com/steel-experiments/internal-agents-map/blob/main/archive/sources/dropbox-nova-source-1/content.md) ## How it works ### Supporting component Bounded iteration with feedback on failure; deterministic systems control test execution Fact · Reported · High confidence · `dropbox-nova--primitives-0` Confidence reason: A linked first-party source states the claim. Evidence: - Supports · [1] [Introducing Nova, our internal platform for coding agents](https://dropbox.tech/machine-learning/introducing-nova-our-internal-platform-for-coding-agents) · [Preserved copy](https://github.com/steel-experiments/internal-agents-map/blob/main/archive/sources/dropbox-nova-source-1/content.md) ### Supporting component Dropbox context-engineering system feeding agents across the SDLC Fact · Reported · High confidence · `dropbox-nova--primitives-1` Confidence reason: A linked first-party source states the claim. Evidence: - Supports · [1] [Introducing Nova, our internal platform for coding agents](https://dropbox.tech/machine-learning/introducing-nova-our-internal-platform-for-coding-agents) · [Preserved copy](https://github.com/steel-experiments/internal-agents-map/blob/main/archive/sources/dropbox-nova-source-1/content.md) ## Supervision evidence ### Operating model assessment Unclassified for agent-assisted SDLC workflow → accepted change; human attention boundary: unknown. Inference · Catalog judgment · Unverified confidence · `dropbox-nova--operating-models-0` Confidence reason: The source documents human participation but does not locate one consistent attention boundary across Nova workflows. Qualifications: - Observation date: 2026-05-22 Evidence: - Supports · [1] [Introducing Nova, our internal platform for coding agents](https://dropbox.tech/machine-learning/introducing-nova-our-internal-platform-for-coding-agents) · [Preserved copy](https://github.com/steel-experiments/internal-agents-map/blob/main/archive/sources/dropbox-nova-source-1/content.md) ## Implementation details ### Sandbox Isolated env with a codebase snapshot at a specific commit; full Dropbox monorepo via Bazel; hermetic remote execution + caching Fact · Reported · High confidence · `dropbox-nova--architecture-sandbox` Confidence reason: A linked first-party source states the claim. Evidence: - Supports · [1] [Introducing Nova, our internal platform for coding agents](https://dropbox.tech/machine-learning/introducing-nova-our-internal-platform-for-coding-agents) · [Preserved copy](https://github.com/steel-experiments/internal-agents-map/blob/main/archive/sources/dropbox-nova-source-1/content.md) ### Harness Validation loop (propose → validate → feed back) with continue_on_validation_failure and max_iterations (~5); branch management kept outside the agent Fact · Reported · High confidence · `dropbox-nova--architecture-harness` Confidence reason: A linked first-party source states the claim. Evidence: - Supports · [1] [Introducing Nova, our internal platform for coding agents](https://dropbox.tech/machine-learning/introducing-nova-our-internal-platform-for-coding-agents) · [Preserved copy](https://github.com/steel-experiments/internal-agents-map/blob/main/archive/sources/dropbox-nova-source-1/content.md) ### Model Platform-agnostic; multiple coding agents behind one interface; swap models without rebuilding infra; prompt-eval tooling Fact · Reported · High confidence · `dropbox-nova--architecture-model` Confidence reason: A linked first-party source states the claim. Evidence: - Supports · [1] [Introducing Nova, our internal platform for coding agents](https://dropbox.tech/machine-learning/introducing-nova-our-internal-platform-for-coding-agents) · [Preserved copy](https://github.com/steel-experiments/internal-agents-map/blob/main/archive/sources/dropbox-nova-source-1/content.md) ### Interfaces web, cli, api, slack Fact · Reported · High confidence · `dropbox-nova--architecture-interfaces` Confidence reason: A linked first-party source states the claim. Evidence: - Supports · [1] [Introducing Nova, our internal platform for coding agents](https://dropbox.tech/machine-learning/introducing-nova-our-internal-platform-for-coding-agents) · [Preserved copy](https://github.com/steel-experiments/internal-agents-map/blob/main/archive/sources/dropbox-nova-source-1/content.md) ### Tool access Skills/plugins to gather evidence, read logs, inspect failures; MCP integrations; Bazel-aware selectivity tools Fact · Reported · High confidence · `dropbox-nova--architecture-tool-access` Confidence reason: A linked first-party source states the claim. Evidence: - Supports · [1] [Introducing Nova, our internal platform for coding agents](https://dropbox.tech/machine-learning/introducing-nova-our-internal-platform-for-coding-agents) · [Preserved copy](https://github.com/steel-experiments/internal-agents-map/blob/main/archive/sources/dropbox-nova-source-1/content.md) ### Knowledge Localized AGENTS.md per service; Dash (Dropbox context engineering); passing + failing test logs Fact · Reported · High confidence · `dropbox-nova--architecture-knowledge` Confidence reason: A linked first-party source states the claim. Evidence: - Supports · [1] [Introducing Nova, our internal platform for coding agents](https://dropbox.tech/machine-learning/introducing-nova-our-internal-platform-for-coding-agents) · [Preserved copy](https://github.com/steel-experiments/internal-agents-map/blob/main/archive/sources/dropbox-nova-source-1/content.md) ### Credentials Operates within Dropbox's existing infra and validation paths; same auth/authz as engineers Fact · Reported · High confidence · `dropbox-nova--architecture-credentials` Confidence reason: A linked first-party source states the claim. Evidence: - Supports · [1] [Introducing Nova, our internal platform for coding agents](https://dropbox.tech/machine-learning/introducing-nova-our-internal-platform-for-coding-agents) · [Preserved copy](https://github.com/steel-experiments/internal-agents-map/blob/main/archive/sources/dropbox-nova-source-1/content.md) ### Context management Session history (notes/logs) carried across retry attempts Fact · Reported · High confidence · `dropbox-nova--architecture-context-mgmt` Confidence reason: A linked first-party source states the claim. Evidence: - Supports · [1] [Introducing Nova, our internal platform for coding agents](https://dropbox.tech/machine-learning/introducing-nova-our-internal-platform-for-coding-agents) · [Preserved copy](https://github.com/steel-experiments/internal-agents-map/blob/main/archive/sources/dropbox-nova-source-1/content.md) ## Reported metrics ### Headline claim Dozens of agents can run in parallel from one runbook Metric · Reported · High confidence · `dropbox-nova--headline-metric` Confidence reason: A linked first-party source states the claim. Qualifications: - The source does not report the denominator of this figure. - Reported by: Dropbox - Scope: Migration-owner orchestration of dozens of agents from a shared runbook; qualitative capacity description Evidence: - Supports · [1] [Introducing Nova, our internal platform for coding agents](https://dropbox.tech/machine-learning/introducing-nova-our-internal-platform-for-coding-agents) · [Preserved copy](https://github.com/steel-experiments/internal-agents-map/blob/main/archive/sources/dropbox-nova-source-1/content.md) · Preserved content.md, lines 65–69 ### Key observation Flaky-test remediation (Deflaker): 100+ validation runs Metric · Reported · High confidence · `dropbox-nova--key-metrics-0` Confidence reason: A linked first-party source states the claim. Qualifications: - The source does not report the denominator of this figure. - Reported by: Dropbox - Scope: CI validation runs per proposed Deflaker flaky-test fix - Method: Run the test 100 or more times depending on its failure rate; retry capped at five fix attempts Evidence: - Supports · [1] [Introducing Nova, our internal platform for coding agents](https://dropbox.tech/machine-learning/introducing-nova-our-internal-platform-for-coding-agents) · [Preserved copy](https://github.com/steel-experiments/internal-agents-map/blob/main/archive/sources/dropbox-nova-source-1/content.md) · Preserved content.md, lines 58–62 ### Key observation Predecessor Goose-based migrator used across thousands of migration entries before workflows moved onto Nova Metric · Reported · High confidence · `dropbox-nova--key-metrics-1` Confidence reason: A linked first-party source states the claim. Qualifications: - The source does not report the denominator of this figure. - Reported by: Dropbox - Scope: Predecessor Goose-based migrator, before workflows moved onto Nova Evidence: - Supports · [1] [Introducing Nova, our internal platform for coding agents](https://dropbox.tech/machine-learning/introducing-nova-our-internal-platform-for-coding-agents) · [Preserved copy](https://github.com/steel-experiments/internal-agents-map/blob/main/archive/sources/dropbox-nova-source-1/content.md) · Preserved content.md, lines 65–69 ### Key observation Dozens of agents launchable from one runbook Metric · Reported · High confidence · `dropbox-nova--key-metrics-2` Confidence reason: A linked first-party source states the claim. Qualifications: - The source does not report the denominator of this figure. - Reported by: Dropbox - Scope: Migration-owner orchestration of dozens of agents from a shared runbook; qualitative capacity description Evidence: - Supports · [1] [Introducing Nova, our internal platform for coding agents](https://dropbox.tech/machine-learning/introducing-nova-our-internal-platform-for-coding-agents) · [Preserved copy](https://github.com/steel-experiments/internal-agents-map/blob/main/archive/sources/dropbox-nova-source-1/content.md) · Preserved content.md, lines 65–69 ## Lessons and interpretation ### Lesson Platform value exceeds code generation; validation, guardrails, and context matter as much Inference · Catalog judgment · Medium confidence · `dropbox-nova--lessons-learned-0` Confidence reason: The catalog derives this observation from the linked sources. Evidence: - Supports · [1] [Introducing Nova, our internal platform for coding agents](https://dropbox.tech/machine-learning/introducing-nova-our-internal-platform-for-coding-agents) · [Preserved copy](https://github.com/steel-experiments/internal-agents-map/blob/main/archive/sources/dropbox-nova-source-1/content.md) ### Lesson Context, validation, and guardrails reinforce each other to make background work trustworthy Inference · Catalog judgment · Medium confidence · `dropbox-nova--lessons-learned-1` Confidence reason: The catalog derives this observation from the linked sources. Evidence: - Supports · [1] [Introducing Nova, our internal platform for coding agents](https://dropbox.tech/machine-learning/introducing-nova-our-internal-platform-for-coding-agents) · [Preserved copy](https://github.com/steel-experiments/internal-agents-map/blob/main/archive/sources/dropbox-nova-source-1/content.md) ### Lesson Not every step belongs in the agent loop; deterministic systems should control test execution and timing Inference · Catalog judgment · Medium confidence · `dropbox-nova--lessons-learned-2` Confidence reason: The catalog derives this observation from the linked sources. Evidence: - Supports · [1] [Introducing Nova, our internal platform for coding agents](https://dropbox.tech/machine-learning/introducing-nova-our-internal-platform-for-coding-agents) · [Preserved copy](https://github.com/steel-experiments/internal-agents-map/blob/main/archive/sources/dropbox-nova-source-1/content.md) ### Lesson Integrate with existing engineering infrastructure rather than building separate AI-specific workflows Inference · Catalog judgment · Medium confidence · `dropbox-nova--lessons-learned-3` Confidence reason: The catalog derives this observation from the linked sources. Evidence: - Supports · [1] [Introducing Nova, our internal platform for coding agents](https://dropbox.tech/machine-learning/introducing-nova-our-internal-platform-for-coding-agents) · [Preserved copy](https://github.com/steel-experiments/internal-agents-map/blob/main/archive/sources/dropbox-nova-source-1/content.md) ## Sources 1. [Introducing Nova, our internal platform for coding agents](https://dropbox.tech/machine-learning/introducing-nova-our-internal-platform-for-coding-agents) - Engineering blog · First party · Evidence - Original URL: - Accessed: 2026-08-12 · Last verified: 2026-08-31 - Preserved copy in the repository: 2. [Hacker News submission for Nova](https://news.ycombinator.com/item?id=48235065) - Hn thread · Community · Discovery - Original URL: - Published: 2026-05-22 · Accessed: 2026-08-12 · Last verified: 2026-08-31 - Preserved copy in the repository: