Harvey's internal collaborative cloud agent platform; turns requests from Slack, the web app, or automations into durable runs that return reviewable summaries, diffs, branches, and PRs.
Explicit tool boundaries; tool configuration injected at run start; requests start from Slack, the web app, or automations; connects to systems like GitHub, Datadog, and Linear[Source 1]
Knowledge
Not reportedNo knowledge store for Spectre runs is documented; the SOC's memory system belongs to the separate security platform.
Context management
Durable runs over disposable execution environments[Source 1]
Credentials
Short-lived, scoped credentials injected at run start; no ambient access to the control plane or a user's machine[Source 1]
Interfaces
The CLI joins Slack, the web app, and automations as a surface over the same durable run.
Cron-based automations materialize ordinary runs for cleanup passes, test generation, dependency checks, and verification loops[Source 1]
Adoption and operating evidence
Not reported: The platform post reports no measured outcomes. The security article's figures describe the separate agentic SOC, which runs on its own infrastructure by design.
Lessons
Spectre returns branches, diffs, summaries, and run history so another person can inspect or continue the work.[Source 1]
Reported opinion: Harvey identifies coordination, ownership, and retained context as challenges when many people and agents share work.[Source 1]
Reported opinion: Harvey keeps Spectre and its security agents on separate infrastructure to limit the consequences of a compromised product agent.[Source 2]
Reported: The named run is the first-version flow the post documents: create a run, start a fresh sandbox, hydrate the repository, run the agent, stream output, persist artifacts.
human involvement
Not applicable: There is no single platform-wide agent review boundary. Scoped downstream operating-model claims remain in research details; access controls are described separately.
implementation
Reported
validation
Reported: Verification loops run as scheduled ordinary runs; the post documents no separate check inside an interactive run beyond the review boundary.
observations
Not reported: The platform post reports no measured outcomes. The security article's figures describe the separate agentic SOC, which runs on its own infrastructure by design.
The security article explains that sharing detection knowledge and investigation memory would expose information valuable to an attacker; this is Harvey's design rationale.
