Pick the AI tool you use below and follow the steps — usually a button or one line. Once connected, every tool reads the same current state and leaves a note when it's done, so the next one picks up where the last left off.
https://harkstudio.io/mcp
Sign in to Hark to connect a client. Personal tokens and per-account details live inside the app.
Let the agent read your project and file the first project for you.
Already deep in a project? Don't fill anything in by hand. Point your connected agent at the code and let it hand Hark the first project — then keep the one thing it can't know.
Read this project, then call propose_venture_from_project with a proposed project (title, one-liner, problem, solution, target market) and the build_state as it actually stands (current phase, summary, in progress, next up, blockers, open questions), plus every decision you can see with its rationale. Then ask me for one constraint or decision that only Hark should know — something not visible in the code — and record it with add_journal_entry as a decision.
One tool call creates the project, its business fields, its Current state and its decisions, and returns the new V-### code.
The getting-started card ticks this step off by itself as soon as a brief read arrives from a second client or a fresh session.
Ask your client: "List my Hark workspaces." Expected: your workspace names.
Then: "Create a project called Connection test in <workspace>." Expected: a new V-### appears in the app and the activity log shows the source ("via Claude Code", "via Codex", etc.). Delete the test venture afterward.