What happens between a goal and a result

Plain language, the way you would say it out loud. Optionally add a deadline, a budget, the time you have, a success metric, restrictions and resources you already own.

"Get three clients for my web agency in seven days without spending money."

Only questions whose answers would change the plan. Each one comes with a control — a choice, a slider, a date — and a line explaining why it matters. Never a long form.

What proof of past work can you point to? · How much time each week? · Anything Parallel must not do?

Parallel states what it understands, what constrains the goal, which routes exist, which one it recommends and which ones it is rejecting — with the reason for each.

Understanding the goal → reviewing constraints → exploring paths → identifying bottlenecks → designing the system

Not three options to choose between. One route, broken into day-anchored stages and measurable steps, with milestones, risks, assumptions, what it needs from you and what agents will handle.

Edit any step, change the deadline, remove work, add work, or ask Parallel to regenerate a section.

Pressing the button generates a custom agent team from the plan. Each agent gets a name, a role, an objective, tools, required inputs, a schedule, success metrics and a permission level.

Card view for detail, node map for how they collaborate. Edit, pause, delete or add agents at any time.

Before activation, confirm what agents may do automatically, what must be approved, and what is prohibited outright. Credentials are never displayed again once saved.

Automatic: research, analysis, drafting. Approval: sending, publishing, contacting, spending. Prohibited: whatever you disable.

Agents work through the schedule and produce deliverables. Anything consequential arrives in Approvals with the proposed action, the reason, the expected effect, the risks and a full preview.

Every run produces a log. Simulated work is labelled as simulated.

Planned against actual, every day. When results diverge, Parallel names the assumption that broke and changes the smallest thing that could fix it — then tells you what it changed and why.

At the end: a full report, the lesson, and a recommended follow-on mission.