Iterate

After turn 1 you have a running app. Iteration is everything that comes after, and it’s where most of the work in Vibely happens. This page covers the three modes of iteration, the prompt shapes that hold up over long sessions, and what to do when the agent gets stuck. For deeper coverage of multi-turn habits, see Tips → Iterating.

​

Three iteration modes

​

Build mode (default)

You prompt; the agent reads, plans, writes, hot-reloads. Use it for anything that touches code: features, refactors, bug fixes, design changes, schema updates. This is what 95% of your turns are.

​

Plan mode

Plan mode is read-only — the agent can search, read files, browse, and reason, but it can’t write. Use it before any change you want a second opinion on.

“We’re about to add multi-tenancy. Read the auth and DB code and tell me what would have to change. Don’t write anything yet.”

The agent researches and responds with a plan. When the plan is right, prompt “go ahead and implement that” and the full toolset unlocks. Plan mode is the cheapest way to avoid five-turn rabbit holes on big changes.

​

Visual edits

Click any element in the preview, type a change (“make this button bigger”, “use the brand purple here”). The agent patches just that element — no re-think of the design system, no unrelated changes. The visual-edit panel covers more than just text. The same surface gives you direct controls for:

• Color — recolour an element or its descendants without typing a prompt.
• Link — set or change an href, including for navigation items.
• Media — swap an image or video for an upload or a URL.
• Spacing — adjust margin and padding visually instead of guessing values.
• Typography — change font family, weight, size on a single element.

Best for: design tweaks, copy edits, spacing adjustments, brand alignment.

​

AI image modal

In the visual-edit panel, the AI image action lets you generate an image inline. Describe what you want; Vibely produces it; click to drop the result in place of the current image. Useful for hero shots, illustration placeholders, and content visuals you don’t want to leave the project to source.

​

Prompt queue

Don’t wait for the agent to finish a turn before lining up the next instruction. The composer has a prompt queue — type and send while the agent is still working, and Vibely queues your message to run as soon as the current turn ends. Queue order is FIFO. You can drag to reorder, edit, or cancel queued prompts before they fire. This is the right way to chain dependent changes — “do A, then do B once that’s done” — without baby-sitting the chat.

​

Draw on the preview

The preview has a draw overlay. Click the brush, scribble on the rendered page to highlight a specific area, and send. Vibely captures the annotated screenshot as a PNG and attaches it to the next prompt. Use this for changes that are easier to point at than describe: “this row, make it wider”, “this thing here is broken on mobile”, “align these three to the same baseline.”

​

Comments mode

When you want feedback to stick around — across turns, across collaborators — switch to Comments instead. Comments pin to the preview, support threads and mentions, and can be turned into prompts with one click. See Comments.

​

Shape your prompts to the change

The shape signals the agent how much latitude it has. Surgical edits get surgical responses; broad asks get broad ones.

​

When the agent gets stuck

• Re-read the brief. Half the time a stuck agent is acting on an outdated assumption from earlier in the chat. A two-line restatement of what you actually want resets it cheaply.
• Switch to Plan Mode. If the agent keeps making the same wrong edit, “Switch to Plan Mode and figure out what’s actually causing X” gets you a research turn instead of another doomed attempt.
• Ask the agent to clarify. If it’s guessing instead of asking, prompt: “If you’re uncertain about X, ask me — don’t guess.” Save it to memory so you never have to type it again.
• Restart the runtime. If the preview is wedged, hit Restart in the project menu — files are preserved, the runtime is rebuilt fresh.

​

Memory across turns

Long chats get compacted — older messages summarised to make room. Memory is what survives. Memory is a small file (.vibely/memory.md) that lives with your project and is read back at the top of every compacted block. Use it for facts you don’t want the agent to forget mid-session:

“Save to memory: this is a B2B app, never use any consumer-style copy. Always require login.”

See Tips → Memory for what belongs there and what doesn’t.

​

When to start over

Sometimes the cheapest path forward is a new chat. Heuristics:

• The chat is 100+ turns and the agent is making contradictory decisions
• You’ve changed the brief substantially since turn 1 (e.g. CRM → CMS)
• You want to try a fundamentally different stack (Next.js instead of Vite)
• The architecture you ended up with isn’t the one you’d have asked for

Starting over does not lose your work — your files are stored safely. A new session restores them. What you lose is the chat context, which by that point is more confusing than helpful. Before starting over, ask:

“Summarise the lessons from this session in 5–10 bullet points I can paste into a new chat.”

​

Next