Plan mode

Plan mode is a toggle on the chat composer. With it on, the in-app assistant writes a short prose plan before doing anything, and you see that plan in a card with two buttons: Approve & run and Abort. This page describes how to turn plan mode on, what the card shows, and when it earns its keep.

Why plan mode exists

Complex workspace operations — setting up a new study, triaging a result batch, importing a CSV and wiring it into a document — are not a single tool call. They require the assistant to first understand its surroundings (which environments and tables exist, which protocol the user means, what the relevant document already contains, what tools are available for the job) and then choose a coherent sequence of actions that gets to the result. Plan mode is the dedicated step where that grounding and sequencing happen.

During planning the assistant searches the wiki, reads relevant workspace documents, checks the tool catalogue, and drafts the steps it intends to run. The plan then surfaces in a card with Approve & run and Abort buttons — so you can intervene on the shape of the answer once instead of correcting tool calls twelve times. The card is a consequence of planning, not its motivation: plan mode is primarily how the model thinks through a complex request, and only secondarily a confirmation surface.

Turning plan mode on

Click the Plan pill next to the composer, beside the Think pill. It is off by default, and the setting is remembered per model, so a chat opened on the same model comes back with plan mode where you left it. With the pill off, the assistant answers and acts directly and no plan card appears.

Turn it on when the request is more than a lookup:

• "What does our IFN-γ protocol look like?" is a direct answer. Leave it off.
• "Search the wiki for the column-type cheat sheet." is a direct answer. Leave it off.
• "Set up a PK study schema for DLA-7 and import the dose groups CSV." is worth planning.
• "Triage these 40 result rows: flag any with CV > 15% and write a summary block at the bottom of the doc." is worth planning.

You can also just ask the assistant to draft a plan without executing, in any mode.

What the plan card shows

The card has a header (the word Plan, a status badge like Needs approval / Executing / Done, and a rev N chip when the assistant revised an earlier draft of the plan), followed by the plan content itself:

Plan body

Markdown: a leading prose sentence stating the approach, then a few numbered or bulleted steps. References specific tools where relevant ("call data_objects_write with action bulk_create and the parsed CSV") and specific resources by name.

Plan envelope

Optional collapsible sections that scaffold the plan: Context (why this work), Assumptions (load-bearing facts the assistant is taking as given), Critical files (resources to be touched), Reuse (existing functions / tools the plan will lean on rather than reinvent), and Verification (end-to-end steps you can follow afterwards). List sections carry a count in the header, and empty sections are hidden.

Approve & run / Abort

Buttons that only render while the plan is awaiting approval. After approval they disappear and the live execution checklist takes over.

Live checklist

Once execution starts, todos render below the plan with circle / spinner / check icons as each step progresses. Driven by the assistant's update_todos tool, not by the plan itself — the plan is the upfront commitment, the checklist is what got done.

Not every plan uses every part. The card and its envelope are how you check the assumptions and the expected behaviour from the model's perspective before anything runs.

Before you see the card

Before emitting the plan card, the assistant grounds the request against the wiki, webresources and your workspace, drafts an approach, double-checks the assumptions, and only then writes the card.

After you approve

The assistant executes step-by-step. Each write still gets its own confirmation card (see AI overview) unless you previously used that card's "Always approve" button for the same tool and action. Read-only steps run straight through.

Revising a plan

There's no inline plan editor — the only two choices on the card are Approve & run and Abort. If the plan needs changes, hit Abort and send a follow-up message describing what to change ("don't touch the protocol doc — write the summary to the daily debrief doc instead"). The assistant replans from the updated conversation context on the next turn.

Aborting a plan

Abort discards the plan but keeps the conversation. The assistant acknowledges and waits for the next message. Nothing has run, nothing has changed.

What's next