AI model routing that selects the right model for each task.

Auto Mode weighs reasoning depth, context size, modality, and response speed, then keeps the result in the same workspace.

Floatboat · Auto Mode

Current model

Auto Mode

Default

What do you want to finish?

Plan a difficult projectSummarize a long documentInspect this screenshotRefactor this code
Describe the outcome or add project files…
Access
Default client option
Availability
Available to everyone
Routing signals
Task, context, modality, availability
API key
Not required

How AI model routing works

A dispatcher that removes model management from the job.

Auto Mode is for people who want to describe the work once and let Floatboat decide how much reasoning, context, and speed it needs.

Initiative

Routes without extra setup

The request itself supplies the routing signal.

Continuity

Keeps one workspace

Files, rules, and prior output stay with the project.

Resilience

Supports fallback

A suitable fallback can keep work moving when a route is unavailable.

Control

Manual choice remains available

Switch to a fixed model when repeatability matters.

Routing signals

Different work calls for different strengths.

Auto Mode selects a route by what the request actually demands—not by one permanent favorite.

01 · Deliberate

Reasoning

Planning, proofs, architecture, and difficult debugging.

Higher deliberation

02 · Large input

Long context

Repositories, research collections, and long documents.

Context-oriented

03 · Multimodal

Vision & media

Screenshots, diagrams, images, and mixed inputs.

Image + text

04 · Everyday

Fast work

Drafting, classification, and lightweight edits.

Lower latency

Typical handoffs

Give Auto the task before choosing the engine.

The value is most visible when one project moves between different kinds of work.

From research to implementation

Task input

Study the source material, decide on an approach, and implement it.

Processing focus

Auto can favor context capacity during reading and deeper reasoning during decisions.

Expected result: One continuous project instead of separate model sessions.

Mixed daily queue

Task input

Handle summaries, edits, debugging, and document work in sequence.

Processing focus

Each request is evaluated on its own demands instead of inheriting one permanent model choice.

Expected result: Less model switching during routine work.

Continue through disruption

Task input

Keep a task moving when the preferred route is unavailable.

Processing focus

Floatboat can select a suitable fallback while preserving project context.

Expected result: Fewer interruptions caused by a single model route.

What Auto manages

Routing decisions that normally interrupt the work.

Auto changes the route, not the project the user is working in.

Task-complexity routing

Distinguishes lightweight requests from work that deserves deeper reasoning.

Context-aware selection

Accounts for repositories, document sets, and long-running conversations.

Modality fit

Considers whether the task includes text, images, or mixed material.

Automatic fallback

Can move to a suitable alternative when the preferred route is unavailable.

Use Auto when the work changes shape.

Choose Auto Mode when

  • You want a reliable default without tracking every model release.
  • One project mixes research, reasoning, editing, and execution.
  • Continuity matters more than fixing one model for every request.

Choose a model directly when

  • A repeatable workflow requires the same model behavior every time.
  • You are testing or comparing a specific model.
  • A task has a known requirement that only one listed route satisfies.

How routing works

One request, three decisions behind the scenes.

  1. 01

    Read the task

    Floatboat identifies the required depth, context, and modality.

  2. 02

    Choose a route

    It selects a suitable model and can fall back if that route is unavailable.

  3. 03

    Keep continuity

    Files, rules, and output remain attached to the same project.

Explore Other Model Families

Compare model families by the kind of work they support. Availability differs by model and entry point.

Auto Mode · FAQ

When should I use Auto Mode instead of choosing a model?+

Use Auto Mode when the task matters more than maintaining a fixed model choice, especially when one project moves between research, reasoning, editing, and execution.

Can I override Auto Mode?+

Yes. Select a model directly when repeatability or explicit control matters.

Does one request go to every provider?+

No. Auto Mode selects a route; it does not broadcast the request to every model.

What happens when a route is unavailable?+

Auto Mode can choose a suitable fallback so the task can continue.

What signals does an AI model router use?+

Auto Mode evaluates task complexity, context size, input modality, response speed, and route availability before selecting a model.

Route the next task without picking a model

Start with the real brief and files. Auto Mode chooses among available models and falls back when needed, so you can review the result.