Web AI Router

Select the best available web AI for a task and delegate to the appropriate worker.

Available Workers

See worker-contract.md for the shared output schema.

Routing Logic

Step 1 — Identify task type

Read the user's request and classify:

Step 2 — Check worker availability

Before routing, verify the target worker is accessible:

• gemini-worker: always available (no login required)
• grok-worker: requires Grok session in Chrome profile
• deepseek-worker: requires DeepSeek session in Chrome profile
• claude-worker: requires Claude session in Chrome profile
• chatgpt-worker: requires ChatGPT session in Chrome profile

If the preferred worker is unavailable (login required but session lost), fall back to gemini-worker and note the fallback in the output.

Step 3 — Route to worker

Load and execute the appropriate worker skill:

[skill] gemini-worker   → for general tasks
[skill] grok-worker     → for real-time search tasks
[skill] deepseek-worker → for reasoning/analysis tasks
[skill] claude-worker   → for writing/long-form tasks
[skill] chatgpt-worker  → for creative/general tasks

Step 4 — Return unified output

All workers return the same schema (defined in worker-contract.md):

{
  "site": "gemini | grok | deepseek | claude | chatgpt",
  "task_type": "qa | summary | translation | rewrite | extraction | comparison | brainstorming | analysis",
  "status": "success | partial | error",
  "answer": "<response text>",
  "retry_count": 0,
  "elapsed_ms": 0,
  "error_reason": null
}

Follow with a short human-readable summary.

Multi-Worker Mode

If the user asks to query multiple AIs and compare results, run workers sequentially and present results side by side.

Example trigger: "ask both Gemini and Grok about X and compare"

Output format for multi-worker:

## Gemini
<answer>

## Grok
<answer>

## Comparison
<brief synthesis>

Decision Examples