02 / Model selection for delegation

FastDelegate

Model recommendations for a predefined task, balancing fit evidence, pricing, context, tools, quota, and recorded outcomes.

View source on GitHub Explore the walkthrough ↓Read as Markdown

The question

Which worker can complete this task with the tools and budget available?

FastDelegate turns one task and the active harness’s available model selectors into a ranked recommendation list. The caller still chooses the worker, dispatches the task, and verifies the result.

Design decisions

Where the boundaries matter

Check the constraints first

Runtime, context, tool support, known quota, and a known price below the lead are safeguards before recommendation.

Keep judgment with the caller

Fit scores are advisory evidence, not success probabilities. Every recommendation requires lead review; the router executes no workers.

Step 1 of 3

Describe a bounded task

An illustrative routing request, not a benchmark or live model call.

01 / Input: A task with acceptance criteria, the lead model, and available worker selectors.
02 / Decision: Supply the actual context and tool requirements for this task.
03 / Output: A routing request grounded in the active harness.

Evidence & current boundaries

Reviewed 2026-10-07

A summary based on the public project documentation, not an independent audit. Read the source README for the basis of these claims.

Implemented

An explicit recommendation boundary

The public README documents routing, an explicitly labeled heuristic fallback, and outcome recording after caller verification.

Source record / Public README: Recommend a model, Jev and fallback, Discovery and feedback

Current limitations

One predefined task per recommendation request; task decomposition and dispatch belong to the caller.
Missing or stale evidence remains unknown. Fit scores are not measured success probabilities.
Subscription and local deployments use shadow cost, not claimed dollar savings.

Continue exploring

codvps

Let’s talk agent systems ↗