Step 1
Baseline route — Claude Sonnet 4.6 (control)
Expected behaviour: agents_used should be ['executor'] only. No planner, no verifier. Useful as the control.
seed: plan.recipe.1
Demo · Multi-agent routing
Same prompt. Three routes. See the lift.
The hardest question in any wrapper-over-LLM product is does the wrapping actually help?This demo answers it the only honest way: by running the same task through the raw baseline and through Aya's pipeline, and showing the receipts side by side.
For each card below, set the route selector at the top to match the card's caption, then click Run. The receipt at the bottom of each card shows agents_used, latency_ms, cost_estimate, and confidence.
Step 2
Aya pipeline — anthropic/claude-sonnet-4.6 + 7-stage cognitive spine
Expected behaviour: agents_used should include planner, executor, verifier (and possibly memory_retriever). Latency higher; confidence and pass-rate should be higher too.
seed: plan.recipe.1
Step 3
Aya reasoner — anthropic/claude-opus-4.6, extended thinking (10k)
Expected behaviour: Includes self_critic. Highest cost, typically highest quality. Use this when accuracy matters more than latency.
seed: plan.recipe.1
What to look for.
- agents_used should grow from 1 (baseline) to 3 (aya_pipeline) to 4 (aya_reasoner). That's the architecture working.
- latency_ms should grow with each route — wrapping isn't free. The interesting question is whether the latency cost buys a meaningful confidence/pass-rate gain.
- cost_estimate follows the same pattern. The aya_reasoner route is roughly 4× the cost of baseline; use it deliberately.
- confidence should improve with the wrapping. If it doesn't, that's a real signal that the task didn't benefit from the cognitive spine — and the harness will honestly tell you so.