Optimize any agentic workflow
against cost, speed, and quality.
Drop in a high-level task or an existing graph. AutoAW co-evolves topology, prompts, models, and tools — searching the Pareto frontier of your utility function so you ship the cheapest version that still hits your bar.
From a brittle prototype to a Pareto-optimal pipeline.
AutoAW doesn't just tune prompts — it rewrites the graph. Below is the actual diff from the customer-support copilot experiment.
The missing third layer.
DSPy compiles prompts. Inspect evaluates agents. Neither searches over architectures — AutoAW does.
Tunes instructions and few-shot examples for a fixed agent topology.
Runs agents in sandboxed environments and scores them against benchmarks.
Evolves the architecture itself — which agents exist, how they connect, which models they use.
Two paradigms. One optimizer. No assumptions.
Multi-agent committees and agentic glue are different bets on where reasoning should live. AutoAW makes neither bet upfront — it searches both and lets your fitness function settle the argument.
| Dimension | Multi-Agent Committee | Agentic Glue + Skills |
|---|---|---|
| Latency | High — each hand-off is a fresh LLM call | Low — one LLM, tools run as fast code |
| Context | Fragmented — state re-interpreted at each hop | Unified — one context window, no drift |
| Debugging | Complex — trace across N reasoning chains | Standard — did the LLM call the skill? Did it run? |
| Cost | Proportional to agent count × task length | Proportional to conductor reasoning only |
Five steps. One Pareto frontier.
Describe the task
Either give a high-level task — "triage support tickets and propose a draft reply" — or import an existing workflow (LangGraph, DSPy, your own Python).
Pick datasets & weights
Choose an eval dataset (yours or one of 18 included). Set the utility weights — quality, $/run, p50 latency. AutoAW does the rest.
AutoAW searches
A search loop swaps models, splits/merges agents, edits prompts, prunes tools, and re-evaluates every candidate. The Pareto frontier fills in as it runs.
Export to AWP / AWF
Pick any point on the frontier and export the winning agent as a single portable graph — Agentic Workflow Protocol (AWP) or an AWF file, or plain JSON. Fork to keep optimizing.
Promote & deploy
Promote a candidate straight to a hosted, versioned endpoint — no infra to manage.
Describe the task
Either give a high-level task — "triage support tickets and propose a draft reply" — or import an existing workflow (LangGraph, DSPy, your own Python).
What it found in our last run.
Task: customer-support copilot, 1,400-ticket eval. Objective = 0.7·quality + 0.25·cost⁻¹ + 0.05·speed.
Recent case studies.
Controlled benchmarks — hand-built workflows measured head-to-head against a strong monolith, not evolutionary runs. Code and per-task data released.
A workflow that runs its own tests beats a one-shot monolith.
On 150 hard BigCodeBench tasks we benchmarked a one-shot monolith against a workflow that executes each task's unit tests and repairs against the failures — then scored both on held-out tests the agent never sees. Base model gpt-oss-120b.
What early users are saying.
Named results from teams putting AutoAW into their eval loop. Want to be here? Tell us your story.
“We worked together in the past on AutoML, and now Andrey is following an interesting direction — how AutoML can be applied to agentic workflows. Very relevant and exciting!”
Licensed for commercial use.
AutoAW is commercial software, licensed per team. Pricing is custom and based on your use case — workloads, integrations, and deployment model.
- Full access to all search algorithms (evo, SMBO)
- Commercial use rights
- Hands-on setup & onboarding
- Help running experiments & custom integrations
- Deployments (SaaS · VPC · on-prem)
- Dedicated solutions engineer
- 1-hour response SLA