Give ASR Labs any codebase with a measurable metric. It runs structured AI research cycles overnight — analysing literature, designing targeted changes, and rigorously evaluating results. You wake up to better software. First application: combinatorial optimization solvers.
Every performance-critical codebase follows the same arc: build, tune, ship, forget. Improvement requires scarce experts, and their knowledge leaves when they do.
Expert engineers hand-tune algorithms. Months of work. Good results — until the expert leaves, the codebase fossilizes, and the literature moves on without you.
Generic solutions get you 80% of the way. Performance plateaus. You can't tune what you don't own. The last 20% is where the competitive advantage lives.
ASR Labs treats software improvement as a research problem. Given a codebase and a metric, AI agents run structured research cycles — reading literature, designing changes, testing rigorously, archiving what they learn. Continuous improvement without continuous headcount.
Karpathy's autoresearch lets AI agents iterate on ML training code overnight. We generalise the pattern: any codebase with a measurable metric can be continuously improved through structured research cycles.
Describe your problem in structured YAML. ASR Labs classifies it, selects proven components from a catalog, assembles a working codebase, verifies correctness, and establishes a baseline metric.
The output is a project you own. Not an API call. Not an opaque runtime. Source code.
Not random mutation — a structured research cycle. AI agents study literature and production data to identify a goal, design a targeted change informed by domain knowledge and past reflections from the archive, implement and test it, benchmark with statistical rigor, then evaluate what was good and bad — feeding insights back into the archive.
~100 research cycles per night. ~$10–50 in API cost. Each cycle is smarter than the last because the archive accumulates.
The first codebase under ASR is a production VRP solver that already competes with state-of-the-art academic implementations. The platform is generic — this is where we prove it works.
The first domain where ASR proves its value. Field service optimization is the ideal testbed: measurable metrics, rich constraints, and real production data.
Technician scheduling — 20–80 jobs per day with variable service times
Skills matching — technicians have certifications, jobs need specific qualifications
Break compliance — lunch breaks, shift limits, labor regulations
Wide time windows — "morning" or "afternoon" slots, not exact times
Heterogeneous fleet — different vehicle types, home starts, equipment
Custom solver tuned to your exact constraint set — not a generic framework
Overnight research cycles on your actual customer data — goal-driven improvements, not random mutations
Source code ownership — no vendor lock-in, no API dependency, full IP
Per-archetype tuning — dense urban, rural spread, emergency replan each get their own profile
No OR headcount — the system replaces the need for scarce optimization engineers
Let's run a proof of concept on your codebase.