Meet Agentrys at DAC 2026 — Booth #743 · Book a live demo →
Where agents start

Introducing Agentrys Studio

Build agentic workflows conversationally inside VS Code, watch them grow on a visual canvas, and run them in three modes — bootstrap, evolve, execute.

Self-improvement

Evolve engine

An offline training loop that re-architects multi-agent workflows — workflow mutation, prompt and agent optimization — gated by a benchmark delta against your oracle.

Knowledge

Knowledge base & skills

Curated EDA know-how — reference testplans, coverage methodology — that agents pull on demand. Toggle it and watch coverage and corner-case completeness jump.

AI-native tools

Agent-native EDA tools

Purpose-built tools for agent–EDA integration — spanning verification, static timing, and placement — all callable over MCP.

Integration

MCP & your existing tools

Connect any MCP tool server and drive the commercial EDA tools you already run through one interface — agents discover tools lazily and call them in the same session.

Safety

Guardrails & human-in-the-loop

Guardrails keep agent actions in bounds: the agent self-reports confidence, auto-handles the routine, and escalates uncertain or sign-off-critical steps to a human with an evidence trail.

Distribution

Agent registry & fleets

Publish an evolved agent once and make it every engineer's baseline. Run it as a parallel fleet across the full benchmark and many engineers at once.

Observability

Flow dashboard

Track agent and user usage, agent traces, and latency across every run.

Applications

EDA workflows, end to end

One self-improving platform across the core EDA domains — and agent-native tools for the areas automation hasn't reached yet, like RTL debug and analog layout.

Design Verification

DV Agent

Generates RTL and self-checking testbenches, runs simulation, adversarially cross-checks, and scores against your oracle — driving verification and coverage closure.

RTL Design

RTL Agent

From spec to synthesizable RTL — generate, lint, and refine, then carry designs into RTL-to-GDS onboarding flows.

Analog Design

Analog Agent

Agentic assistance for analog layout — one of the highest-effort, least-automated workflows in the flow.

Physical Design

Physical Agent

Physical implementation, evolved against your PPA targets.

Case studies

Real runs, real numbers

Not toy examples — formal bug-hunting on a production RISC-V core, self-evolving verification on a public benchmark, a 50-agent spec-to-GDS flow, and open-PDK validation.

Formal Verification · RISC-V

5 real bugs in Berkeley BOOM

Pointed at Berkeley BOOM — a large, heavily-reviewed open-source RISC-V out-of-order core — the agent used OSS formal tools to surface five functional bugs (freelist double-free, store-load forwarding, TLB multi-hit, ROB multi-flush, LR/SC), all caught at BMC step 1–2.

5 functional bugs · OSS formal tools only
Verification · Self-evolve

Past 95% on CVDP's hardest verification tasks

The DV Agent generates stimulus, checkers, and assertions, runs simulation and coverage feedback, then evolves through no-human-in-the-loop self-learning — reaching 90–96% pass rates across CVDP's hardest verification categories.

CID12–14 → 90–96% pass rate · no human in loop
Read the case study →
RTL coding · Multi-agent evolution

95.8% overall pass rate on CVDP RTL tasks

The RTL Agent evolves from a single-agent flow into a hierarchical multi-agent network, solving completion, spec-to-RTL, modification, and debug tasks — reaching 95.8% overall and 100% on Code Debug.

Gen 0 → Gen 6 · 16-agent network · 100% debug
Read the case study →
Spec-to-GDS · End to end

A 50-agent spec-to-GDS flow

An objective-agnostic, 50-agent flow auto-sets-up open-source EDA tools and runs four convergence loops — spec→RTL, RTL↔DV, physical↔DV, and PPA optimization — taking a design from specification all the way to GDS.

50 agents · monotonic PPA improvement · OSS
Read the case study →
PDK / DK Validation

Real issues in the SkyWater 130 PDK

Run against an open production process kit, the validation workflow flags actual issues in the SkyWater 130 PDK/DK — the kind of silent kit problems that derail downstream tapeouts.

Real DK issues · open production PDK
Spec → Waveforms

SPEC2WAVE: spec PDF to timing diagrams

Point SPEC2WAVE at a specification PDF and render correct WaveDrom timing diagrams (PNG/SVG) — in a single prompt.

Spec → diagram in one prompt
Why customers trust us

Smarter every run — and secure by design

Design IP used to live in engineers' heads. Now it lives in agents — and customers build and own those agents to keep their competitive advantage.

Your expertise

Inject human expertise

Capture your senior and retiring engineers' know-how — methodologies, coverage standards, reference designs — into agents that work like your best people.

Gets smarter

Self-improving agents

Agents learn from trial and error and continuously improve. Every execution's observations feed the next — capability compounds over time.

Tool mastery

Deep EDA-tool understanding

Agents learn the idiosyncrasies of the commercial tools you already run, and drive them more effectively — augmenting your flow, not replacing it.

Your history

Learns from your design data

Years of accumulated design data from past projects becomes training signal — advantage that no off-the-shelf model can replicate.

IP-secure

Inside your firewall

Code never leaves your machine — behind the IP-shield redactor and an encrypted local store. Self-hosted, with offline signed licensing and no runtime phone-home.

Platform, not a model

Own the whole flow

A model is a component; Agentrys is the platform around it. Migrate model-based workflows in, orchestrate many tools and agents, and keep improving — on your terms.