AMESA provides an intelligence engineering platform that lets enterprises design, train, and deploy teams of autonomous agents using a no‑code, drag‑and‑drop visual editor. The platform includes a secure simulation‑driven proving ground for testing and benchmarking agents with proprietary data, and an Agent Cloud for scalable production deployment, enabling continuous learning and human‑agent collaboration to automate complex processes and preserve institutional knowledge.
Funding
$5.7M raised to dateRaised to date based on public sources. This may differ from the amount the company actually raised and is based only on what is publicly available on the internet.
Founders
Product
Problem
Enterprises often rely on fragmented, manually coded automation solutions that are difficult to scale, maintain, and adapt to evolving operational knowledge. This leads to inefficiencies, knowledge loss, and limited ability to automate complex, interdependent processes across large organizations.
Solution
AMESA (formerly Composabl) offers an intelligence engineering platform that enables organizations to design, train, and deploy teams of autonomous agents. Using a no‑code, drag‑and‑drop interface, engineers can compose multi‑agent workflows, integrate proprietary data, and simulate performance in a secure proving ground. The platform supports simulation‑driven training, continuous benchmarking, and safe testing to ensure agents meet real‑world reliability standards. Once validated, agents are deployed via the Agent Cloud, providing direct human‑agent collaboration, continuous learning, and scalable operation across existing systems. This end‑to‑end solution captures institutional expertise, future‑proofs knowledge, and optimizes enterprise performance through coordinated AI autonomy.
Target Audience
Primary customers are large enterprises and engineering teams across industries such as manufacturing, logistics, energy, aerospace, and finance that need to automate complex processes and preserve institutional knowledge.
Features
- No‑code visual editor for building and configuring multi‑agent workflows with drag‑and‑drop components
- Modular architecture that allows rapid iteration and reuse of agent modules
- Visual debugging tools for inspecting agent interactions and performance
- Simulation‑driven training environment that validates agents against real data before deployment
- Continuous benchmarking and performance metrics to drive ongoing improvement
- Secure, scalable proving ground for safe testing of imported or custom‑built agents
- Agent Cloud for production deployment, supporting direct human‑agent collaboration and continuous learning
- Integration capabilities for connecting agents to existing enterprise systems and data sources