William Astley
AI Agent Architect
Agentic systems engineer who independently created the Haive framework, enabling dynamic multi-agent AI where agents compose workflows, coordinate teams, discover tools, and adapt behavior at runtime.
Haive Framework
Runtime-configurable multi-agent infrastructure spanning orchestration, MCP, deployment, evaluation, and prebuilt workflows for production teams.
GitHub Pages docs not live yet
Projects & Open Source
Resume-backed flagship work first, with the broader archive covering PyPI packages, MCP servers, and older experiments one click away.
Work Experience
Production-scale agentic systems, quantitative risk management, and Y Combinator startup experience.
Creator
Haive Framework
Architected Haive's runtime and standardized ACP-style deployment services for dynamic multi-agent systems, with stateful serializable graphs, persistent memory, runtime reconfiguration, capability discovery, and MCP integrations.
Key Projects & Achievements
- Built composable agent-team orchestration with planners, reasoners, memory, dynamic supervision, parallel execution, and validation and repair loops for adaptive workflows.
- Developed configurable RAG and context pipelines across 200+ sources, spanning custom ingestion, document processing, embedding, indexing and storage, retrieval orchestration, and 20+ RAG patterns.
- Designed evaluation and benchmarking systems across 22 game and application environments, using fixed-config ablations to compare tools, prompts, models, and agent architectures.
Senior Quantitative Risk Developer
Corpay, Toronto
Led Corpay's agentic AI initiative by building multi-agent systems on Haive, including a KYC and AML watchlist assistant that achieved 96% detection accuracy, 5x faster throughput, and full coverage over sampling.
Key Projects & Achievements
- Built a database intelligence agent and credit underwriting assistant for internal teams, improving data access and enabling faster, more consistent credit reviews.
- Engineered an automated forecasting and stress-testing platform using GARCH-based models for VaR, volatility, and scenario analysis, improving accuracy by 35% and reducing runtime by 75% across $500M.
- Built and maintained a centralized multi-repo platform, unifying CI/CD across credit, treasury, and trading.
Founder & Lead Developer
Algebraic Wealth Technologies, Toronto
Built and led a 10-person team developing EquityExpert, an early multi-agent platform for automated sell-side equity research with live, data-driven reports spanning fundamental, technical, macro, and quantitative analysis.
Key Projects & Achievements
- Advanced to the Y Combinator interview stage for AI-driven analytics and document-ingestion systems.
Key Technologies
The stack behind my agent runtimes, quantitative systems, and developer tooling work.
Runtime design, orchestration, memory, observability, and evaluation for production agent systems.
Core implementation stack for API design, data processing, and backend services.
Modeling, retrieval, and quantitative methods used across research and forecasting systems.
State, queues, storage, telemetry, and deployment primitives for resilient runtime infrastructure.
Packaging, testing, quality, and release tooling that keeps multi-repo systems shippable.
Get In Touch
Interested in collaborating on AI projects or have questions about my work? Feel free to reach out.
Your information is protected and never shared publicly.
Messages are delivered directly to my inbox.