Orchestrating Human-AI Software Delivery: A Retrospective Longitudinal Field Study of Three Software Modernization Programs

Most AI tools improve how individuals write code. But enterprise software is delivered by teams—across planning, implementation, validation, and release.

This paper presents a benchmark study of agentic software delivery across three real-world modernization programs and five delivery models. The results show what happens when AI agents are orchestrated across the full software development lifecycle, working alongside human teams in a shared system.

The outcome: faster delivery, lower engineering effort, and higher first-release quality.

Download the paper to see how hybrid human–AI teams compress the entire SDLC—and turn software delivery into a measurable competitive advantage.

Your paper “Orchestrating Human-AI Software Delivery: A Retrospective Longitudinal Field Study of Three Software Modernization Programs” is ready and has opened in a new tab.

Coupled Control, Structured Memory, and Verifiable Action in Agentic AI (SCRAT — Stochastic Control with Retrieval and Auditable Trajectories): A Comparative Perspective from Squirrel Locomotion and Scatter-Hoarding

Most agentic AI research studies control, memory, and verification in isolation. But in deployment, these demands don't arrive separately.

This paper introduces SCRAT (Stochastic Control with Retrieval and Auditable Trajectories): a comparative framework drawn from squirrel ecology—arboreal locomotion, scatter-hoarding, and audience-sensitive caching—to argue that robust agentic systems must couple fast feedback control, structured episodic memory, and embedded verification in a single loop. Three falsifiable hypotheses and a benchmark agenda follow from that coupling.

The implication: agentic systems succeed or fail by how well control, memory, and verification work together.

Download the paper to see how squirrel behavior sharpens the joint engineering problem, and what it means for how agentic systems should be built and evaluated.

Your paper “Coupled Control, Structured Memory, and Verifiable Action in Agentic AI (SCRAT — Stochastic Control with Retrieval and Auditable Trajectories): A Comparative Perspective from Squirrel Locomotion and Scatter-Hoarding” is ready and has opened in a new tab.

Explore our resources
Research-backed insights and benchmark studies designed to help you understand how modern teams deliver software with human–AI collaboration.

Explore our resources

content type

Explore our resourcesResearch-backed insights and benchmark studies designed to help you understand how modern teams deliver software with human–AI collaboration.

Explore our resources

content type

Explore our resources
Research-backed insights and benchmark studies designed to help you understand how modern teams deliver software with human–AI collaboration.