The Agentic Engineering Assurance Layer connects intent, evidence, and human authority. It governs how agentic engineering work is performed and evidenced, so that humans can trust and accept the resulting work. Software engineering is crossing from a world in which code was expensive to produce into one in which code is expensive to trust and accept. As agentic AI makes implementation increasingly abundant, the engineering constraint shifts toward verifying, validating, evidencing, and taking accountable ownership of work that no human watched being performed. The layer addresses a cross-tool engineering question: should this engineering outcome be trusted and accepted, by whom, on what evidence, and does that evidence remain valid? Kealu is developing an early access commercial implementation within Kealu Vector, currently designated Vector Assurance Assist.
The Assurance Plane is the persistent architecture that connects engineering intent, agentic work, evidence, human authority, and lifecycle change. It governs how work is performed and evidenced. It coordinates Assurance Work Packages, Assurance Cases, engineering and intent context, policies and standards, coding agents, specialist assurance agents, testing and verification systems, human decision authorities, evidence provenance, evidence freshness, and re-assurance triggers. Within Kealu Vector, the Chief Agent Engineer coordinates delegated work; the Assurance Plane preserves the conditions, evidence, and authority on which humans may rely. It does not take ownership of the customer's software work product or replace the customer's engineering, quality, testing, or certification responsibilities. The greater the scale of agentic execution, the greater the need for an independent Assurance Plane.
The Assurance Work Package is the atomic unit of work and value in Kealu Vector. Each consequential request, obligation, change, or environmental event can create a Work Package. It contains or references the originating intent or trigger, requirements and constraints, applicable standards and internal policies, required evidence, the participating humans, agents, tools, and systems, the produced engineering work, verification and intent-validation findings, human decisions, and the resulting Assurance Case. Wherever possible, the Work Package is created before consequential implementation begins. It then remains active throughout the relevant lifecycle. A Work Package may be decomposed into linked child Work Packages. Completion of child tasks does not automatically establish acceptance of the parent outcome.
The Assurance Case is the structured explanation of why an engineering outcome may be relied upon for a particular decision. It connects assurance claims to supporting evidence, identifies unresolved matters, preserves provenance, and records applicable human decisions. It explains what was intended, which obligations applied, what work was performed, which evidence originated independently from the producing agent, whether the work remained aligned with intent, and which human or authorized role made each consequential decision. The purpose is to allow a quality representative, auditor, customer, regulator, executive, or future engineer to inspect the basis of a decision without relying solely on the original reviewer's personal trust or recollection. Consequential decision points may create tamper-evident Assurance Case snapshots. The Assurance Case supports a human decision. It is not a Kealu certification or guarantee of product correctness.
The Chief Agent Engineer is the persistent engineering intelligence within Kealu Vector and steward of the Assurance Plane. It is designed to serve as the primary conversational interface for coordinating long-horizon work across people, agents, tools, and related Work Packages. It maintains engineering and assurance context, frames and prioritizes Work Packages, coordinates customer-selected coding agents and specialist assurance agents, and preserves shared intent and architectural context as parallel work evolves. It identifies conflicts between intent, architecture, policy, and standards, briefs humans, requests decisions, and escalates matters when its authority or knowledge is insufficient. The Chief Agent Engineer supervises and harmonizes the process. It does not become the accountable engineering authority or the primary producer of the customer's software.
The Engineering Graph provides connected, persistent context across intent, requirements, architecture, software components, repositories, interfaces, dependencies, tests and verification evidence, standards and policies, Work Packages, Assurance Cases, human authorities, prior decisions, and evidence dependencies. The graph allows Kealu to determine which engineering obligations and prior assurance claims may be affected by a proposed or observed change. Within Kealu Vector's intended platform architecture it belongs to the Context and Evidence Layer, together with intent and authority context, provenance and activity records, the evidence registry, Work Package and Assurance Case history, evidence dependencies, and evidence-freshness state. It is one of the intended product components of the initial pilot, with implementation depth confirmed for each engagement.
Kealu is a vertically integrated AI research and product-development company building the foundations of engineering for the intelligence age. Kealu Labs is the advanced, applied research organization within Kealu. Kealu Vector is Kealu's AI engineering platform under development for consequential software. It combines a Chief Agent Engineer for long-horizon coordination of people, agents, and tools with an Agentic Engineering Assurance Layer that connects intent, evidence, and human authority. Consequential software means systems where failure can affect safety, security, health, or material financial outcomes. Vector Assurance Assist is the current designation for the intended assistance-oriented early-access capabilities within Kealu Vector. Kealu is headquartered in Miami Beach, Florida.
Kealu was founded in 2025 by Roy Reichbach, Stefan Birrer, and Fabián E. Bustamante. Roy Reichbach is Co-Founder and CEO, Stefan Birrer is Co-Founder and CTO, and Fabián E. Bustamante is Co-Founder and Chief Scientist. Fabián E. Bustamante is a Professor of Computer Science at Northwestern University. He and Stefan Birrer wrote Kealu's working terminology for agent systems, published in May 2026. The leadership team also includes Reza Zanjani, Chief Operating Officer, and Antonio Vasaiely, Chief Product and Strategy Officer.