Retiring the Agent Persona: Fail-Closed, Catalogue-Constrained Process Orchestration as a Successor to Vertical LLM Agents: An Experience Report and Evaluation

Enterprise automation built on large language models has predominantly followed the persona-agent pattern: a named agent persona owns a business domain, reasons through unconstrained prose, and executes tools in an iterative prompt loop. Recent empirical evaluations demonstrate that this pattern suffers from framework-level failure modes, non-deterministic control flow, and unprincipled governance. Consequently, systems engineering has begun shifting toward deterministic orchestration architectures. In this experience report, we document the architectural retirement of seven vertical persona agents within a production-scale multi-tenant enterprise platform. We replaced these agents with a deterministic-first process engine that fundamentally inverts the control loop. A deterministic compiler maps natural-language user goals onto a registered catalogue of capabilities. The large language model operates solely as a bounded, untrusted fallback whose structural proposals are validated against the catalogue; any unrecognized capability or execution failure automatically demotes to an audited human task. Our contributions are threefold: An empirical migration case study and defect post-mortem detailing a declarative skill registry breakdown (where 23 of 29 capability pointers silently failed to resolve) along with its startup-reconciliation remedy. The architecture of catalogue-constrained goal compilation enforcing a verifiable safety invariant: the orchestration engine cannot emit or execute a capability outside its verified catalogue. An evaluation of this safety invariant and its operational flexibility cost: 8/8 hostile-input cases contained (including strict zero-call containment on unverified tenant context), 24 representative enterprise goals compiled with zero hallucinated capabilities at a measured human demotion rate of 0.109, and a 271/276 passing test suite verified against the frozen prototype snapshot. Artifact Note: Gathered against frozen research tag V2-Prototype. Repository archived as research-only. Accompanying systems architecture baseline: Console V4 (July 2026).

Authors

Publication Details

Journal
Zenodo (CERN European Organization for Nuclear Research)
Published
2026-11-20
DOI
https://doi.org/10.5281/zenodo.24399709
Primary Topic
Artificial Intelligence Applications
Type
preprint
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
preprint

Retiring the Agent Persona: Fail-Closed, Catalogue-Constrained Process Orchestration as a Successor to Vertical LLM Agents: An Experience Report and Evaluation

Marcelinus Apakhade
5 links
Zenodo (CERN European Organization for Nuclear Research)
Artificial Intelligence Applications
preprint

Retiring the Agent Persona: Fail-Closed, Catalogue-Constrained Process Orchestration as a Successor to Vertical LLM Agents: An Experience Report and Evaluation

Marcelinus Apakhade
preprint en

Abstract

Enterprise automation built on large language models has predominantly followed the persona-agent pattern: a named agent persona owns a business domain, reasons through unconstrained prose, and executes tools in an iterative prompt loop. Recent empirical evaluations demonstrate that this pattern suffers from framework-level failure modes, non-deterministic control flow, and unprincipled governance. Consequently, systems engineering has begun shifting toward deterministic orchestration architectures. In this experience report, we document the architectural retirement of seven vertical persona agents within a production-scale multi-tenant enterprise platform. We replaced these agents with a deterministic-first process engine that fundamentally inverts the control loop. A deterministic compiler maps natural-language user goals onto a registered catalogue of capabilities. The large language model operates solely as a bounded, untrusted fallback whose structural proposals are validated against the catalogue; any unrecognized capability or execution failure automatically demotes to an audited human task. Our contributions are threefold: An empirical migration case study and defect post-mortem detailing a declarative skill registry breakdown (where 23 of 29 capability pointers silently failed to resolve) along with its startup-reconciliation remedy. The architecture of catalogue-constrained goal compilation enforcing a verifiable safety invariant: the orchestration engine cannot emit or execute a capability outside its verified catalogue. An evaluation of this safety invariant and its operational flexibility cost: 8/8 hostile-input cases contained (including strict zero-call containment on unverified tenant context), 24 representative enterprise goals compiled with zero hallucinated capabilities at a measured human demotion rate of 0.109, and a 271/276 passing test suite verified against the frozen prototype snapshot. Artifact Note: Gathered against frozen research tag V2-Prototype. Repository archived as research-only. Accompanying systems architecture baseline: Console V4 (July 2026).

Zenodo (CERN European Organization for Nuclear Research)
Artificial Intelligence Applications
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon