AgentForge: A Survey of Harness Engineering for Reliable Agentic AI and a State-Bound Action-Control Framework for Enterprise Workflows

Large language model (LLM) agents no longer only answer questions; they now call tools, read databases and change the state of business systems. Orchestration frameworks such as LangGraph coordinate these agents well, but they leave execution governance to every application: who may write, whether a decision is still valid at the moment of writing, what happens when a call is retried, and how each effect is traced. This paper surveys the research that addresses parts of this problem: reasoning-and-acting agents, reliability and safety benchmarks, prompt-injection defences and guardrails, privilege control, transaction and compensation models, observability, and AI-risk governance standards. From this survey we derive a taxonomy of seven failure classes that occur on an agent’s write path and show that no single existing approach covers stale decisions, unauthorized actions, duplicate side effects and incomplete audit together. We then present AgentForge, a domain-agnostic tool-effect gateway built on the idea of harness engineering. In AgentForge an agent can only propose an action. The gateway validates it against typed contracts, current business state and declarative policy; obtains human approval bound to a cryptographic state fingerprint; enforces exactly-once effects with idempotency keys and optimistic concurrency; revalidates the action immediately before commit; verifies the post-condition; and records the whole journey as an OpenTelemetry trace. The framework is demonstrated on a simulated supply-chain procurement workflow. We specify a paired evaluation protocol (60 scenario templates × 3 runs per arm, judged on the final database state) with measurable targets: at least 90% fewer unauthorized commits, at most 1% duplicate effects, at least 95% of stale approvals blocked, at most 5% false blocks, at least 98% audit completeness and below 500 ms median overhead. We close with open challenges and a research agenda for trustworthy agentic infrastructure. Index Terms Agentic AI, LLM agents, harness engineering, tool-effect gateway, execution governance, policy engine, human-in-the-loop approval, state fingerprint, idempotency, optimistic concurrency control, audit trace, OpenTelemetry, procurement, LangGraph.

Authors

Institutions

Publication Details

Journal
International Scientific Journal of Engineering and Management
Published
2026-11-20
DOI
https://doi.org/10.55041/isjem08763
Primary Topic
Distributed systems and fault tolerance
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

AgentForge: A Survey of Harness Engineering for Reliable Agentic AI and a State-Bound Action-Control Framework for Enterprise Workflows

Aum Patil, Prithviraj Chavan, Suraj Bichitkar, Mrs. Aparna Veer
3 links
International Scientific Journal of Engineering and Management
Distributed systems and fault tolerance
article

AgentForge: A Survey of Harness Engineering for Reliable Agentic AI and a State-Bound Action-Control Framework for Enterprise Workflows

Aum Patil, Prithviraj Chavan, Suraj Bichitkar, Mrs. Aparna Veer
article en

Abstract

Large language model (LLM) agents no longer only answer questions; they now call tools, read databases and change the state of business systems. Orchestration frameworks such as LangGraph coordinate these agents well, but they leave execution governance to every application: who may write, whether a decision is still valid at the moment of writing, what happens when a call is retried, and how each effect is traced. This paper surveys the research that addresses parts of this problem: reasoning-and-acting agents, reliability and safety benchmarks, prompt-injection defences and guardrails, privilege control, transaction and compensation models, observability, and AI-risk governance standards. From this survey we derive a taxonomy of seven failure classes that occur on an agent’s write path and show that no single existing approach covers stale decisions, unauthorized actions, duplicate side effects and incomplete audit together. We then present AgentForge, a domain-agnostic tool-effect gateway built on the idea of harness engineering. In AgentForge an agent can only propose an action. The gateway validates it against typed contracts, current business state and declarative policy; obtains human approval bound to a cryptographic state fingerprint; enforces exactly-once effects with idempotency keys and optimistic concurrency; revalidates the action immediately before commit; verifies the post-condition; and records the whole journey as an OpenTelemetry trace. The framework is demonstrated on a simulated supply-chain procurement workflow. We specify a paired evaluation protocol (60 scenario templates × 3 runs per arm, judged on the final database state) with measurable targets: at least 90% fewer unauthorized commits, at most 1% duplicate effects, at least 95% of stale approvals blocked, at most 5% false blocks, at least 98% audit completeness and below 500 ms median overhead. We close with open challenges and a research agenda for trustworthy agentic infrastructure. Index Terms Agentic AI, LLM agents, harness engineering, tool-effect gateway, execution governance, policy engine, human-in-the-loop approval, state fingerprint, idempotency, optimistic concurrency control, audit trace, OpenTelemetry, procurement, LangGraph.

International Scientific Journal of Engineering and ManagementVol. 02(11)
AISSMS Institute of Information Technology (IN)
Distributed systems and fault tolerance
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