Agentic Datasets: Giving AI Agents More Autonomy Without Losing Control

Slides for Agentic Datasets: Giving AI Agents More Autonomy Without Losing Control, a talk at the Agentic AI Summit, part of AI+AI Toronto 2026, given on 12 November 2026 in Toronto. As agents move from executing predefined tasks to making decisions and taking action, traditional access controls are no longer enough. Without clear context around data quality, provenance, permissions and refusal conditions, agents can act on the wrong information or take the right action in the wrong context. The talk explores how datasets can become active, governed control surfaces that communicate machine-readable rules directly to agents, and how to design data boundaries that give agents greater freedom to operate while keeping their decisions traceable, policy-aware and within defined limits. The running example is Agentic LIMS, an agentic dataset served over the Model Context Protocol on public Water Quality Portal data, which also ran live in the session. Every number in Parts 1 to 4 comes from its recorded run, archived at doi:10.5281/zenodo.23625293. This published edition is the deck as presented, without the three backup slides kept for questions and without one line in the speaker's list of upcoming publications. Independent work, unaffiliated with any employer.

Authors

Publication Details

Journal
Zenodo (CERN European Organization for Nuclear Research)
Published
2026-11-12
DOI
https://doi.org/10.5281/zenodo.24202758
Primary Topic
Access Control and Trust
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Agentic Datasets: Giving AI Agents More Autonomy Without Losing Control

Alexander Chernov
Zenodo (CERN European Organization for Nuclear Research)
Access Control and Trust
article

Agentic Datasets: Giving AI Agents More Autonomy Without Losing Control

Alexander Chernov
article en

Abstract

Slides for Agentic Datasets: Giving AI Agents More Autonomy Without Losing Control, a talk at the Agentic AI Summit, part of AI+AI Toronto 2026, given on 12 November 2026 in Toronto. As agents move from executing predefined tasks to making decisions and taking action, traditional access controls are no longer enough. Without clear context around data quality, provenance, permissions and refusal conditions, agents can act on the wrong information or take the right action in the wrong context. The talk explores how datasets can become active, governed control surfaces that communicate machine-readable rules directly to agents, and how to design data boundaries that give agents greater freedom to operate while keeping their decisions traceable, policy-aware and within defined limits. The running example is Agentic LIMS, an agentic dataset served over the Model Context Protocol on public Water Quality Portal data, which also ran live in the session. Every number in Parts 1 to 4 comes from its recorded run, archived at doi:10.5281/zenodo.23625293. This published edition is the deck as presented, without the three backup slides kept for questions and without one line in the speaker's list of upcoming publications. Independent work, unaffiliated with any employer.

Zenodo (CERN European Organization for Nuclear Research)
Access Control and Trust
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