Skip to content

GCRI · Künstliche Intelligenz und autonome Systeme

Agentische Systeme

Agentic AI Systeme pursue goals by planning and taking actions: calling tools, browsing, writing and running code, or operating other software, sometimes over long tasks with little supervision. Autonomy brings usefulness and new failure modes, from compounding errors to misuse of granted permissions. This page sets out how agents fail, how their actions can be bounded and overseen, and what evidence serves those who build, deploy and govern them.

01Registrieren

Agentic systems on the record.

02Die Frage

Agentic systems: how the risk develops.

Tool access, delegated authority and safe execution. The dossier below sets out how the risk develops, what is measured, where the data come from, how it is modelled and who decides.

Mechanismus

Errors compound over steps

Each step in a long task can go wrong, and an early mistake shapes later actions. Small per-step error rates add up over many steps.

Mechanismus

Permissions define the blast radius

An agent can only do harm with the access it has been given. Broad credentials, write access and payment rights turn errors or manipulation into real-world consequences.

Mechanismus

Untrusted inputs steer behaviour

Agents read web pages, documents and messages that may contain instructions. Prompt injection can redirect an agent to act against its user.

Mechanismus

Oversight must be designed in

Humans cannot review every action of a fast agent. Approval steps for consequential actions, logging and the ability to stop and roll back are design choices.

03Monitoring

Agent oversight console.

Die Ansicht, die ein Team nutzen würde, um dieses Thema zu verfolgen: seine Messgrößen, Zustände und Entscheidungen. Namen sind Beispiele, Werte sind illustrativ.

Agent oversight console

Agentic systems · Agent sandbox · Session AG-6627

Human approval pendingGCRI · Künstliche Intelligenz und autonome Systeme

Tool calls

  1. 10:34Infosearch(documents) · read-only
  2. 10:51Inforun_model(flood_nowcast) · sandbox
  3. 10:51Meilensteinsend_message(external) · needs approval
  4. 10:53Errorwrite_file(outside workspace) · denied

Politik

Geltungsbereich
workspace only
External actions
human approval
Spend limit
43 units
Kill switch
Armed

Actions by approval class

050100count this weekAutomatischProtokolliertGenehmigtDeniedEskaliert
Agent oversight console: the screen’s structure, terms and states for Agentic systems.Beispielnamen und beispielhafte Werte; ein Entwurf, kein Eintrag und kein Live-System.
04Domänenübergreifend

Agents that act need guardrails in every domain they touch.

Agentic system studies are designed for the Reihe Exponential Technology. The OWASP Top 10 for LLM applications lists failure modes such as excessive agency and prompt injection; the page describes them without exploit detail.

  • Incident reports involving agents.
  • Designs for oversight and permission scoping.
05Methoden und Evidenz

How agentic systems is modelled, measured and tested.

Das Modell, seine Annahmen, seine Daten und seine Unsicherheit in der Form, in der eine Wissenschaftlerin oder ein Ingenieur sie prüfen würde. Die Strukturen folgen veröffentlichten Methoden. Die dargestellten Werte sind illustrativ, keine Befunde.

Systemmodell

The couplings between the systems in agentic systems: signs of influence, a reinforcing and a balancing loop, and cross-links where stress jumps.

++−+Künstliche IntelligenzDatenGemeinschaftenWirtschaftR verstärkendB ausgleichend
Causal loop diagram from the page’s systems; signs show the direction of influence. Illustrative structure for a system dynamics or network model, not estimated couplings.
FAIR-Leitprinzipien · GO FAIR und FORCE11W3C PROV · World Wide Web ConsortiumHinweise zur einheitlichen Behandlung von Unsicherheiten · IPCCCEOS Analysis Ready Data · Committee on Earth Observation Satellites
06Indikatoren

Was gemessen wird und wie gut.

Jeder Indikator trägt seine Einheit, seinen Rhythmus, die Art der zugrunde liegenden Quelle und die Evidenzkennzeichnung, die ein Wert tragen würde. Es werden keine Werte gezeigt: Ein Programm liefert sie unter seiner eigenen Autorität.

IndikatorEinheitTaktQuellentypKennzeichnung
Task success rate on agent benchmarkspercent of tasks completed correctlyper evaluationAgent benchmark resultsBERICHTET
Actions requiring human approvalpercent of consequential actionsper deploymentDeployment configurationDEKLARIERT
Prompt injection success ratepercent of attempts succeedingper evaluationSecurity testingBEOBACHTET
Agent incidentscount by severitymonatlichIncident reportsBERICHTET
Actions logged and attributablepercent of agent actionsper deploymentAudit logsBEOBACHTET
Mean task length before human interventionsteps or minutesper evaluationEvaluation logsBEOBACHTET
07Quellen

Woher die Evidenz stammt.

Benannte öffentliche Datensätze und institutionelle Aufzeichnungen, jeweils mit ihrer Lizenzklasse. Quellen auf Vereinbarungsbasis werden nur zu ihren Bedingungen genutzt und niemals weiterveröffentlicht.

QuelleWas es liefertLizenzklasse
OWASP Top 10 for LLM Applications and agentic security guidanceRisks such as prompt injection and excessive agencyOpen, CC BY-SA 4.0
Published agent benchmarks such as SWE-bench and related suitesTask-based evaluation of agentsOpen, licence per benchmark (to check)
NIST AI Risk Management FrameworkPractices for governing and measuring AI riskPublic domain, US government
AI Incident DatabaseReported incidents involving AI SystemeOpen, licence to check
Developer system cards describing agent safeguardsDeveloper-reported agent evaluations and controlsPublic documents, terms per developer
08Entscheidungen

Wer entscheidet und wozu die Evidenz dient.

Studio Künstliche Intelligenz und autonome System prepares evidence. The decisions below are taken by the authorities named, under their own rules, and never by the platform.

Wer entscheidetDie FrageEvidenz, der diese Seite dient
Deploying organisationsWhich actions an agent may take alone and which need approvalPermission patterns; evaluation results
Security teamsHow to protect agents from manipulationInjection testing; incident evidence
AufsichtsbehördenWhat oversight to require for autonomous AI actionsOversight design evidence

Ergebnisse, die dieses Thema hervorbringt

  • Permission and approval design patterns for agents
  • Agent evaluation protocols covering long tasks
  • Prompt injection test suites for deployments
  • Logging and rollback requirements
09Kernfragen

What designers and evaluators ask.

  • What actions can the agent take, with whose authority, and which are reversible?
  • How does it behave when instructions are ambiguous, conflicting or malicious?
  • Can a human see what it is doing, understand why and stop it in time?
  • How do errors compound over long sequences of steps?
10Mechanismen

How agents fail.

An agent combines a model’s reasoning with permissions in the world. Small errors in early steps can compound across a long task. Agents can misinterpret goals, pursue them in unintended ways or take shortcuts that satisfy a metric but not the intent. Content the agent reads, such as a web page or document, can contain instructions designed to hijack it, an attack known as prompt injection.

The more permissions an agent holds, the larger the potential harm. System that coordinate several agents add further failure modes, as agents pass errors to each other or interact in unforeseen ways.

11Methoden und Daten

Designing for safe execution.

  1. 01

    Least privilege

    Granting only the permissions a task needs, with sandboxes and spending or action limits, drawing on Cybersicherheit und Kryptografie.

  2. 02

    Human oversight points

    Requiring confirmation for consequential or irreversible actions. Too many prompts lead to rubber-stamping, so placement matters.

  3. 03

    Task-based evaluation

    Testing agents on realistic multi-step tasks in controlled environments, using Engineering für KI-Evaluierung und -Assurance. Simulated environments miss some real-world complexity.

  4. 04

    Logging and audit

    Recording actions and reasoning traces so incidents can be reconstructed. Traces may not fully reflect how a model reached a decision.

13Where this page’s references

Where this page’s references lead.

Die Gremien und Dokumente, vor deren Hintergrund diese Seite gelesen wird. Status und Ausgaben ändern sich; jeder Link führt zur herausgebenden Stelle.

14Fragen

Fragen und Antworten.

What is an AI agent?
An AI system that pursues goals by planning and taking actions, such as using tools, browsing or running code, with some degree of autonomy.
What is prompt injection?
An attack in which instructions hidden in content the AI reads, such as a web page or document, cause it to act against its user’s intent.
How can agent risk be reduced?
By limiting permissions to what the task needs, requiring approval for consequential actions, logging all actions, testing against manipulation and keeping the ability to stop and undo.
Should agents ever act without human approval?
For low-consequence, reversible actions within tight limits, often yes. For consequential or irreversible actions, the design question is where and how a human confirms.
Can agents be evaluated before deployment?
Partly, in controlled environments with realistic tasks. Monitoring after deployment remains necessary because real environments are more varied.
Does the platform build agents?
Its work is evaluation and method. Any build work for Consortium projects runs through Foundry under its own governance.
BerichteBeitragen

Evidenz von dieser Seite aus beitragen.

Berichte is the Consortium’s quarterly publication. What you know about this subject can become evidence, a case or a correction in the next edition, credited to you and published under CC BY 4.0 where it is your own work.

GCRIKünstliche Intelligenz und autonome SystemeExponentielle TechnologieLabs-Evidenz
Künstliche Intelligenz und autonome Systeme

Bringen Sie eine Methode, einen Datensatz oder eine Frage mit.

Information und Anfragen sind heute offen. Eine Anfrage erhält ein Aktenzeichen und nennt den nächsten Schritt; Bewerbungen, Zahlungen, Rechenzuteilungen und Registrierungen öffnen erst, wenn Team, Bedingungen und Prüfkapazität bestehen.