Skip to content

GCRI · Inteligência artificial e sistemas autônomos

Sistemas agênticos

Agentic AI sistemas 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.

01Registrar

Agentic systems on the record.

02A pergunta

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.

Mecanismo

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.

Mecanismo

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.

Mecanismo

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.

Mecanismo

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.

03Monitoramento

Agent oversight console.

A tela que uma equipe usaria para acompanhar esta matéria: suas medidas, estados e decisões. Os nomes são exemplos e os valores são ilustrativos.

Agent oversight console

Agentic systems · Agent sandbox · Session AG-6627

Human approval pendingGCRI · Inteligência artificial e sistemas autônomos

Tool calls

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

Políticas públicas

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

Actions by approval class

050100count this weekAutomáticoRegistradoAprovadoDeniedEscalado
Agent oversight console: the screen’s structure, terms and states for Agentic systems.Nomes de exemplo e valores ilustrativos; um projeto, não um registro nem um sistema ativo.
04Em todos os domínios

Agents that act need guardrails in every domain they touch.

Agentic system studies are designed for the série 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.
05Métodos e evidência

How agentic systems is modelled, measured and tested.

O modelo, os seus pressupostos, os seus dados e a sua incerteza, na forma que um cientista ou engenheiro verificaria. As estruturas seguem métodos publicados. Os valores representados são ilustrativos, não conclusões.

Modelo de sistema

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

++−+Inteligência artificialDadosComunidadesEconomiaR de reforçoB equilíbrio
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.
Princípios orientadores FAIR · GO FAIR e FORCE11W3C PROV · World Wide Web ConsortiumOrientação sobre o tratamento consistente das incertezas · IPCCCEOS Analysis Ready Data · Committee on Earth Observation Satellites
06Indicadores

O que é medido e com que qualidade.

Cada indicador leva sua unidade, sua periodicidade, o tipo de fonte por trás dele e a etiqueta de evidência que um valor levaria. Nenhum valor é mostrado: um programa os fornece sob sua própria autoridade.

IndicadorUnidadeCadênciaTipo de fonteRótulo
Task success rate on agent benchmarkspercent of tasks completed correctlyper evaluationAgent benchmark resultsREPORTADO
Actions requiring human approvalpercent of consequential actionsper deploymentDeployment configurationDECLARADO
Prompt injection success ratepercent of attempts succeedingper evaluationSecurity testingOBSERVADO
Agent incidentscount by severitymensalIncident reportsREPORTADO
Actions logged and attributablepercent of agent actionsper deploymentAudit logsOBSERVADO
Mean task length before human interventionsteps or minutesper evaluationEvaluation logsOBSERVADO
07Fontes

De onde vêm as evidências.

Conjuntos de dados públicos nomeados e registros institucionais, cada um com sua classe de licença. As fontes obtidas por acordo só são usadas nos seus termos e nunca são republicadas.

FonteO que ofereceClasse de licença
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 sistemasOpen, licence to check
Developer system cards describing agent safeguardsDeveloper-reported agent evaluations and controlsPublic documents, terms per developer
08Decisões

Quem decide, e a que servem as evidências.

Estúdio de Inteligência artificial e sistemas prepares evidence. The decisions below are taken by the authorities named, under their own rules, and never by the platform.

Quem decideA perguntaEvidências a que esta página serve
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
ReguladoresWhat oversight to require for autonomous AI actionsOversight design evidence

Produtos que este tema gera

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

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?
10Mecanismos

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. sistemas that coordinate several agents add further failure modes, as agents pass errors to each other or interact in unforeseen ways.

11Métodos e dados

Designing for safe execution.

  1. 01

    Least privilege

    Granting only the permissions a task needs, with sandboxes and spending or action limits, drawing on cibersegurança e criptografia.

  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 Engenharia de avaliação e garantia de IA. 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.

Os organismos e documentos à luz dos quais esta página é lida. O estado e as edições mudam; cada ligação leva ao organismo emissor.

14Perguntas

Perguntas e respostas.

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.
RelatóriosContribuir

Contribua com evidências a partir desta página.

Relatórios 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.

GCRIInteligência artificial e sistemas autônomosTecnologia exponencialEvidências de Labs
Inteligência artificial e sistemas autônomos

Traga um método, um conjunto de dados ou uma pergunta.

A informação e os pedidos estão abertos hoje. Um pedido recebe uma referência e indica o próximo passo; candidaturas, pagamentos, alocações de computação e registros só abrem quando existem a equipa, os termos e a capacidade de revisão.