Skip to content

GCRI · الذكاء الاصطناعي والنظم المستقلة

الأنظمة الوكيلة

Agentic AI النظم 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.

02السؤال

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.

الآلية

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.

الآلية

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.

الآلية

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.

الآلية

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.

03الرصد

Agent oversight console.

الشاشة التي قد يستخدمها فريق لمتابعة هذا الموضوع: مقاييسه وحالاته وقراراته. والأسماء أمثلة والقيم توضيحية.

Agent oversight console

Agentic systems · Agent sandbox · Session AG-6627

Human approval pendingGCRI · الذكاء الاصطناعي والنظم المستقلة

Tool calls

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

السياسات

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

Actions by approval class

050100count this weekتلقائيمسجلمعتمدDeniedمُصعَّد
Agent oversight console: the screen’s structure, terms and states for Agentic systems.أسماء مثالية وقيم توضيحية؛ تصميم وليس سجلًا ولا نظامًا حيًا.
04عبر المجالات

Agents that act need guardrails in every domain they touch.

05الأساليب والأدلة

How agentic systems is modelled, measured and tested.

النموذج وافتراضاته وبياناته وعدم اليقين فيه، بالصورة التي يفحصها بها عالم أو مهندس. وتتبع البنى أساليب منشورة. والقيم المرسومة توضيحية، وليست نتائج.

نموذج النظام

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

++−+الذكاء الاصطناعيالبياناتالمجتمعاتالاقتصاد⁨R⁩ معزِّزة⁨B⁩ موازِنة
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.
مبادئ FAIR التوجيهية · GO FAIR وFORCE11⁨W3C PROV⁩ · اتحاد الشبكة العالميةإرشادات بشأن المعالجة المتسقة لأوجه عدم اليقين · الهيئة الحكومية الدولية المعنية بتغير المناخبيانات CEOS الجاهزة للتحليل · لجنة سواتل رصد الأرض
06المؤشرات الفرعية

ما الذي يُقاس، ومدى جودة قياسه.

يحمل كل مؤشر وحدته ووتيرته ونوع المصدر الذي يستند إليه ووسم الأدلة الذي ستحمله القيمة. ولا تُعرض أي قيم: فالبرنامج يقدّمها بموجب سلطته الخاصة.

المؤشرالوحدةوتيرة الإصدارنوع المصدرالوسم
Task success rate on agent benchmarkspercent of tasks completed correctlyper evaluationAgent benchmark resultsمُبلَّغ عنه
Actions requiring human approvalpercent of consequential actionsper deploymentDeployment configurationمُعلَن
Prompt injection success ratepercent of attempts succeedingper evaluationSecurity testingمرصود
Agent incidentscount by severityشهريIncident reportsمُبلَّغ عنه
Actions logged and attributablepercent of agent actionsper deploymentAudit logsمرصود
Mean task length before human interventionsteps or minutesper evaluationEvaluation logsمرصود
07المصادر

من أين تأتي الأدلة.

مجموعات بيانات عامة مسمّاة وسجلات مؤسسية، لكلٍّ منها فئة ترخيصها. ولا تُستخدم المصادر المتاحة بموجب اتفاق إلا وفق شروطها، ولا يُعاد نشرها أبدًا.

المصدرما يقدّمهفئة الترخيص
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 النظمOpen, licence to check
Developer system cards describing agent safeguardsDeveloper-reported agent evaluations and controlsPublic documents, terms per developer
08القرارات

من يقرر، وما الذي تخدمه الأدلة.

استوديو الذكاء الاصطناعي و النظم prepares evidence. The decisions below are taken by the authorities named, under their own rules, and never by the platform.

من يقررالسؤالالأدلة التي تخدمها هذه الصفحة
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
الجهات التنظيميةWhat oversight to require for autonomous AI actionsOversight design evidence

المخرجات التي يُنتجها هذا الموضوع

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

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?
10الآليات

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

11المناهج والبيانات

Designing for safe execution.

  1. 01

    Least privilege

    Granting only the permissions a task needs, with sandboxes and spending or action limits, drawing on الأمن السيبراني والتشفير.

  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 هندسة تقييم الذكاء الاصطناعي وضمانه. 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.

الهيئات والوثائق التي تُقرأ هذه الصفحة في ضوئها. وتتغير الحالات والإصدارات؛ ويقود كل رابط إلى الهيئة المُصدِرة.

14أسئلة

أسئلة وأجوبة.

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.
التقاريرساهم

ساهم بأدلة من هذه الصفحة.

التقارير 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.

GCRIالذكاء الاصطناعي والنظم المستقلةالتقنيات الأسيةأدلة Labs
الذكاء الاصطناعي والنظم المستقلة

قدّم منهجية أو مجموعة بيانات أو سؤالا.

المعلومات والاستفسارات متاحة اليوم. ويحصل الاستفسار على رقم مرجعي ويحدد الخطوة التالية؛ ولا تُفتح الطلبات والمدفوعات وتخصيصات الحوسبة والتسجيلات إلا حين يتوافر فريقها وشروطها وقدرة المراجعة.