The Polyaxon agent sandbox roadmap
Our plans for persistent sandbox workspaces, suspend/resume, activity-aware idle suspension, and ready pools on Kubernetes—and where AX and Substrate differ.
RoadmapSandboxesAI Agents
AI Agents
Explore practical AI agent guides covering architecture, evaluation, sandboxed execution, tracing, security, and production operations.
Start here
Essential guides, selected for this topic.
Kubernetes for AI agents: A platform engineering guide
Design a Kubernetes platform for AI agents with clear workload boundaries, durable state, scoped access, resource controls, and end-to-end evidence.
AI AgentsKubernetesInfrastructure
Choose an AI agent architecture for production
Map agent architectures to Polyaxon jobs, services, and DAGs, with concrete workload configuration and a repeatable architecture-comparison workflow.
AI AgentsOrchestrationGuides
Sandbox AI agents on Kubernetes
Design isolated Kubernetes execution for AI agents with a threat model, stronger runtimes, scoped identity, controlled egress, bounded storage, and auditable cleanup.
AI AgentsKubernetesSecurity
Orchestrate parallel coding agents with Polyaxon
Run parallel coding agents in separate Polyaxon workspaces, collect candidate patches, evaluate independently, and merge only reviewed changes.
AI AgentsSandboxesCollaboration
Designing the runtime layer for AI agents
Design agent execution around durable state, safe tool retries, approval waits, and recovery, with clear responsibilities for Polyaxon and your agent framework.
AI AgentsOrchestrationGuides
Latest articles
The latest guides, tutorials, and product updates.
Recover agent actions after a lost tool response
Reconcile uncertain tool effects, preserve approval and cancellation across task changes, and compare recovery policies using final-state evidence.
AI AgentsOrchestrationReliability
Optimize a small-model harness with autoresearch on Polyaxon
Build a measured research loop around Jev or a self-hosted classifier using Polyaxon jobs, sandboxes, experiment matrices, and per-case evidence.
LLMOpsAutoresearchClassification
Autoresearch as a controlled experiment
A design note on autonomous experimentation: fixed protocols, selection bias, independent evaluation, and durable research campaigns in Polyaxon.
RoadmapAI AgentsExperimentation
Build a coding agent with Polyaxon sandboxes
Give an open model a bounded read, edit, and check loop in a Polyaxon workspace, then retain the patch and evidence behind its completion claim.
AI AgentsSandboxCode Execution
The Polyaxon agent sandbox roadmap
Our plans for persistent sandbox workspaces, suspend/resume, activity-aware idle suspension, and ready pools on Kubernetes—and where AX and Substrate differ.
RoadmapSandboxesAI Agents
Design multi-tenant AI agent infrastructure on Kubernetes
Separate identity, network access, data, queues, budgets, and evidence when multiple teams or customers run AI agents on shared Kubernetes infrastructure.
AI AgentsKubernetesSecurity
Sandbox AI agents on Kubernetes
Design isolated Kubernetes execution for AI agents with a threat model, stronger runtimes, scoped identity, controlled egress, bounded storage, and auditable cleanup.
AI AgentsKubernetesSecurity
Pods, Jobs, or Services for AI agents?
Choose the Kubernetes execution shape for an AI agent by separating logical task identity from Pods, Jobs, Services, workflows, and sandbox lifecycles.
AI AgentsKubernetesGuides
Orchestrate parallel coding agents with Polyaxon
Run parallel coding agents in separate Polyaxon workspaces, collect candidate patches, evaluate independently, and merge only reviewed changes.
AI AgentsSandboxesCollaboration
Kubernetes for AI agents: A platform engineering guide
Design a Kubernetes platform for AI agents with clear workload boundaries, durable state, scoped access, resource controls, and end-to-end evidence.
AI AgentsKubernetesInfrastructure
Beyond agent traces: State, artifacts, and recovery
Connect agent traces to checkpoint state, versioned artifacts, action receipts, and evaluations so failures lead to controlled recovery and reproducible improvements.
AI AgentsObservabilityEvaluation
Design measurable AI agents before you build
Define agent outcomes, prohibited actions, events, evaluators, budgets, segments, and feedback loops before implementation begins.
AI AgentsEvaluationObservability
Build an operating model for agentic AI
Operate agentic AI with explicit service ownership, platform contracts, task lifecycle rules, change control, incident response, SLOs, and financial accountability.
AI AgentsPlatform EngineeringOperations
Design production security for AI agents
Contain AI agent identity, tools, memory, network access, and delegated actions with enforceable production boundaries.
AI AgentsSecurityGovernance
Connect agent execution to the ML platform
Connect AI agent execution to Polyaxon projects, components, scheduling, tracking, and artifacts through a stable application-owned execution contract.
AI AgentsMLOpsArchitecture
Build a shared library of agent evaluators
Package application-owned agent evaluators as versioned Polyaxon components with typed contracts, reusable execution profiles, and consistent result evidence.
AI AgentsEvaluationAutomation
Operating long-running AI agents
Choose jobs, services, queues, and capacity controls for agent workloads using task duration, dependency limits, resume latency, and execution cost.
AI AgentsOrchestrationKubernetes
An AI agent deployment checklist for the first production release
Build an agent release checklist around Polyaxon qualification jobs, versioned components, artifact reports, termination settings, and manual approval.
AI AgentsLLMOpsGuides
Build a reliable foundation for autonomous agents
Build an operational foundation for autonomous agents using Polyaxon workload profiles, durable state, bounded authority, evaluation, and recovery ownership.
AI AgentsPlatform EngineeringReliability
Durable execution for AI agents
Build agent recovery around committed checkpoints, versioned inputs, safe side effects, and approval state so interrupted tasks can continue reliably.
AI AgentsOrchestrationGuides
Designing a control plane for AI agents
Separate live agent requests from versioning, evaluation, policy, rollout, identity, evidence, and recovery across the application lifecycle.
AI AgentsOrchestrationObservability
MCP security testing: tools, permissions, and untrusted content
Build MCP security tests for tool discovery, authorization, injected tool results, session identity, and approval boundaries in AI agents.
MCPRed TeamingAI Agents
Designing the runtime layer for AI agents
Design agent execution around durable state, safe tool retries, approval waits, and recovery, with clear responsibilities for Polyaxon and your agent framework.
AI AgentsOrchestrationGuides
Measure AI agent workflow bottlenecks
Measure Polyaxon agent workflow bottlenecks across planning, queueing, execution, transfers, and evaluation using critical-path timing and quality-aware comparisons.
AI AgentsPerformanceObservability