> ## Documentation Index
> Fetch the complete documentation index at: https://labs.prompthon.io/llms.txt
> Use this file to discover all available pages before exploring further.

# Radar

<div className="not-prose my-4 rounded-md border border-gray-200 bg-gray-50 p-2 text-sm dark:border-gray-800 dark:bg-gray-900/40">
  <div className="mb-2 px-1 text-xs font-semibold uppercase tracking-wide text-gray-500 dark:text-gray-400">Need help?</div>

  <div className="flex flex-wrap gap-2">
    <a className="inline-flex items-center gap-2 rounded-md border border-gray-200 bg-white px-3 py-1.5 font-medium text-gray-700 no-underline shadow-sm hover:border-gray-300 hover:bg-gray-50 dark:border-gray-800 dark:bg-gray-950/60 dark:text-gray-200 dark:hover:bg-gray-900" href="https://discord.gg/sDE2HhGTg4" target="_blank" rel="noreferrer">
      <Icon icon="discord" iconType="brands" size={14} />

      <span>Ask in Discord</span>
    </a>

    <a className="inline-flex items-center gap-2 rounded-md border border-gray-200 bg-white px-3 py-1.5 font-medium text-gray-700 no-underline shadow-sm hover:border-gray-300 hover:bg-gray-50 dark:border-gray-800 dark:bg-gray-950/60 dark:text-gray-200 dark:hover:bg-gray-900" href="https://github.com/Prompthon-IO/agent-systems-handbook/issues/new/choose" target="_blank" rel="noreferrer">
      <Icon icon="github" iconType="brands" size={14} />

      <span>Open a GitHub issue</span>
    </a>

    <a className="inline-flex items-center gap-2 rounded-md border border-gray-200 bg-white px-3 py-1.5 font-medium text-gray-700 no-underline shadow-sm hover:border-gray-300 hover:bg-gray-50 dark:border-gray-800 dark:bg-gray-950/60 dark:text-gray-200 dark:hover:bg-gray-900" href="https://github.com/Prompthon-IO/agent-systems-handbook/blob/main/SUPPORT.md" target="_blank" rel="noreferrer">
      <Icon icon="life-ring" size={14} />

      <span>Support guide</span>
    </a>
  </div>
</div>

This lane is the fast-moving layer for changes in the field that should not be
forced into evergreen lab chapters too early.

## What belongs here

* Monthly or quarterly market updates
* New framework and protocol watch items
* Short notes on launches worth tracking
* Emerging categories and shifting terminology
* Curated editor picks and field notes

## Editorial intent

Keep entries short, timely, and easy to update. This is the easiest surface
for junior contributors and the fastest way for the repository to stay current
without destabilizing the evergreen structure.

## Current notes

* [June 2026 Agent Runtime Billing Watch](/radar/2026-06-agent-runtime-billing-watch):
  a current signal on separating local SDK orchestration, managed runtime
  metering, and authoritative billing surfaces for agent products.
* [June 2026 Agentic Resource Discovery Watch](/radar/2026-06-agentic-resource-discovery-watch):
  a current signal on searchable capability registries, `ai-catalog.json`,
  trust metadata, and discovery-before-execution boundaries for agents.
* [June 2026 Open Agent Training Environments Watch](/radar/2026-06-open-agent-training-environments-watch):
  a current signal on OpenEnv, stateful execution environments, and the
  separation between agent harnesses, environments, and reward loops.
* [June 2026 Prompt Injection Lockdown Mode Watch](/radar/2026-06-prompt-injection-lockdown-mode-watch):
  a current signal on Lockdown Mode, elevated-risk assistant surfaces,
  connector scope, and outbound-network containment for prompt injection.
* [June 2026 Agent-First Devices Watch](/radar/2026-06-agent-first-devices-watch):
  a current signal on Project Solara, agent-native runtimes, just-in-time UI,
  OS-enforced containment, and control-plane governance for local agents.
* [May 2026 Agentic Shopping Assistant Watch](/radar/2026-05-agentic-shopping-assistant-watch):
  a current signal on AI assistants moving from search and product comparison
  into scheduled actions, cart building, cross-device shopping memory, and
  review-before-checkout boundaries.
* [April 2026 Cyber Defense Access Policy Watch](/radar/2026-04-cyber-defense-access-policy-watch):
  a current signal on broad trusted cyber-defense access, gated frontier
  defensive releases, and access-aware agent runtime boundaries.
* [April 2026 Assistant Safety Escalation Watch](/radar/2026-04-assistant-safety-escalation-watch):
  a current signal on credible violence flags, duty-to-report boundaries,
  repeat policy violators, and audit-ready safety handoffs.
* [April 2026 Defense Agent Training Loop Watch](/radar/2026-04-defense-agent-training-loop-watch):
  a current signal on domain-specific field training, simulation-to-deployment
  loops, and high-risk autonomy boundaries.
* [April 2026 Portable Assistant Memory Watch](/radar/2026-04-portable-assistant-memory-watch):
  a time-scoped note on imported personal context, default-on assistant memory,
  and chat-history transfer as a separate trust boundary from retrieval and
  durable artifacts.
* [April 2026 Local Agent Watch](/radar/2026-04-local-agent-watch): a
  time-scoped note on local agents as a concrete product shape: nearby working
  environments, reusable skills or integrations, explicit context boundaries,
  and reviewable artifacts.
* [April 2026 Interoperability Watch](/radar/2026-04-interoperability-watch):
  a current field note on how A2A, A2UI, and MCP are separating into different
  interoperability layers.
* [Protocol Watch](/radar/2026-04-protocol-watch): a sample time-scoped note on
  how to track protocol boundaries without collapsing them together.