101 · 15 canons

Managed agents

The control planes, durable execution, sandboxes, logs and human approvals that let an agent keep working after the first model call ends.

TL;DR Managed agents are a systems problem around the model: durable state, isolated compute, tools, secrets, streaming, approvals and recovery. Read Anthropic and OpenAI for the hosted platforms, then Omnara for the open control-plane argument.

Curated by Ali Abouelatta

Cofounder of Lazyweb (a16z Speedrun). Previously grew subscriptions and built native ads at Duolingo. Writes First1000 (90,000+ subscribers).

Voices in this 101

Reading path 1

Understand the managed platform

These are the current first-party definitions from Anthropic and OpenAI. Compare what each platform owns before deciding what remains application code.

01
Claude Managed Agents overview ↗
Anthropic
Builder of Claude, MCP and Claude Managed Agents.
TL;DR
Claude Managed Agents supplies the harness, environments, sessions, tool execution and durable state around Claude so teams do not rebuild the control plane.
What you'll read
The core objects, execution lifecycle, security model and the boundary between Anthropic's managed layer and the agent you define.
02
Claude Managed Agents: get to production faster ↗
Anthropic
Builder of Claude, MCP and Claude Managed Agents.
TL;DR
Anthropic positions managed agents as composable cloud infrastructure for long-running work, not another prompt template or chatbot framework.
What you'll read
The launch case, agent-environment-session model, examples, observability and the product decisions behind the hosted service.
03
Scaling Managed Agents: decoupling the brain from the hands ↗
Anthropic
Builder of Claude, MCP and Claude Managed Agents.
TL;DR
Separating model reasoning from execution workers lets the platform scale, recover and secure long-running agents without tying identity to one process.
What you'll read
Anthropic's architecture for orchestration, sandboxes, event streams, state, permissions and production scaling.
04
Introducing the Agents API ↗
OpenAI
Builder of ChatGPT, Codex, Site Tools, workspace agents and ChatGPT ads.
TL;DR
OpenAI's Agents API exposes managed cloud agents powered by the Codex harness, with long-running sessions, environments and orchestration behind one API.
What you'll read
The API object model, environment choices, tool execution, streaming and the relationship between a managed service and the Codex harness.
05
Introducing workspace agents in ChatGPT ↗
OpenAI
Builder of ChatGPT, Codex, Site Tools, workspace agents and ChatGPT ads.
TL;DR
Workspace agents package repeatable, connected workflows for teams and run them in the cloud through ChatGPT's shared work surface.
What you'll read
How a business creates, connects, publishes and governs agents that can work across team knowledge and applications.

Reading path 2

Read the open control-plane argument

Omnara's founders make the counter-case: durable agent infrastructure should be model-, machine- and harness-independent, with the event log as the stable identity.

06
Omnara introduction ↗
Ishaan Sehgal
Omnara cofounder writing about durable, serverless managed agents.
TL;DR
Omnara is an open-source control plane that manages execution and state while letting the builder choose models, tools, machines and deployment.
What you'll read
The platform objects, event stream, sessions, machines, approvals and the portability promise behind an open managed-agent layer.
07
The Log Is the Agent ↗
Ishaan Sehgal
Omnara cofounder writing about durable, serverless managed agents.
TL;DR
An agent's durable identity is the append-only history of inputs, outputs, tool calls and state transitions—not the current model process.
What you'll read
A systems argument for event sourcing, replay, recovery, portability and observability across models and machines.
08
Serverless Agents ↗
Ishaan Sehgal
Omnara cofounder writing about durable, serverless managed agents.
TL;DR
If no machine owns the loop, an agent can pause, resume and move across compute while the control plane preserves state and intent.
What you'll read
The architecture tradeoffs behind decoupled execution, durable queues, resumability and assigning work to ephemeral machines.
09
What Is an Async Agent, Really? ↗
Kartik Sarangmath
Omnara cofounder writing about harnesses and asynchronous agents.
TL;DR
Async agents are not just slow requests; they need a durable interaction model for later input, approvals, progress and failure.
What you'll read
A conceptual teardown of asynchronous work, sessions, user return paths and what a platform must remember after the request ends.
10
The Harness Doesn't Matter ↗
Kartik Sarangmath
Omnara cofounder writing about harnesses and asynchronous agents.
TL;DR
Most agent harnesses reduce to a small loop; durable state, tools, permissions and operations create more differentiation than another wrapper around that loop.
What you'll read
A deliberately contrarian explanation of the harness core and the infrastructure that begins where the simple loop stops.

Reading path 3

Watch the builders explain the hard parts

These talks are the shortest path to the operating details: long horizons, memory, recovery, safety and shipping a real managed agent.

11
Ship your first Managed Agent ↗
Anthropic
Builder of Claude, MCP and Claude Managed Agents.
TL;DR
A working incident-investigator agent makes the managed platform concrete: define an agent, environment and session, then stream and supervise the run.
What you'll read
A 37-minute first-party build walkthrough covering setup, tools, execution, events and production-shaped debugging.
12
Claude for Long-Horizon Tasks ↗
Lance Martin
Anthropic engineer and speaker on long-horizon Claude agent harnesses.
TL;DR
Long-horizon reliability comes from the harness and environment around Claude: decomposition, state, feedback, security and recovery.
What you'll read
An Anthropic engineer's lessons from building agents that work for longer than one turn, presented at AI Engineer.
13
Memory and dreaming for self-learning agents ↗
Anthropic
Builder of Claude, MCP and Claude Managed Agents.
TL;DR
Agent memory needs deliberate consolidation and reflection; saving every token is not the same as learning from experience.
What you'll read
A first-party session on memory design, offline reflection, durable knowledge and the risks of self-modifying agent behavior.
14
Building more effective AI agents ↗
Anthropic
Builder of Claude, MCP and Claude Managed Agents.
TL;DR
Reliable agent systems start with simple workflows and add autonomy only when the task and evidence justify the extra uncertainty.
What you'll read
Anthropic's patterns for prompt chaining, routing, parallelization, orchestrator-workers and evaluator-optimizer loops.
15
Workspace agents ↗
OpenAI
Builder of ChatGPT, Codex, Site Tools, workspace agents and ChatGPT ads.
TL;DR
A managed team agent combines instructions, knowledge, tools, publishing controls and repeatable runs inside a shared workspace.
What you'll read
OpenAI's practical guide to agent anatomy, workflow examples, connections, testing and team deployment in ChatGPT.