Managed Agents: who runs the loop, a 45-minute workshop
With JavaScript off, the slides and their notes read as one page; the figures and the presses need JavaScript.
Managed Agents: who runs the loop
Phil Wagner · [Event]
github.com/brokenairplane/managed-agent-session
Session goal
- Engineers, and anyone new to agents
- Evaluate what parts of an agent run on the developer's side or Anthropic's side
Today we work in the lab. Coding is not required: everyone is welcome to stay.
Setup · runs while the talk goes on
Run these three lines now
Short link: [SHORT-LINK]
git clone https://github.com/ brokenairplane/ managed- agent- session cd managed-agent- session python3 lab/setup_lab.py --no-key
While setup runs, open lab/ in a browser.
In the lab: the loop the sandbox the wire call or send return or stream
The page at 2am
The request: an agent that handles the first hour of working out what broke, with nobody at the keyboard.
Name one job from your own team's work that an agent could run unattended.
Managed Agents in context
Click a word to see where the thing the word names sits on the map.
What do you want to own?
* the wire: the network boundary. Between the app and Anthropic only API calls and streamed events cross it.
Demo: the 2am triage agent's first send
Managed Agents, cloud sandbox
Skipped the setup?
Short link: [SHORT-LINK]
git clone https://github.com/ brokenairplane/ managed- agent- session cd managed-agent- session python3 lab/setup_lab.py --no-key
Already ran them? Open lab/ in a browser.
In pairs · 4 minutes
Task: Who answers a pause
- Open lab/index.html in a browser; it opens on Task: Who answers a pause
- Click Show the diagram, drag Replay step to 1, then click
Next step for each step, naming it a send, a watch or an answer
- In bash runs only after, select a person (always_ask) so bash waits for approval; predict which step moves, then click
Next step again
In the lab: the loop the sandbox the wire call or send return or stream
Lab: Who answers a pause, live
- The lab, open on Task: Who answers a pause
- Click Next step to walk the run, one step at a time
Pick what the on-call team stops owning
| Loop run by | Sandbox run by | |
|---|---|---|
| developer | developer | |
| developer | developer | |
| Anthropic | developer | |
| Anthropic | Anthropic |
Which way runs the loop in your own process, using Anthropic's library? Choose one.
Lab · 25 minutes
Task: Where the loop lives
- Open lab/index.html in a browser
- Open lab/index.html in a browser
- Select Task: Where the loop lives
- Select a job
- Drag the loop and sandbox boxes to the side that runs each
- Click Check to see the result
This task comes after the pairs' Task: Who answers a pause.
Lab: Where the loop lives, live
- The lab, open on Task: Where the loop lives
- Drag the boxes the way a group placed them, then click Check
With Managed Agents, the developer's app sends events, watches them, and answers the agent; Anthropic runs the loop and the sandbox.
Questions?github.com/brokenairplane/managed-agent-session[handle]
Lab progress stays in the browser until the learner copies a summary
Feedback preview
{
"lab_version": 1,
"day": "2026-12-03",
"task_reached": 3,
"tasks_made": ["d1", "pauses"],
"misses_per_row": { "pause:bash": 2 },
"second_miss_hint_shown": true,
"time_on_task": {
"task_1": "1 to 5 min",
"task_2": "5 to 15 min",
"task_3": "under 1 min",
"task_4": "under 1 min"
}
}- Click Feedback: preview what would be shared to review the summary
- Click Copy to take the summary out of the browser and share it
Anonymous feedback: [FEEDBACK-LINK]
Which is the highest that is true for you now? Choose one.
After the talk
Frequently asked questions
One slide per question, listed on the next slide.
FAQ
- Settings, run by run
- What the agent may do
- What to create, in order
- Session cost
- Beta header
- Custom tools and MCP
- Permission policies
- Auto mode
- Why a session went idle
- Streaming text
- Default network access
- Giving the agent files
- Capping spend
- SDK, Managed Agents or Messages API
- Self-hosted sandboxes
- Web tools under limited networking
- Agent updates mid-session
- Long runs and context
- Delegation and schedules
- ZDR and HIPAA
- Rate limits
- AWS, Google Cloud, Bedrock
- Ready to run unattended
- Production monitoring
- Subscription or API billing
- Where to go next
Which step of the triage run does each setting change? Click a run
Loading the four recorded runs
Which settings decide what the agent may do?
- Create the agent: model, prompt, tools
- Create the environment: where tools run
- Start the session: one run
- Send a message
Click a setting to see where the setting sits on the map.
What do I actually create, in what order?
Agent, then environment, then a session
What does a session cost?
Tokens, plus $0.08 per running session-hour
A budget sets a ceiling on the session's cost at published prices; at the ceiling the session goes idle and keeps its history
Is there a beta header, and do I set the header?
Required on every call; the SDKs set it
Are custom tools handled through MCP?
No: the app runs a custom tool
What permission policies exist, and what are the defaults?
always_ask: bash waits for the app's yes
Custom tools: the app decides, no policy
Is auto a human-in-the-loop checkpoint?
No: the server judges each call
My session went idle. How do I know why?
Read the idle event's stop reason
How do I show text while the agent writes?
Event deltas give a live preview
What network access does an environment get by default?
Unrestricted, unless the request says otherwise
How do I give the agent files?
Upload, then mount: read-only copies
How do I stop an unattended run from overspending?
Set a session budget at creation
Agent SDK, Managed Agents, or the Messages API: how do I choose?
The SDK's loop runs in the developer's process
| Loop run by | Sandbox run by | |
|---|---|---|
| developer | developer | |
| Anthropic | Anthropic |
Self-hosted environment: where does the sandbox run?
A self-hosted sandbox moves the sandbox, not the loop
| Loop run by | Sandbox run by | |
|---|---|---|
| Anthropic | developer | |
| Anthropic | Anthropic |
Does limited networking also govern web search and web fetch?
Yes, under limited networking
If I update the agent, do running sessions change?
Not if the session pins a version
What happens on long runs that exceed the context window?
The service compacts the history
Can agents delegate to other agents or run on a schedule?
Yes: threads, workflow runs, schedules
Can we use Managed Agents under Zero Data Retention or HIPAA?
Hosted: not eligible. Self-hosted Managed Agents: ZDR exception
| Transcript kept by | |
|---|---|
| developer | |
| Anthropic | |
| Anthropic |
What are the rate limits at scale?
300 a minute to create, 1,200 to read
Is Managed Agents on AWS or Google Cloud, and how does Bedrock AgentCore compare?
On both, with some differences
How do I know the agent is good enough to run unattended?
Evals before launch, many trials
What should production monitoring look like?
Alert on idle, budget and termination
Can learners use their Claude subscription instead of API billing?
Max and Team plans include API credits
Where to keep going: the docs, the tutorial, the podcast
- Docs: Managed Agents overview
- Docs: Reference, every event and field
- Docs: Events and streaming, in and out
- Tutorial: Quickstart, a first session
- Tutorial: this workshop's lab README