Phase 4
Trainings

Source: c133 Remediation Training, Phase 3, 2026-11-11 · the collection in app/data/trainings/<lang>/, read by app/data/trainings/parse.ts for the lab and for the API

The design site is the studio (D4): one markdown file per training and language, written once with {slots} and filled from the finding. This page lists the collection as the lab reads it, checks every sentence against the brand voice rules as the person would read it on each finding of its policy, and opens any training on any of those findings in the mock. What the apps read is the same files through the same parser, published at /api/trainings (D21).

The format: authoring.md · what the apps read: publish.md · the loop for a new training: the /training skill

The collection

9 trainings published
TrainingPolicy or topicMinutesStepsQuestionsLangVersionVoiceOpen on a finding of its policy
Approved model providers →
T-PROVIDERS-1
Approved model providers only
P-PROVIDERS
344env1pass
67 texts · 1 finding
Ask before an agent sends or publishes →
T-APPROVAL-1
Consequential tool calls require approval
P-TOOL-APPROVAL
344env1pass
58 texts · 1 finding
Instructions hidden in content →
T-INJECT-1
Prompts are inspected for injection and leakage
P-PROMPT-INSPECT
344env1pass
63 texts · 1 finding
Observe and Enforce →
T-MODES-1
Observe and Enforce
topic: observe-and-enforce
244env1pass
46 texts · 0 findings
a topic, no finding: take it on its own →
Personal accounts for work →
T-ACCT-1
Personal account is in use
P-ACCT
344env1pass
80 texts · 1 finding
Secrets in prompts →
T-SECRETS-1
Credentials must not be sent to a model
P-CREDENTIALS
344env1pass
59 texts · 1 finding
Skills that update themselves →
T-PROVENANCE-1
MCP servers and skills are pinned to reviewed versions
P-PROVENANCE
344env1pass
58 texts · 0 findings
no finding under P-PROVENANCE in this world
Unapproved MCP servers →
T-MCP-1
Unsanctioned MCP server in use
P-MCP
344env1pass
86 texts · 3 findings
Unattended agents and their spend →
T-SPEND-1
Spend stays under the ceiling
P-SPEND
344env1pass
53 texts · 0 findings
no finding under P-SPEND in this world

Approved model providers

app/data/trainings/en/approved-model-providers.mdv1 · sha256:39ef31c9c92add262aa3f4087b372035d9dc83f46fd9df12a8ab431eedffe634/api/trainings/T-PROVIDERS-1

Lesson · 4 steps

  1. 1What happened on {device}provider-request · motion
  2. 2Where a prompt goesprovider-terms
  3. 3What Qpoint does about itpolicy-modes
  4. 4What to do insteadmode-ask· instead

Check · 4 questions

  1. 1Your agent sends a prompt to a provider that is not on the approved list. What goes with it?→ where-prompts-go
  2. 2Why does it matter which provider a prompt reaches?→ where-prompts-go
  3. 3A colleague shares a cheaper model that works well for your task. What do you do?→ instead
  4. 4A model your agent uses asks for a card's expiry date and security code "to verify a refund". What do you do?→ instead

Slots it reads

{agent} {approved} {blocked} {date} {device} {evidence} {minutesWord} {outcome} {owner} {policy} {provider} {session} {team} {time}

On its own (the library)

4 of 4 steps and 4 of 4 questions, as User A reads it with no finding. In the file's own words for the library (D38): what-happened.

Voice

Zero violations across 67 texts: the file as written, as read on F-F, and as read on its own (productUI).

Ask before an agent sends or publishes

app/data/trainings/en/ask-before-an-agent-sends-or-publishes.mdv1 · sha256:38bb5adc55221d1dd5cc61265bab72440a19de40c6aa749ba890306f01d236ea/api/trainings/T-APPROVAL-1

Lesson · 4 steps

  1. 1What happened on {device}unapproved-call · motion
  2. 2Which calls should wait for youconsequential-calls
  3. 3What Qpoint does about itpolicy-modes
  4. 4What to do insteadapprove-call· instead

Check · 4 questions

  1. 1Which of these should your agent ask you about before it does it?→ consequential
  2. 2You ask your agent to "share the export with Sam". What decides how it shares it?→ consequential
  3. 3Your agent asks you to approve a call that shows public: true. What do you do?→ instead
  4. 4Your agent offers to stop asking before it sends mail for the rest of the session. What do you choose?→ instead

Slots it reads

{agent} {blocked} {date} {device} {evidence} {minutesWord} {outcome} {owner} {policy} {session} {time} {tool}

On its own (the library)

4 of 4 steps and 4 of 4 questions, as User A reads it with no finding. In the file's own words for the library (D38): what-happened.

Voice

Zero violations across 58 texts: the file as written, as read on F-I, and as read on its own (productUI).

Instructions hidden in content

app/data/trainings/en/instructions-hidden-in-content.mdv1 · sha256:188fc4696bbc771738d9aa0d9b254a00159da2f3bbe5b3097408763d8c8ddc58/api/trainings/T-INJECT-1

Lesson · 4 steps

  1. 1What happened on {device}hidden-instruction · motion
  2. 2Why an agent follows text it readsone-context
  3. 3What Qpoint does about itmode-observe · motion
  4. 4What to do insteadapprove-send· instead

Check · 4 questions

  1. 1You ask your agent to summarise an email. A line in it, invisible to you, tells the agent to send your files somewhere. Why might the agent do it?→ one-context
  2. 2Prompt inspection flagged a hidden instruction in what your agent read. What did that stop?→ what-qpoint-does
  3. 3Your agent is working through a web page and proposes sending a file to an address you have never seen. What do you do?→ instead
  4. 4Which setting gives a hidden instruction the least room to act?→ instead

Slots it reads

{agent} {blocked} {date} {device} {evidence} {heuristics} {heuristicsOffSentence} {minutesWord} {outcome} {owner} {policy} {session} {time} {via}

On its own (the library)

4 of 4 steps and 4 of 4 questions, as User A reads it with no finding. In the file's own words for the library (D38): what-happened.

Voice

Zero violations across 63 texts: the file as written, as read on F-H, and as read on its own (productUI).

Observe and Enforce

app/data/trainings/en/observe-and-enforce.mdv1 · sha256:67e66883351c95398795897fe33f2761af6d52f487a51f4e95bc6e6fb0ac1a9b/api/trainings/T-MODES-1
Open the prototype →on its own, as User A takes it from the library

Lesson · 4 steps

  1. 1What a policy does on {device}policy-modes
  2. 2Observe: the work goes through, and it is written downmode-observe · motion
  3. 3Enforce: the action is stoppedmode-enforce
  4. 4What to do when a policy stops your workmode-ask· instead

Check · 4 questions

  1. 1On your team, a policy is set to Observe. Your agent does something the policy covers. What happens?→ observe
  2. 2A policy is set to Enforce. Where does qcontrol stop the action?→ enforce
  3. 3Who decides whether a policy observes or enforces on your team?→ three-modes
  4. 4A policy stopped something your work needs. What do you do?→ when-stopped

Slots it reads

{agent} {device} {minutesWord} {team}

On its own (the library)

4 of 4 steps and 4 of 4 questions, as User A reads it with no finding. Written for anyone: a topic has no finding to leave out (D49).

Voice

Zero violations across 46 texts: the file as written, as read on no finding, and as read on its own (productUI).

Personal accounts for work

app/data/trainings/en/personal-accounts-for-work.mdv1 · sha256:5f4eca745e9af12e70a10d9ec13df4ee69384de297c4d2ce191d98dc25d0550f/api/trainings/T-ACCT-1

Lesson · 4 steps

  1. 1What happened on {device}account-session · motion
  2. 2Where the work goesaccount-boundary
  3. 3How to tell which account a session usesaccount-check
  4. 4What to do insteadaccount-switch· instead

Check · 4 questions

  1. 1You are signed in to {agent} with {account} and use it for a work task. Whose terms cover what the session sent?→ where-it-goes
  2. 2Which account does a session in {agent} run under?→ which-account
  3. 3This policy cannot block a sign-in, so nothing was stopped. Why does the finding still matter?→ what-happened
  4. 4You do not have a seat on your organisation's {agent} account yet, and a task is due today. What do you do?→ instead

Slots it reads

{account} {agent} {blocked} {date} {device} {evidence} {exceptionSentence} {minutesWord} {outcome} {owner} {policy} {session} {time}

On its own (the library)

4 of 4 steps and 4 of 4 questions, as User A reads it with no finding. In the file's own words for the library (D38): what-happened, q-record.

Voice

Zero violations across 80 texts: the file as written, as read on F-C, and as read on its own (productUI).

Secrets in prompts

app/data/trainings/en/secrets-in-prompts.mdv1 · sha256:5c9780085bcefa460897a26f617780c8fbf841495c8787f4e6b8ec11c042f715/api/trainings/T-SECRETS-1

Lesson · 4 steps

  1. 1What happened on {device}secret-prompt · motion
  2. 2Why a key in a prompt is a key disclosedsecret-copies
  3. 3What to do about this keysecret-rotate
  4. 4What to do insteadsecret-reference· instead

Check · 4 questions

  1. 1Your prompt had a key in it, and the agent sent it. A minute later you deleted the conversation. Is the key safe now?→ why-disclosed
  2. 2A key you pasted reached the model. What makes that key safe again?→ this-key
  3. 3Your agent needs a database password to run a migration. How does it get the password?→ instead
  4. 4qcontrol did not flag a prompt you sent. Does that mean the prompt had no secret in it?→ instead

Slots it reads

{aDataClass} {agent} {blocked} {date} {detectors} {detectorsOffSentence} {device} {evidence} {keyAdvice} {minutesWord} {outcome} {owner} {policy} {session} {time}

On its own (the library)

4 of 4 steps and 4 of 4 questions, as User A reads it with no finding. In the file's own words for the library (D38): what-happened, this-key.

Voice

Zero violations across 59 texts: the file as written, as read on F-G, and as read on its own (productUI).

Skills that update themselves

app/data/trainings/en/skills-that-update-themselves.mdv1 · sha256:d5695a3aee631ffc6373b17cd6e6350a260fe30ea56cb3833fa5dc31812279a2/api/trainings/T-PROVENANCE-1
Open the prototype →on its own, as User A takes it from the library

Lesson · 4 steps

  1. 1What happened on {device}version-load · motion
  2. 2Why a new version mattersversion-trust
  3. 3What Qpoint does about itmode-observe · motion
  4. 4What to do insteadpin-version· instead

Check · 4 questions

  1. 1A skill you use every day publishes a new version overnight. What decides what it does in your next session?→ new-version
  2. 2qcontrol recorded a skill loading at a version nobody pinned. What did that stop?→ what-qpoint-does
  3. 3Your agent offers to update a server to its latest version. What do you do?→ instead
  4. 4A skill version nobody reviewed has already run and read your key files. What do you do?→ instead

Slots it reads

{agent} {blocked} {component} {date} {device} {evidence} {minutesWord} {outcome} {owner} {pinned} {pinnedSentence} {policy} {session} {time}

On its own (the library)

4 of 4 steps and 4 of 4 questions, as User A reads it with no finding. In the file's own words for the library (D38): what-happened.

Voice

Zero violations across 58 texts: the file as written, as read on no finding, and as read on its own (productUI).

Unapproved MCP servers

app/data/trainings/en/unapproved-mcp-servers.mdv1 · sha256:bc19dbf8d6099a972c1601513329f239717424d1abc7dff1f611c6b75fba4864/api/trainings/T-MCP-1

Lesson · 4 steps

  1. 1What happened on {device}connection · motion
  2. 2What an MCP server can doserver-reach · motion
  3. 3Why there is a sanctioned listsanctioned-list
  4. 4What to do insteadask· instead

Check · 4 questions

  1. 1You let an agent connect to an MCP server you have not used before. After that, what decides what the agent can do through the server?→ server-reach
  2. 2{server} is sanctioned for {exceptionTeam}. Does that make it sanctioned for {team} too?→ why-the-list
  3. 3Your work needs an MCP server that is not on your team's sanctioned list. What do you do?→ instead
  4. 4On {team}, this policy is set to Observe, not Enforce. An agent connects a server that is not sanctioned. What happens?→ what-happened

Slots it reads

{agent} {blocked} {date} {device} {evidence} {exceptionSentence} {exceptionTeam} {minutesWord} {outcome} {owner} {policy} {sanctioned} {server} {session} {team} {time}

On its own (the library)

4 of 4 steps and 4 of 4 questions, as User A reads it with no finding. In the file's own words for the library (D38): what-happened, q-observe.

Voice

Zero violations across 86 texts: the file as written, as read on F-A, F-B, F-E, and as read on its own (productUI).

Unattended agents and their spend

app/data/trainings/en/unattended-agents-and-their-spend.mdv1 · sha256:2d3b3d1da9d7853002c9e8a3285f932d08ecee48dc1781cff5dd2af644bec455/api/trainings/T-SPEND-1
Open the prototype →on its own, as User A takes it from the library

Lesson · 4 steps

  1. 1What happened on {device}spend-ceiling · motion
  2. 2How an agent on its own runs up a billretry-loop
  3. 3What Qpoint does about itmode-observe · motion
  4. 4What to do insteadagent-limit· instead

Check · 4 questions

  1. 1An agent left overnight retries a failing test every forty seconds. What does each retry cost?→ retry-loop
  2. 2Your agent passed the spend ceiling during the night. What did Qpoint do?→ what-qpoint-does
  3. 3Before you leave an agent running on its own, what helps most?→ instead
  4. 4You come in and find your agent still retrying the same step. What do you do?→ instead

Slots it reads

{agent} {blocked} {ceiling} {ceilings} {date} {device} {evidence} {minutesWord} {outcome} {owner} {policy} {session} {time}

On its own (the library)

4 of 4 steps and 4 of 4 questions, as User A reads it with no finding. In the file's own words for the library (D38): what-happened.

Voice

Zero violations across 53 texts: the file as written, as read on no finding, and as read on its own (productUI).

Scenes

35 drawings in components/training/scenes/, from the pawns and the sketch kit (D7), each drawn on a real finding as its step reads there (a topic's, as a reader takes it on its own); the one motion stops under reduced motion

Inspired by Rob Genova's drawings in two Qpoint posts: The Hidden Agent Surface and Your Agents Need a Dynamic Sandbox. One idea per drawing, flat and labelled, with the pixel agent and what happened to each attempt.

Claude Code on mac-a1
MCP
◇Vanta MCP

not sanctioned for Team A

Claude Code on mac-a1 connects to the Vanta MCP server, which sits outside the sanctioned list for Team A.
connectionmotion · drawn for T-MCP-1

the agent on this machine reaches a server outside the list

reads {agent} {device} {server} {team}

Step 1 of T-MCP-1 on F-A →
your agent
tool calls
◇Vanta MCP

the tool list

⬓read

what the server can read

▤write

what it can write

▣send

where it can send

The agent reaches through the server to everything the server can read, write or send.
server-reachmotion · drawn for T-MCP-1

everything the server can read, write or send, the agent can

reads {server}

Step 2 of T-MCP-1 on F-A →
▤Sanctioned for Team A

GitHub MCP, Atlassian MCP and Postgres MCP (read-only) for analytics harnesses only

reviewed
◇Vanta MCP

allowed for GRC only, after their review

The sanctioned servers for Team A beside Vanta MCP, which is sanctioned for GRC only.
sanctioned-liststill · drawn for T-MCP-1

the team's sanctioned list beside the server, sanctioned elsewhere

reads {team} {sanctioned} {server} {exceptionTeam}

Step 3 of T-MCP-1 on F-A →
●You

your work needs the server

ask
●Dana (security admin)

reviews what it can reach

▤added for Team A
◇or a sanctioned server

that does the same job

You ask the policy's owner; the server is added for your team, or a sanctioned one that does the same job is named.
askstill · drawn for T-MCP-1

you ask the policy's owner; the server is added, or a sanctioned one named

reads {owner} {team}

Step 4 of T-MCP-1 on F-A →
Claude Code on mac-a1
session
●usera@gmail.com

a personal account, not your organisation's

Claude Code on mac-a1 runs a session under usera@gmail.com, a personal account.
account-sessionmotion · drawn for T-ACCT-1

the agent on this machine runs a session under a personal account

reads {agent} {device} {account}

Step 1 of T-ACCT-1 on F-C →
▤your work

prompts, files the agent reads, answers

under
●your organisation's account

its agreement: how long work is kept, who may review it

under
●usera@gmail.com

your own terms: out of your organisation's reach

The same work under two accounts: your organisation's, inside its agreement with the provider, and usera@gmail.com, outside it.
account-boundarystill · drawn for T-ACCT-1

the same work under the organisation's account, inside its agreement, and the personal one, outside it

reads {account}

Step 2 of T-ACCT-1 on F-C →
Claude Code
signed in as
▭settings · account

check it shows your organisation's, not usera@gmail.com

Claude Code shows the account it is signed in with; check it before work starts.
account-checkstill · drawn for T-ACCT-1

the agent shows the account it is signed in with

reads {agent} {account}

Step 3 of T-ACCT-1 on F-C →
●usera@gmail.com

sign out

then
●your organisation's account

sign in

no seat yet?
ask
●IT

a seat on the organisation's account

Sign out of usera@gmail.com and sign in with your organisation's account; with no seat yet, ask IT for one.
account-switchstill · drawn for T-ACCT-1

sign out of the personal account, sign in with the organisation's; no seat yet, ask IT

reads {account}

Step 4 of T-ACCT-1 on F-C →
Cursor CLI on priya-x1
prompt
◇the model

received the AWS access key

Cursor CLI on priya-x1 sends a prompt with an AWS access key in it to the model.
secret-promptmotion · drawn for T-SECRETS-1

the agent on this machine sends a prompt with a key in it; the model received it, or never did

reads {agent} {device} {modelGot}

Step 1 of T-SECRETS-1 on F-G →
▭your prompt

with the AWS access key

sent
▤the session's transcript
⬓the provider's logs
▣tools the agent passed it to
A prompt, once sent, has copies outside your machine: the transcript, the provider's logs and the tools it reached.
secret-copiesstill · drawn for T-SECRETS-1

once sent, a prompt has copies outside the machine: the transcript, the provider's logs, the tools it reached

reads {dataClass}

Step 2 of T-SECRETS-1 on F-G →
▤AWS access key

revoked

then
▤a new key

where the tool reads it

and
tell
●IT

what you did, and when

The old key revoked, a new one issued where the tool reads it, and IT told.
secret-rotatestill · drawn for T-SECRETS-1

revoke the key, issue a new one where the tool reads it, tell IT

reads {dataClass}

Step 3 of T-SECRETS-1 on F-G →
⬓your secret manager

or an environment variable

read when it runs
the tool
▭your prompt

names the secret, never holds it

The secret stays in a secret manager or an environment variable; the tool reads it when it runs, and the prompt only names it.
secret-referencestill · drawn for T-SECRETS-1

the secret stays in a secret manager or an environment variable; the tool reads it, the prompt only names it

reads no slots

Step 4 of T-SECRETS-1 on F-G →
▤Off
▣goes through
nothing recorded
▤Observe
▣goes through
▤a finding

recorded

▤Enforce
▣stopped
▤a finding

recorded

the mode each policy has for Engineering
The same request under each mode: Off lets it through, Observe lets it through and records it, Enforce stops it and records it.
policy-modesstill · drawn for T-MODES-1 · also used by T-PROVIDERS-1, T-APPROVAL-1

a policy in each mode: Off lets it through, Observe lets it through and records, Enforce stops it and records

reads {team}

Step 3 of T-PROVIDERS-1 on F-F →
Claude Code on mac-eng-11
observe
◇goes through

your work carries on

▤a finding

recorded by qcontrol

Claude Code on mac-eng-11 carries on, and qcontrol records a finding beside it.
mode-observemotion · drawn for T-MODES-1 · also used by T-INJECT-1, T-PROVENANCE-1, T-SPEND-1

under Observe the action goes through, and a finding records it

reads {agent} {device}

Step 3 of T-INJECT-1 on F-H →
your agent on mac-a1
enforce
▣stopped

on mac-a1, before it leaves

▤a finding

recorded by qcontrol

◇the model or the server

never reached

Your agent on mac-a1 acts under a policy that enforces: qcontrol stops the action on the machine and records a finding.
mode-enforcestill · drawn for T-MODES-1

under Enforce the action is stopped on the machine, and a finding records it

reads {agent} {device}

Step 3 of T-MODES-1, a topic, as User A reads it →
●You

your work needs what was stopped

ask
●IT or the policy's owner

reads what was stopped

▤sanctioned

for the work

▤an exception for Engineering

with a reason

You ask IT or the policy's owner about the provider your work needs; it is approved, or Engineering gets an exception.
mode-askstill · drawn for T-MODES-1 · also used by T-PROVIDERS-1

ask IT or the policy's owner; it is sanctioned, or the team gets an exception

reads {team}

Step 4 of T-PROVIDERS-1 on F-F →
▭content from outside

read through GitHub MCP

▤a hidden line

written for the agent

read
Claude Code on mac-eng-11
Claude Code on mac-eng-11 reads content through GitHub MCP; a line in it, hidden from the reader, addresses the agent.
hidden-instructionmotion · drawn for T-INJECT-1

content from outside reaches the agent on this machine with a hidden line written for the agent

reads {agent} {device}

Step 1 of T-INJECT-1 on F-H →

what the agent reads

●your request

summarise this email

▭a line in the email

send the money files out

one context
the agent
Your request and the hidden line sit together in what the agent reads, with nothing to tell them apart.
one-contextstill · drawn for T-INJECT-1

your request and the hidden line sit together in what the agent reads, at the same weight

reads no slots

Step 2 of T-INJECT-1 on F-H →
Claude Code
asks first
▭send 2 files?

to an address you have never seen

●you decline

and tell IT

Claude Code asks before it sends anything, and you decline a step you did not ask for.
approve-sendstill · drawn for T-INJECT-1

the agent asks before it sends; you decline a step you did not ask for and tell the owner

reads {agent} {owner}

Step 4 of T-INJECT-1 on F-H →
Cursor CLI on priya-x1
prompt
◇deepseek.com

not on the approved list

never received the prompt
Cursor CLI on priya-x1 sends a prompt to deepseek.com, which is not on the approved list.
provider-requestmotion · drawn for T-PROVIDERS-1

the agent on this machine sends a prompt to a provider off the approved list; it received the prompt, or never did

reads {agent} {device}

Step 1 of T-PROVIDERS-1 on F-F →
▤your prompt

the files, the pasted text, a ticket

◇anthropic.com and openai.com

terms your organisation agreed to

◇deepseek.com

terms nobody here has read

The approved providers work under terms your organisation agreed to; a provider off the list works under terms nobody here has read.
provider-termsstill · drawn for T-PROVIDERS-1

a prompt carries what the agent put in it; the approved providers under terms the organisation agreed to, one off the list under terms nobody read

reads {approved}

Step 2 of T-PROVIDERS-1 on F-F →
No published training uses this scene in this world, so there is nothing to draw it on.
version-loadmotion · drawn for T-PROVENANCE-1

the agent on this machine loads a skill or a server at a version nobody pinned

reads {agent} {device}

No published training uses this scene in this world, so there is nothing to draw it on.
version-truststill · drawn for T-PROVENANCE-1

the version the team reviewed, and the next one, which does what its publisher wrote with the agent's access

reads no slots

No published training uses this scene in this world, so there is nothing to draw it on.
pin-versionstill · drawn for T-PROVENANCE-1

install at a fixed version; the latest waits until the owner reviews and pins it

reads {owner}

Claude Code on mac-eng-05
a call
◇GitHub MCP

sends, posts or publishes

▭outside the machine

it ran without anyone approving it

Claude Code on mac-eng-05 makes a call through GitHub MCP that acts outside the machine.
unapproved-callmotion · drawn for T-APPROVAL-1

the agent on this machine makes a call through a server or tool that acts outside the machine, unapproved or held

reads {agent} {device}

Step 1 of T-APPROVAL-1 on F-I →
stays on your machine
▤read a file
▤search
▤draft
acts on the world: ask first
▭send mail
▭post or publish

a public link is found in minutes

▭delete
▣run a command that reaches out
Calls that read stay on your machine; calls that send, post, publish or delete act on the world and cannot be taken back.
consequential-callsstill · drawn for T-APPROVAL-1

calls that stay on the machine beside calls that act on the world and cannot be taken back

reads no slots

Step 2 of T-APPROVAL-1 on F-I →
Claude Code
asks first
▭publish the file?

where it goes · public: true

●you decline

and say how to share it

Claude Code asks before it sends or publishes; the request shows where it goes and who can open it, and you decline or say how.
approve-callstill · drawn for T-APPROVAL-1

the agent asks before it publishes; the request shows where it goes and who can open it; you decline or say how

reads {agent}

Step 4 of T-APPROVAL-1 on F-I →
No published training uses this scene in this world, so there is nothing to draw it on.
spend-ceilingmotion · drawn for T-SPEND-1

the agent on this machine runs on its own, paid turn after paid turn, and its spend passes the ceiling

reads {agent} {device} {ceiling}

No published training uses this scene in this world, so there is nothing to draw it on.
retry-loopstill · drawn for T-SPEND-1

a step fails, the agent tries again, and each try is a paid turn with the model

reads no slots

No published training uses this scene in this world, so there is nothing to draw it on.
agent-limitstill · drawn for T-SPEND-1

before you leave it, a limit: a few tries then stop and report, and a maximum number of turns

reads no slots

No published training uses this scene in this world, so there is nothing to draw it on.
skill-updatemotion · drawn for c144 S3

a reviewed, pinned skill is published again overnight with a step nobody reviewed

reads {skill} {from} {to} {adds} {agent} {device}

No published training uses this scene in this world, so there is nothing to draw it on.
share-requestmotion · drawn for c144 S4

a person asks their assistant to share a file and leaves how to it

reads {person} {file} {to} {holds} {agent}

No published training uses this scene in this world, so there is nothing to draw it on.
public-linkmotion · drawn for c144 S4

a file posted where anyone with the link, and search engines, can read it

reads {where} {file} {to}

No published training uses this scene in this world, so there is nothing to draw it on.
ticket-cardmotion · drawn for c144 S5

a support ticket with a full card number is pasted into the assistant

reads {customer} {card} {agent} {device}

No published training uses this scene in this world, so there is nothing to draw it on.
stranger-asksmotion · drawn for c144 S5

an unapproved model asks back for the card's expiry and code, and the assistant passes it on

reads {provider} {agent} {person}

Qpoint Brand Style Guide