Skip to content

Cloudpack and Cloud Agents

An operating system for agent work — how we keep cloud agents useful without making them reckless.

Matt Dennis

Most of the value of an AI agent isn’t the model — it’s the operating system around it. This is the explainer we built internally for how our cloud agents run: what modes they operate in, how they stay safe, and what proof they have to come back with. The deck is embedded below as an interactive slideshow — click the arrows or dots, or use your keyboard. Hit View all slides to read it as one long page.

cloudpack / cloud agents01 / 10
An operating system for agent work

Make cloud agents useful without making them reckless.

Cloudpack gives agents a shared way to investigate, plan, change, operate, verify, and hand work back. Cloud agents execute inside that system.

The pitch: more work moves forward while the important decisions stay visible and controlled.
rulesevidencehandofftools
CLOUD
PACK
maven / internal explainerstart here
the value proposition02 / 10

Cloudpack turns “AI helped” into “the work is trustworthy.”

It puts a repeatable shape around agent work so speed does not come from skipping context, approvals, or proof.

01

Less stall

Agents know which mode they are in and what to do next, so they do not stop for questions that evidence can answer.

02

Less rework

The loop forces the agent to inspect dependencies and define proof before it edits the system.

03

More trust

Every meaningful result comes with a concrete handoff: what changed, what proves it, and what remains.

value = autonomy × evidence × repeatability

why it exists02
what is in it for me?03 / 10

Different people get a different kind of relief.

engineer
I get a worker that can carry a ticket farther.

It reads the repo rules, follows the delivery path, tests the right thing, and brings back a reviewable result.

reviewer
I get evidence instead of chat archaeology.

The handoff explains the causal path and names the test, sandbox, screenshot, or query behind the claim.

team lead
I get consistency across agents.

One work loop replaces a collection of personal habits and one-off prompt rituals.

operator
I get boundaries around blast radius.

Production stays protected. Development and integration environments have distinct jobs and explicit checks.

who benefits03
the before / after04 / 10

The difference is not a smarter prompt. It is a better operating path.

without a shared pack
“I found a likely fix. Want me to try it?”

Context lives in the chat. The agent may miss local rules, test the wrong surface, or stop at a plausible patch.

with cloudpack
“I classified the work, checked the dependencies, changed the slice, and proved the result.”

The agent follows a known route and returns evidence that another person can inspect.

Cloudpack does not promise perfect agents. It makes their behavior legible, bounded, and easier to correct.

the shift04
what it does05 / 10

One loop. Four modes. No persona sprawl.

The work changes shape by mode and risk, not by inventing a new agent identity for every request.

investigateEstablish facts, diagnose behavior, answer a question, or produce findings.
designCompare approaches, define a solution, or decompose a larger initiative.
changeModify code, metadata, documentation, configuration, or tests.
operatePerform a deployment, data update, backfill, or monitored procedure.

same loop / different proof bar

the operating model05
how it works06 / 10

The agent starts by making the work explicit.

This internal contract keeps the agent from treating every task as “edit files until it looks right.”

01

Classify

Mode, scope, side effects, deliverable, verification.

02

Investigate

Read the system and gather evidence before choosing.

03

Choose

Pick the smallest approach and define the proof.

04

Execute

Work in controlled increments and reassess.

05

Verify

Use the strongest practical evidence, then hand off.

The loop is intentionally boring. Boring is what makes it repeatable.

the work loop06
how agents stay safe07 / 10

Safety comes from boundaries and proof, not from asking permission for everything.

Evidence before preference

If code, data, or a safe test can answer the question, the agent probes before it asks.

!

Hard stops win

Access controls, protected environments, and missing business decisions override a numeric complexity score.

Strongest practical proof

Tests are not the only proof. Use integration checks, UI evidence, queries, and rollback readiness when they fit.

Lessons become structure

When a pitfall repeats, encode it in a learning, script, or runbook instead of relying on memory.

autonomy is earned by verifiable work

guardrails07
the cloud agent path08 / 10

A cloud agent is a worker with a clean environment and a delivery contract.

Cloudpack defines how the worker thinks and reports. The repository pack defines where it may work and what counts as done.

SCRATCH

Iterate

Targeted deploys and narrow tests in an isolated development org.

AGENT_DEV

Prove

Full affected suite, coverage, integration behavior, and UI evidence.

MR / GEARSET

Deliver

Conflict preflight, reviewable handoff, and promotion-aware evidence.

Production is read-only for the agent path. Delivery is a separate, visible step.

cloud execution08
a real run09 / 10

Suppose the ticket is fuzzy: “fix the Closed Won launch-date issue.”

The pack turns a vague request into a sequence that can expose the real dependency chain before code changes land.

the agent sees
A symptom in one record.

It does not assume the symptom is the whole system. It inspects the trigger, flow, validation rule, and related records.

the agent learns
The change crosses three gates.

The opportunity, products, and assets each have their own state and documentation requirements.

the agent does
Stages the fix in the right order.

It changes the minimum slice, runs representative tests, and proves the behavior in the integration sandbox.

the reviewer gets
A causal handoff.

What failed, why it failed, what changed, what remains unchanged, and which evidence supports the result.

from ticket to proof09
the decision10 / 10

Use cloudpack when you want agents to do more than generate a first draft.

It gives the team a common operating model for agent work: investigate with evidence, change in controlled slices, verify the real outcome, and hand back something another person can trust.

faster starts fewer surprises clearer ownership

Cloudpack is the system. Cloud agents are the workers. The value is trustworthy progress.

cloudpack / cloud agentsship with proof
01 / 10