<?xml version="1.0" encoding="utf-8"?>
<feed xmlns="http://www.w3.org/2005/Atom" xml:lang="en">
  
  <title>Lane Stevens on Cycle Time</title>
  <subtitle>Faster cycles only count if they converge to done.</subtitle>
  <link href="https://www.cycletime.com/feed.xml" rel="self" />
  <link href="https://www.cycletime.com/" />
  <updated>2026-11-12T00:00:00Z</updated>
  <id>https://www.cycletime.com/</id>
  <author>
    <name>Lane Stevens</name>
  </author>
  <entry>
    <title>Every Role but Author: Directing AI Agents on Mission-Critical Infrastructure</title>
    <link href="https://www.cycletime.com/writing/every-role-but-author/" />
    <updated>2026-11-12T00:00:00Z</updated>
    <id>https://www.cycletime.com/writing/every-role-but-author/</id>
    <summary>AI agents made the scale possible; five human-controlled gates made it trustworthy. How a team of one moved a mission-critical platform to AWS.</summary>
    <content type="html">&lt;p&gt;&lt;em&gt;AI disclosure: I wrote this article. Claude, ChatGPT, Gemini and Grok reviewed drafts, and I accepted some of their edits. Claude also checked facts against the project record and drew the figures.&lt;/em&gt;&lt;/p&gt;
&lt;p&gt;MobilSense Technologies recently migrated MobilSentry, its flagship
wireless management product, from a collection of leased hardware in a
data center to AWS. The objective of the effort was to establish GitOps
against an infrastructure-as-code control plane for the full
lifecycle of the platform. The first measure of success was the
migration of all systems on a legacy, host-centric
configuration to a cloud-native platform designed to align with the
AWS Well-Architected Framework.&lt;/p&gt;
&lt;p&gt;The stakes for this migration were high because we had limited
rollback options. We started the migration on Saturday of Labor Day
weekend to give us an additional day should we need to roll back and
take a second run at the migration. Beyond that, the grip of time
would grow tighter with each passing day as our hosting provider was
closing the data center in which we were hosted, and our contract with
them ended on 13 September, the Sunday following Labor Day.&lt;/p&gt;
&lt;p&gt;The migration was uneventful, with just over 6 hours of
customer-facing outage, comfortably within the planned window of 12
hours. The long pole in the tent was the migration of hundreds of
Postgres databases. If our business weren&#39;t on the line, it would be
reasonable to characterize the migration as boring. That it went that
way was by design, and the reasons grow out of a foundation that was
established five months earlier, in April.&lt;/p&gt;
&lt;p&gt;MobilSentry began serving customers in 2005. As business grew,
the platform grew through the addition of hosts. The configuration was
managed following commonly accepted practices for the time. These
practices were based on manual administrative tasks supported by
open-source and homegrown tools.&lt;/p&gt;
&lt;p&gt;This migration had been anticipated for a number of years. We had
planned to complete the migration in Q4 of 2026, and started the year
with that intention. Early in the year, our hosting provider was
acquired. During our getting-to-know-you call with the new provider,
we told them of our plans to migrate out by Q4. They pressured us to
be complete by the end of October.&lt;/p&gt;
&lt;p&gt;Our platform development commenced on 6 April 2026 with a team of one.
I was responsible for what was built: architect, business analyst,
project manager, reviewer of record, release manager, and, on the
night of the migration, operator. I rounded out the team with AI
agents that drafted, implemented, and reviewed under my direction.
Agents authored every work product.&lt;/p&gt;
&lt;h2&gt;Rigor Before Load&lt;/h2&gt;
&lt;p&gt;I required every change to move the system from one known state to
another by a difference that was well defined and verifiable. The
vehicle to accomplish this was a statement of work (SOW) for each
change.&lt;/p&gt;
&lt;p&gt;I configured three types of agents: analyst, implementer, and
reviewer. I established rules for treatment of reviewer feedback, and
no work product advanced until the review process was completed. This
level of rigor was a guiding principle for the project, and was
specifically captured in the role definition that framed every SOW:
&amp;quot;The rigor is not a response to current external load. It is the
discipline we want in place before external load exists.&amp;quot;&lt;/p&gt;
&lt;p&gt;The primary work products, Terraform code and related configuration
files, are the infrastructure-as-code control plane for the
platform. The full lifecycle of the platform is managed through a
GitOps methodology that includes a manual approval gate for which I am
responsible. Every change is tracked in the repository.&lt;/p&gt;
&lt;p&gt;Resources and the workflows that they enable are instrumented with
monitors, alarms, backup, and operational tooling as appropriate to
manage them over their full lifecycle. For compute resources this may
include the ability to destroy and relaunch the resource while
preserving the continuity of its configuration. Building these
supporting aspects enabled an accurate assessment of operational
readiness without overlooking essential behind-the-scenes elements of
the platform.&lt;/p&gt;
&lt;h2&gt;Six Weeks Vanish&lt;/h2&gt;
&lt;p&gt;A month into our project, we were contacted by the new hosting
provider with bad news. Their schedule to shut down the data center
had changed, and we were to be out by the middle of September. We were
not in a position of leverage, and the net of this change was that we
lost six weeks of our platform implementation and operational
readiness preparation time. We set Labor Day weekend as the scheduled
migration date and agreed to a meeting after the middle of July to
confirm that we were on schedule.&lt;/p&gt;
&lt;p&gt;In mid-July, I considered contingency plans that we could implement.
None were very appealing. I had developed a high level of confidence
in both the platform and the process that had produced it. Over three
months, the agents had demonstrated their ability to deliver quickly
and correctly. I had an operational system that I could assess against
the full set of requirements. I was confident in the ability to go
live with the core of MobilSentry, but less confident that every
incidental workflow would be ready. I made a calculated decision: we
would prioritize incomplete workflows and fill the gaps with interim
solutions until each workflow was fully supported. With this in mind,
I notified the hosting provider that we were still on track for the
Labor Day migration.&lt;/p&gt;
&lt;h2&gt;Trust Through Gates&lt;/h2&gt;
&lt;p&gt;Every change passed through five gates, and I controlled each one:&lt;/p&gt;
&lt;ol&gt;
&lt;li&gt;&lt;strong&gt;Authoring.&lt;/strong&gt; I set the objective and dispatched an analyst agent
to write the SOW: what to build, not how, with acceptance criteria.
A separate agent reviewed it until no actionable findings remained.
I consider these the most valuable reviews in the process.&lt;/li&gt;
&lt;li&gt;&lt;strong&gt;Implementation.&lt;/strong&gt; Only a reviewed SOW could be dispatched to an
implementation agent, whose work went through the same review loop
before a pull request was opened.&lt;/li&gt;
&lt;li&gt;&lt;strong&gt;Merge.&lt;/strong&gt; I approved and merged every pull request based primarily
on my review of the agents&#39; review. I resolved any concerns with
the implementation agent before merging.&lt;/li&gt;
&lt;li&gt;&lt;strong&gt;Deployment.&lt;/strong&gt; I ran the pipeline and approved each apply at the
manual gate.&lt;/li&gt;
&lt;li&gt;&lt;strong&gt;Validation.&lt;/strong&gt; I confirmed the acceptance criteria were met before
the SOW was marked validated.&lt;/li&gt;
&lt;/ol&gt;
&lt;p&gt;&lt;img src=&quot;https://www.cycletime.com/writing/every-role-but-author/gates-bold.png&quot; alt=&quot;Agents worked between the gates; a human decided at each one.&quot;&gt;&lt;/p&gt;
&lt;p&gt;The gates were sequential for each SOW, but not for me. Where
dependencies allowed, I kept several SOWs moving at once, each with
its own agents, at times as many as 10. The pace was the agents&#39;.
Staying on target was up to me.&lt;/p&gt;
&lt;p&gt;When the migration started, the record showed:&lt;/p&gt;
&lt;ol&gt;
&lt;li&gt;424 SOWs closed, 7 pending validation.&lt;/li&gt;
&lt;li&gt;410 pull requests reviewed and merged in the core repository; work
for other repositories is not included in this number.&lt;/li&gt;
&lt;li&gt;520 pipeline executions, none applied without my approval.&lt;/li&gt;
&lt;li&gt;4,825 commits, every one made at my direction or as directed by our
development process.&lt;/li&gt;
&lt;li&gt;1,581 managed AWS resources.&lt;/li&gt;
&lt;/ol&gt;
&lt;p&gt;This was an objective-driven project with real constraints, breaking
new ground. That there were strains was to be expected. The bastion
configuration grew from 4 planned SOWs to 78. Each strain became
tracked work through the same gates. When the strains surfaced
weaknesses in the process, I updated the agent instructions, and the
process became stronger.&lt;/p&gt;
&lt;h2&gt;Turned Loose or Reined In&lt;/h2&gt;
&lt;p&gt;Methods of applying AI to software solutions fit on a spectrum from
turning agents loose to see what they produce, to managing them
closely. One common concern about close management is that the
advantage of agents is lost because human review of agent-produced
code becomes the bottleneck. That concern is reasonable.&lt;/p&gt;
&lt;p&gt;The review process stands on two pillars. The first pillar is that
agents need rules of engagement for reviewer feedback. The second
pillar is that humans primarily review the agents&#39; well-structured
reviews. I delegated examination, not accountability.&lt;/p&gt;
&lt;p&gt;Agents that produce work products judge each reviewer finding on four
criteria: suitability, accuracy, relevance, and actionability.
Actionable findings meet those four criteria. The rest are rejected,
and the review process continues until there are no actionable
findings. Agents reviewing agents may share blind spots. The
deployment and validation gates mitigate this through independent
lines of sight: human review of the Terraform plan and objective
acceptance criteria applied to the running system.&lt;/p&gt;
&lt;p&gt;&lt;img src=&quot;https://www.cycletime.com/writing/every-role-but-author/review-loop.png&quot; alt=&quot;The agent review loop: a separate reviewer, the producer judging each finding, and a gate at the exit.&quot;&gt;&lt;/p&gt;
&lt;p&gt;Where a project is placed on the spectrum should depend on the blast
radius of failure. A defect in a new application can be confined to
the application. A defect in mission-critical infrastructure can
disrupt everything that it supports.&lt;/p&gt;
&lt;p&gt;At 17:00 on the evening of the cutover, I launched the pipeline to
tear down the test hosts ahead of launching their production versions.
This was execution 521 of the pipeline. My review of the Terraform
plan surfaced an error that excluded some of the hosts. I aborted the
run at 17:06. Six minutes later, execution 522 was launched with the
correction and the migration was under way.&lt;/p&gt;
&lt;p&gt;By Labor Day Monday, the system had been fully migrated and
operational for more than 24 hours. End-to-end testing that had
previously not been possible surfaced two failing interfaces. Those
were fixed the same day using the established process.&lt;/p&gt;
&lt;p&gt;The process that we established supports the full lifecycle of the
platform; it was not abandoned after the migration. AI made possible
the scale within the deadline. The discipline made it trustworthy.&lt;/p&gt;
</content>
  </entry>
</feed>