Rubric
Contents — domains, guide and mocks

Life cycle of a Claude system

CCDV-F 2.210 min read · checked 21 September 2026

Task statementSystems Life Cycle (2.8%) — life cycle management concepts and frameworks for developing, implementing, operating and maintaining IT systems

The life cycle, as a loop

  1. Planrequirements and success criteria
  2. Buildprompts, tools, integration, config
  3. Verifyevaluate against the criteria
  4. Operaterelease, monitor, support
  5. Evolve or retirechange, migrate, decommission

every change re-enters at plan · nothing ships straight from build to operate

Operate and evolve is where a system spends nearly all of its life. The arrow back to plan is not decoration — it is where a retirement notice or a quality regression enters the process.

The phases, and what each one owes the next

Whatever framework your organisation uses — a staged waterfall, an iterative sprint cadence, or continuous delivery — the same responsibilities have to land somewhere. Planning produces requirements and the measurable success criteria that task statement 2.1 covers. Build produces the application, its prompts, its tool definitions and its configuration. Verification compares the built thing against the criteria rather than against somebody's impression of it. Operation runs it, watches it and supports the people using it. Evolution changes it, and eventually retires it.

What each phase owes the next is an artefact, and that is what exam scenarios usually probe. Planning owes verification a target that can fail. Build owes operations a configuration that is written down rather than typed by hand. Operations owes evolution evidence: what actually happened, how often, at what cost. A team that cannot say what “good” looked like last month has no basis for deciding whether this month's model upgrade helped.

PhaseTypical activity on a Claude systemThe artefact it hands on
PlanTurn a business outcome into measurable criteriaSuccess criteria with units and a sample
BuildPrompts, schemas, tools, settings, pinned model IDA repository that fully describes the system
VerifyRun the evaluation set; review code and outputsA pass/fail record against the criteria
OperateMonitor errors, latency, spend; support usersTraces, usage data and incident history
EvolveMigrate models, revise prompts, widen scopeA change record and a fresh evaluation
RetireDecommission, export data, revoke keysA decommissioning record

Operating a system whose dependency has its own calendar

This is the part generic life-cycle training does not prepare you for. Anthropic publishes a lifecycle for every model with four states: active, fully supported; legacy, still working but no longer receiving updates; deprecated, given a retirement date and a recommended replacement; and retired, at which point requests to that model fail. For publicly released models, Anthropic commits to notifying customers with active deployments at least 60 days before retirement, by email and on the deprecations page.

The practical consequences are maintenance tasks, and they are the kind of thing a question can be built from. Audit which model IDs your organisation is actually calling — the Console's usage data will tell you, and it is often not what the team believes. Test against the recommended replacement well before the date. Migrate rather than waiting, because the day after retirement is not a good day to discover a behaviour change.

A model's service life

from fully supported down to unavailable

  1. Activesupported and recommended
  2. Legacyworks, no longer updated
  3. Deprecatedretirement date and replacement named
  4. Retiredrequests to it fail
Your own release calendar does not control this sequence. The only lever you have is when you start testing the replacement.

Change that arrives without a release of yours

Two more external clocks are worth knowing. The first is the API version itself: requests carry an anthropic-version header, and within a version Anthropic preserves existing input and output parameters. Additive changes are explicitly allowed without a version bump — new optional inputs, new values in enum-like outputs such as additional stop_reason values or new streaming event types. That is a maintenance instruction disguised as a policy: parse defensively, ignore fields you do not recognise, and never write a switch that crashes on an unfamiliar value.

The second is the platform around the model. Model identifiers from the 4.6 generation onward are dateless and each one is a fixed snapshot whose weights are not updated; new versions ship as new identifiers. The serving infrastructure around them — routing, safety classifiers, sampling — can still evolve, so small behavioural differences are possible even on a pinned identifier. That is precisely why verification is a repeatable artefact rather than a one-off.

Two kinds of change

Change you schedule

  • A prompt or schema revision you ship
  • A new tool added to the application
  • An infrastructure or dependency upgrade
  • You choose the date and the rollback

Change that arrives

  • A model moves to deprecated with a retirement date
  • A newer model makes your current one worth re-testing
  • Additive API fields and new enum values appear
  • Your input mix shifts as users find new uses
Most life-cycle failures happen in the right-hand column, because nothing in your own backlog announces them.

Wiring the life cycle into the tools the team already uses

Life-cycle management becomes real when it lives in the pipeline rather than in a document. Claude Code's GitHub Action runs inside a repository's workflows and can be pointed at a pull request: the review workflow installs a review plugin and posts findings as inline comments on the pull request rather than burying them in a run log. Teams cap what each run may do with arguments such as a turn limit and an allowed-tool list, and store credentials as repository or organisation secrets rather than in the workflow file.

None of that replaces human review, and the exam does not reward pretending otherwise. It supports the verification phase: an extra reviewer that never gets bored, on every pull request, with the project's standards written down where both people and tools can read them.

Traps the wrong answers are built from

Tempting but wrongDo this instead
Treating go-live as the end of the projectPlan operations and evolution as explicit phases with owners and artefacts.
Waiting for the retirement date before testing the replacementStart the comparison when the deprecation notice arrives; at least 60 days' notice is only useful if you use it.
Writing code that fails on an unfamiliar enum valueParse defensively — additive values and new event types can appear without an API version bump.
Keeping prompts and configuration outside version controlPut them in the repository so a change gets review, history and an evaluation run.
Judging a new model by trying a few prompts by handRe-run the same evaluation set and compare against the recorded baseline.

You should now be able to

  • Name the life-cycle phases and the artefact each one hands to the next.
  • Describe Anthropic's model lifecycle states and the minimum retirement notice period.
  • Plan a migration off a deprecated model using usage data and an existing evaluation set.
  • Explain which API changes can appear without a version bump, and how to code for them.
  • Place verification activity inside a pull-request pipeline rather than after release.

Practice questions

Original questions written for this lesson, in the exam’s style. Answer first, then open the reasoning — every option is explained, including why the wrong ones are tempting.

  1. Question 1

    A team receives a deprecation notice for the model behind a live customer-facing assistant. The retirement date is roughly two months away and a replacement is recommended.

    What should the team do first?

    1. ASwitch production to the replacement immediately to avoid forgetting.
    2. BIdentify everywhere the model ID is used and re-run the evaluation set on the replacement.
    3. CWait until closer to the date in case the retirement is postponed.
    4. DPin the API version header to an older value so the model keeps working.
    Show answer and reasoning
    1. AIncorrect. Switching before any comparison risks trading a scheduled problem for an unmeasured one.
    2. BCorrect. Scope and evidence come first: usage data finds the forgotten callers, and the evaluation set turns the migration into a measurement.
    3. CIncorrect. Retirement dates are published commitments, and waiting spends the notice period that exists to make migration safe.
    4. DIncorrect. The version header governs request and response shape, not which model identifiers remain available.
  2. Question 2

    An integration deployed a year ago starts logging errors after a routine week with no releases from the team. The log shows an unhandled value where the code branches on a response field.

    Which two practices would have prevented this? (Select 2.)

    1. AHandling unknown enum-like values gracefully instead of failing on them.
    2. BTreating the vendor's API as a dependency that changes additively, and testing against it periodically.
    3. CDeploying the integration to a second region for redundancy.
    4. DIncreasing the request timeout so responses have longer to arrive.
    5. EMoving the parsing logic into the prompt so the model formats output itself.
    Show answer and reasoning
    1. ACorrect. New values, such as additional stop reasons or event types, can be added without an API version bump, so unfamiliar values must not crash the caller.
    2. BCorrect. A dependency with its own release calendar needs scheduled verification, not only verification when your own code changes.
    3. CIncorrect. Redundancy helps with availability incidents; it does nothing about a value the code cannot parse.
    4. DIncorrect. The failure is in parsing a response that did arrive, so timeouts are unrelated.
    5. EIncorrect. Formatting instructions do not control the API's own response fields, and this replaces a parsing bug with a reliability one.
  3. Question 3

    An internal tool works well in a demo. The team plans to ship it next week, with the prompt maintained in a shared document and the model chosen inside each call site.

    Which change most improves the system's maintainability?

    1. AAdd more examples to the prompt so it handles more cases before launch.
    2. BUse the most capable model everywhere so quality never becomes the problem.
    3. CMove the prompt and the pinned model identifier into the repository as configuration.
    4. DWrite a runbook describing how to update the prompt document by hand.
    Show answer and reasoning
    1. AIncorrect. More coverage may help quality, but it makes an unversioned prompt longer without making it maintainable.
    2. BIncorrect. This raises cost without addressing where the prompt and configuration live.
    3. CCorrect. Both then get review, history and a defined place to change, which is what later migrations and incident investigations need.
    4. DIncorrect. A runbook documents a fragile process rather than removing it; the artefact still has no history or review.

Sources

Drafted with AI assistance and checked against the sources above; expert review is in progress. Spotted an error? Tell us and it gets fixed, dated and listed on how this is written.