Run Conversion Experiment

Paste this into an assistant that can read the web, such as Claude, ChatGPT or Cursor. It reads the specification and the current LangGraph documentation, then writes two files: the graph, and a note on what did not survive the translation. Read the note first. What a runtime cannot express is the part worth arguing about, and this process is a draft to argue with.

Convert the business process below into a runnable LangGraph graph:
one Python file with a TypedDict state, a StateGraph, nodes, edges,
conditional edges and a checkpointer.

The document is a reference process written to the Agent Processes
specification. Read the specification before you start, because it defines
terms that look ordinary and are not:

  https://agentcatalog.com/spec/agent-processes

Sections 6 (the phase graph), 6.5.1 (exception edges), 6.7.1 (deviations),
7 (automation) and 8 (handoffs) are the ones this conversion turns on.

Then read the current documentation for the primitives you will need, rather
than relying on what you remember of the API:

  https://docs.langchain.com/oss/python/langgraph/interrupts
    interrupt() and Command(resume=), which is how a gate stops a run
  https://reference.langchain.com/python/langgraph/graph/state/StateGraph
    StateGraph, add_edge, add_conditional_edges, defer

WHAT THE DOCUMENT ASKS FOR

These hold wherever the process lands, and they matter more than style.

1. Each phase under `phases:` becomes one step, and keeps its name.

2. `after:` gives the edges. `after: a + b` is a join and waits for BOTH.
   Reading it as "either" is the defect the specification calls out by name.

3. Every handoff carries a key in square brackets. Each key becomes one field
   on the run's state, named exactly as the key with hyphens turned into
   underscores, and the sentence beside it becomes that field's comment. The key
   is the stable name; the sentence is prose that may be rewritten.

4. A phase MUST NOT begin before its inbound handoff exists. Where that is
   checkable, check it in the step rather than assuming it.

5. `automation: never` is a gate a person signs. The run stops there and does
   not continue until a person's decision comes back. Do not turn one into a
   notification, a log line, or an automatic transition, whatever the queue
   looks like.

6. Each line under `deviations:` is a backward or sideways edge, returning to
   the phase named on the right. The key in brackets names it, and that name
   belongs in the code.

7. A phase whose `after:` reads like "X or Y, whichever could not finish" is an
   exception edge: it is entered when those phases FAIL, not when they succeed.
   Do not wire it as an ordinary successor.

8. Anything in angle brackets is a blank the adopting organization fills in.
   Leave each one as a named constant at the top of the file with a TODO. Do not
   invent a value, a threshold or a date.

9. Record the document's `from:` line at the top of the file, so it says which
   reference process and which version it was generated from.

10. Run-scoped lines under `run-scoped:` are work that runs alongside the whole
    process rather than at one point in it, and a run may not close while one is
    unfinished. Say in the code what you did about them, including if the answer
    is that the runtime has nowhere to put them.

HOW THAT LOOKS IN LANGGRAPH

11. A phase is a node added with `add_node`, under the phase's own name.

12. The state is a TypedDict. Each handoff key is one field on it.

13. A join is the trap. `add_edge(["a", "b"], "c")` looks right and releases
    once: when a backward edge re-enters ONE arm, the joined node never runs
    again, and the run ends early reporting success rather than raising. Mark the
    joined node `defer=True` and re-check inside it that both inbound handoffs
    exist.

14. A gate is `interrupt()` inside the node, resumed with `Command(resume=...)`.
    The platform lets anything at all call resume, so require the resumed value to
    name a person and a date and refuse anything else. Say in the fidelity note
    that this proves only that whoever resumed typed a name, because
    `Command(resume=True)` from a scheduled job is indistinguishable from a person
    signing.

15. A deviation is `add_conditional_edges` with a routing function named after
    the key in brackets.

16. Pass a durable checkpointer rather than taking the in-memory default. The
    gates wait days, and the default loses every paused run on restart.

17. Leave every phase body unimplemented, raising until somebody registers an
    implementation. The automation level is a blank, so writing a body would
    answer on the adopter's behalf whether an agent may do that work.

Produce a second file alongside it, `FIDELITY.md`, and treat it as the more
important of the two. The code is for whoever builds this. The fidelity note
is for whoever has to decide whether this platform suits the process at all,
and that is usually a different person who will never read the code.

It has three parts.

**What came across.** Briefly: how many phases became steps, how many handoff
keys became state fields, which gates stop the run, which deviations became
edges. Counts and names, not reassurance.

**What did not, and what was done instead.** One entry per gap. For each one,
say what the document requires, what the platform can actually express, what
you did in its place, and what breaks if somebody later removes your
workaround. This last part matters most: a workaround nobody understands is a
workaround somebody deletes.

**What a person still has to decide.** The blanks are not a translation
failure, they are the point of a reference process, so list what has to be
filled in before this could run against anything real, and say which of those
choices the platform constrains.

Write it in plain English for somebody who has not read the specification, and
do not soften it. A translation of a reference process is a draft to argue
with, not a build artifact, and the honest account of what was lost is the most
useful thing you will produce.

Here is the process document.

```
PROCESS: conversion experiment        id: <team>/conversion-experiment   v1
from: ref/mkt/conversion-experiment v1
owner: <who>                          effective: <date>
trigger: a hypothesis is accepted for testing in <your planning process>
         watch: record=<hypothesis>
                system=<your planning process>
                change=<a hypothesis is accepted for testing>
concurrency: runs may overlap - <how many> tests live on the same
             visitors at once
goal: a change tested against the version it replaces, read on the date
      the test was sized for, and rolled out or reverted by a named
      person
phases:
  take-in-hypothesis - human: write down what the change is meant to
                       do, to whom, and what would count as it having
                       worked
                       owner: study-manager      after: trigger
                       automation: <level>
  set-terms          - human: the change, the audience it is shown to,
                       the one measure that decides, and the measures
                       that must not get worse. <who> confirms them
                       owner: study-manager
                       after: take-in-hypothesis
                       automation: <level>
  size-test          - human: the traffic the test needs, how long that
                       takes, and the date the result may be read
                       owner: statistician       after: set-terms
                       by: <days>                automation: <level>
  clear-traffic      - human: the other tests and the other changes due
                       on the same visitors while this one runs
                       owner: study-manager      after: set-terms
                       by: <days>                automation: <level>
  brief-makers       - convenes briefing: the versions, the deciding
                       measure and the run length, heard by every agent
                       at once
                       owner: study-manager
                       after: size-test + clear-traffic
                       automation: <level>
  produce-variants   - runs build-by-talent: the copy and the visuals
                       for each version being compared
                       owner: study-manager      after: brief-makers
                       by: <days>                automation: <level>
  build-variants     - human: each version assembled in the site, and
                       the split set up to send visitors to them
                       owner: web-producer       after: produce-variants
                       by: <days>                automation: <level>
  wire-measurement   - human: the deciding measure and every guardrail
                       measure, counted separately on each version
                       owner: conversion-tracker after: build-variants
                       automation: <level>
  get-sign-offs      - convenes approval: brand, accessibility and
                       legal sign, as named signers, against every
                       version the test will show
                       owner: <your legal role>  after: wire-measurement
                       by: <days>                automation: never
  check-setup        - runs assessment: a dry run showing each version
                       serving and each of its numbers arriving
                       owner: conversion-tracker after: get-sign-offs
                       by: <days>                automation: <level>
  start-test         - human: the named owner says go and the traffic
                       starts splitting
                       owner: study-manager      after: check-setup
                       automation: <level>
  watch-test         - human: delivery, the split as it is running, and
                       the guardrail measures
                       owner: statistician       after: start-test
                       automation: <level>
  read-result        - runs collect-and-report: the number on each
                       version, the size of the difference, and the
                       range around it
                       owner: statistician       after: watch-test
                       by: the read date         automation: <level>
  decide-outcome     - convenes decide-and-announce: a named person
                       says roll it out or put it back, with the
                       reasons said out loud
                       owner: study-manager      after: read-result
                       by: <days>                automation: never
  carry-out          - human: one version goes to everyone, or the
                       change comes out and the original stands
                       owner: web-producer       after: decide-outcome
                       by: <days>                automation: <level>
  record-learnings   - convenes debrief: the finding, filed with the
                       numbers and the design it rests on
                       owner: study-manager      after: carry-out
                       automation: <level>
run-scoped:
  health - runs collect-and-report              owner: statistician
           every: <cadence>
           from: start-test   until: read-result
  status - runs roll-call                       owner: study-manager
           every: <cadence>
           from: brief-makers   until: carry-out
handoffs:
  take-in-hypothesis -> set-terms [the-hypothesis]: the hypothesis in
    one line the test can settle, and who it is about
  set-terms -> size-test [deciding-measure]: the deciding measure, the
    rate it runs at now, and the smallest improvement worth acting on
  set-terms -> clear-traffic [audience-and-dates]: the audience the
    test runs on, and the dates it needs those visitors for
  size-test -> brief-makers [test-size]: the traffic the test needs,
    the run length, the read date, and the rule saying what would end
    the test early
  clear-traffic -> brief-makers [booked-traffic]: the tests and changes
    already booked on the same visitors, and what was moved to make
    room
  brief-makers -> produce-variants [variant-brief]: the request as
    every agent heard it, and which version each maker is building
  produce-variants -> build-variants [variant-content]: the copy and
    the visuals for every version, at a version
  build-variants -> wire-measurement [served-variants]: each version as
    it will be served, and the rule that decides which visitor sees
    which one
  wire-measurement -> get-sign-offs [measured-variants]: every version
    at a version, with the deciding measure and the guardrail measures
    named against it
  get-sign-offs -> check-setup [approved-variants]: the approved
    versions at the signed version. A later change voids the approval
    and sign-offs run again
  check-setup -> start-test [setup-proof]: a dated record showing every
    version serving and every measure arriving
  start-test -> watch-test [split-start]: the time the split started,
    and the date the result may be read
  watch-test -> read-result [traffic-delivered]: the traffic each
    version got, set against the traffic the test was sized for
  read-result -> decide-outcome [result-reading]: the number on each
    version with the range around it, the size of the difference,
    whether that difference is larger than the noise, and what the
    guardrail measures did
  decide-outcome -> carry-out [outcome-decision]: the decision, the
    person who made it, and the version that stands
  carry-out -> record-learnings [live-version]: what is live now, and
    the numbers the decision rested on
deviations:
  get-sign-offs -> produce-variants [sign-off-changes]: a signer comes
    back with changes, so the version they named is made again
  check-setup -> build-variants [version-will-not-serve]: a version
    does not serve in the dry run, so it is built again
  check-setup -> wire-measurement [numbers-do-not-arrive]: a version's
    numbers do not arrive in the dry run, so the measurement is wired
    again
  watch-test -> get-sign-offs [changed-mid-run]: a version is changed
    while the test is live, which voids the approval and starts the
    traffic count again
  watch-test -> clear-traffic [visitors-taken]: another change lands on
    the same visitors mid-run, so the test is recorded as spoiled and
    the traffic is cleared again before it starts over
  watch-test -> decide-outcome [guardrail-gets-worse]: a guardrail
    measure gets worse while the test is live, so the decision is put
    to a person on the partial numbers and nothing is read at
    read-result
  read-result -> watch-test [traffic-fell-short]: the read date arrives
    with less traffic than the test was sized for, so the result is
    recorded as undecided and a person says whether the test runs on
bindings:
  roster:  <who holds each role - agents claiming the abstract agents
           above, and named people for leadership and legal>
  systems: the website's content system (write), the website (write),
           the traffic splitting system (write),
           analytics platforms (write), the test register (write),
           the calculation record (write), the CRM (read)
  data:    brand guidelines <version>, <your claims register>,
           <your accessibility standard> <version>, the hypothesis as
           it was accepted, the current rate of the deciding measure
policy:
  the deciding measure is not read before the date the test was sized
    for, whoever asks for it
  a test that ends with less traffic than it was sized for is recorded
    as undecided
  only a named person ends a running test early, and the reason is
    recorded with the partial numbers
  sign-off is a human gate and is never delegated to an agent
  a version changed after sign-off goes back through sign-offs, and the
    traffic count starts again
  nothing starts splitting traffic without a recorded go from the named
    owner
measures:
  cycle time: <target> from the hypothesis to the read
  volume: <tests per period>
  quality gate: no result is reported without the range around it and
                the traffic it rests on
```

Paste this into an assistant that can read the web, such as Claude, ChatGPT or Cursor. It reads the specification and the current Agent Framework documentation, then writes two files: the workflow, and a note on what did not survive the translation. Read the note first. What a runtime cannot express is the part worth arguing about, and this process is a draft to argue with.

Convert the business process below into a runnable Microsoft Agent Framework workflow:
one Python file with Executor classes, a WorkflowBuilder, typed edges,
request_info gates and durable checkpoint storage.

The document is a reference process written to the Agent Processes
specification. Read the specification before you start, because it defines
terms that look ordinary and are not:

  https://agentcatalog.com/spec/agent-processes

Sections 6 (the phase graph), 6.5.1 (exception edges), 6.7.1 (deviations),
7 (automation) and 8 (handoffs) are the ones this conversion turns on.

Then read the current documentation for the primitives you will need, rather
than relying on what you remember of the API:

  https://learn.microsoft.com/en-us/agent-framework/workflows/human-in-the-loop
    ctx.request_info, @response_handler, and answering a parked run later
  https://learn.microsoft.com/en-us/agent-framework/workflows/checkpoints
    what a checkpoint holds, and allowed_checkpoint_types
  https://learn.microsoft.com/en-us/agent-framework/concepts/workflows/edges
    add_edge with condition, add_fan_in_edges, add_switch_case_edge_group
  https://learn.microsoft.com/en-us/agent-framework/concepts/workflows/state
    ctx.set_state and ctx.get_state as they actually are today

WHAT THE DOCUMENT ASKS FOR

These hold wherever the process lands, and they matter more than style.

1. Each phase under `phases:` becomes one step, and keeps its name.

2. `after:` gives the edges. `after: a + b` is a join and waits for BOTH.
   Reading it as "either" is the defect the specification calls out by name.

3. Every handoff carries a key in square brackets. Each key becomes one field
   on the run's state, named exactly as the key with hyphens turned into
   underscores, and the sentence beside it becomes that field's comment. The key
   is the stable name; the sentence is prose that may be rewritten.

4. A phase MUST NOT begin before its inbound handoff exists. Where that is
   checkable, check it in the step rather than assuming it.

5. `automation: never` is a gate a person signs. The run stops there and does
   not continue until a person's decision comes back. Do not turn one into a
   notification, a log line, or an automatic transition, whatever the queue
   looks like.

6. Each line under `deviations:` is a backward or sideways edge, returning to
   the phase named on the right. The key in brackets names it, and that name
   belongs in the code.

7. A phase whose `after:` reads like "X or Y, whichever could not finish" is an
   exception edge: it is entered when those phases FAIL, not when they succeed.
   Do not wire it as an ordinary successor.

8. Anything in angle brackets is a blank the adopting organization fills in.
   Leave each one as a named constant at the top of the file with a TODO. Do not
   invent a value, a threshold or a date.

9. Record the document's `from:` line at the top of the file, so it says which
   reference process and which version it was generated from.

10. Run-scoped lines under `run-scoped:` are work that runs alongside the whole
    process rather than at one point in it, and a run may not close while one is
    unfinished. Say in the code what you did about them, including if the answer
    is that the runtime has nowhere to put them.

HOW THAT LOOKS IN MICROSOFT AGENT FRAMEWORK

11. Write for Python, and read those pages before writing a line. This API has
    moved: `set_shared_state`, `RequestInfoExecutor`, `RequestInfoMessage` and
    `send_responses_streaming` are all in the training data and none of them exist
    any more. The .NET workflow API differs in kind rather than in spelling, so a
    file written for one does not port by renaming.

12. A phase is a class deriving from `Executor` whose `super().__init__(id=...)`
    takes the phase name verbatim. The id is not cosmetic: a checkpoint stores a
    signature over the topology and the executor ids, so an id built from a run, a
    timestamp or a counter cannot be resumed into.

13. Give each phase a `@handler` method and move work on with
    `await ctx.send_message(...)`. A handler that returns without sending is a dead
    end: the branch stops, the run converges, and it reports success. So a phase
    you are deliberately leaving unimplemented must still send a placeholder
    onward. Do not stub with `raise NotImplementedError`, which fails the run
    instead of leaving it runnable.

14. `after: a` is `builder.add_edge(a, b)`. `after: a + b` is
    `builder.add_fan_in_edges([a, b], target)`, and the target's handler must be
    annotated `list[T]`, because a fan-in delivers one aggregated list rather than
    the separate messages. A handler typed for the single value is dropped as a
    mismatch with nothing raised.

15. The join is the trap here, and it is the opposite of LangGraph's. The
    barrier re-arms: it clears its buffer when it fires and then demands a fresh
    message from every source. So a deviation that re-enters ONE arm parks the
    run forever waiting for an arm that will not run again, and the workflow ends
    IDLE reporting success. Wherever a deviation re-enters one arm of a join,
    replace the barrier with an ordinary edge from each arm into a small executor
    that records each arrival with `ctx.set_state` and only forwards when every
    expected key is present, and say in a comment that putting `add_fan_in_edges`
    back reintroduces the stall.

16. A phase that is both a join target and a deviation target needs two
    handlers, one annotated `list[T]` for the barrier and one annotated `T` for the
    backward message. Write only the list handler and every backward edge into it
    is discarded as a type mismatch, silently.

17. `automation: never` is `await ctx.request_info(request_data=...,
    response_type=...)` inside the phase, answered by a `@response_handler` on the
    same executor whose annotations match those exact types. The run parks at
    `IDLE_WITH_PENDING_REQUESTS` and the host answers with
    `workflow.run(stream=True, responses={request_id: value})`. If no handler
    matches the pair, the framework logs a warning and parks anyway, so the gate
    reads as working right up until somebody asks why the approval did not take.

18. A gate is only a gate if the wait survives a restart, so pass
    `checkpoint_storage=FileCheckpointStorage(...)` to the builder. Checkpointing
    is off by default and `InMemoryCheckpointStorage` reads as configured while
    persisting nothing. Register every handoff payload type in
    `allowed_checkpoint_types`, or the first restore raises. Anything an executor
    keeps as an instance attribute is absent after a restore unless you export it
    from `on_checkpoint_save` and read it back in `on_checkpoint_restore`, and it
    comes back empty rather than missing.

19. Each line under `deviations:` is `builder.add_edge(source, earlier,
    condition=fn)` with `fn` named after the key. Cycles are legal and unchecked,
    but raise `max_iterations` well above its default of 100, because several live
    cycles will exhaust a budget sized for a straight line and fail with a message
    about convergence that reads like a broken graph. Keep the ordinary forward
    edge unconditional and add each deviation beside it: a condition that returns
    false is dropped with no event, so a forward path expressed as a condition
    dies silently on every normal run, which is most of them.

20. Handoff values go in `ctx.set_state(key, value)` and come back from
    `ctx.get_state(key)`, untyped and unchecked. A write is visible to its writer
    at once and to everyone else only in the next superstep, and two writers of one
    key in a superstep keep the last write. Never read a key in the same superstep
    another phase wrote it.

21. There are no timers, no deadlines and no scheduled wakes. Nothing in
    `run-scoped:` becomes an executor and `by:` has no expression at all, so write
    them as comments naming where they start and stop, and say plainly in the
    fidelity note that a run can close over an unfinished run-scoped line. Do not
    fake a deadline with a sleep inside a handler, which blocks the whole superstep
    barrier, and never let an expiring wait release a gate.

Produce a second file alongside it, `FIDELITY.md`, and treat it as the more
important of the two. The code is for whoever builds this. The fidelity note
is for whoever has to decide whether this platform suits the process at all,
and that is usually a different person who will never read the code.

It has three parts.

**What came across.** Briefly: how many phases became steps, how many handoff
keys became state fields, which gates stop the run, which deviations became
edges. Counts and names, not reassurance.

**What did not, and what was done instead.** One entry per gap. For each one,
say what the document requires, what the platform can actually express, what
you did in its place, and what breaks if somebody later removes your
workaround. This last part matters most: a workaround nobody understands is a
workaround somebody deletes.

**What a person still has to decide.** The blanks are not a translation
failure, they are the point of a reference process, so list what has to be
filled in before this could run against anything real, and say which of those
choices the platform constrains.

Write it in plain English for somebody who has not read the specification, and
do not soften it. A translation of a reference process is a draft to argue
with, not a build artifact, and the honest account of what was lost is the most
useful thing you will produce.

Here is the process document.

```
PROCESS: conversion experiment        id: <team>/conversion-experiment   v1
from: ref/mkt/conversion-experiment v1
owner: <who>                          effective: <date>
trigger: a hypothesis is accepted for testing in <your planning process>
         watch: record=<hypothesis>
                system=<your planning process>
                change=<a hypothesis is accepted for testing>
concurrency: runs may overlap - <how many> tests live on the same
             visitors at once
goal: a change tested against the version it replaces, read on the date
      the test was sized for, and rolled out or reverted by a named
      person
phases:
  take-in-hypothesis - human: write down what the change is meant to
                       do, to whom, and what would count as it having
                       worked
                       owner: study-manager      after: trigger
                       automation: <level>
  set-terms          - human: the change, the audience it is shown to,
                       the one measure that decides, and the measures
                       that must not get worse. <who> confirms them
                       owner: study-manager
                       after: take-in-hypothesis
                       automation: <level>
  size-test          - human: the traffic the test needs, how long that
                       takes, and the date the result may be read
                       owner: statistician       after: set-terms
                       by: <days>                automation: <level>
  clear-traffic      - human: the other tests and the other changes due
                       on the same visitors while this one runs
                       owner: study-manager      after: set-terms
                       by: <days>                automation: <level>
  brief-makers       - convenes briefing: the versions, the deciding
                       measure and the run length, heard by every agent
                       at once
                       owner: study-manager
                       after: size-test + clear-traffic
                       automation: <level>
  produce-variants   - runs build-by-talent: the copy and the visuals
                       for each version being compared
                       owner: study-manager      after: brief-makers
                       by: <days>                automation: <level>
  build-variants     - human: each version assembled in the site, and
                       the split set up to send visitors to them
                       owner: web-producer       after: produce-variants
                       by: <days>                automation: <level>
  wire-measurement   - human: the deciding measure and every guardrail
                       measure, counted separately on each version
                       owner: conversion-tracker after: build-variants
                       automation: <level>
  get-sign-offs      - convenes approval: brand, accessibility and
                       legal sign, as named signers, against every
                       version the test will show
                       owner: <your legal role>  after: wire-measurement
                       by: <days>                automation: never
  check-setup        - runs assessment: a dry run showing each version
                       serving and each of its numbers arriving
                       owner: conversion-tracker after: get-sign-offs
                       by: <days>                automation: <level>
  start-test         - human: the named owner says go and the traffic
                       starts splitting
                       owner: study-manager      after: check-setup
                       automation: <level>
  watch-test         - human: delivery, the split as it is running, and
                       the guardrail measures
                       owner: statistician       after: start-test
                       automation: <level>
  read-result        - runs collect-and-report: the number on each
                       version, the size of the difference, and the
                       range around it
                       owner: statistician       after: watch-test
                       by: the read date         automation: <level>
  decide-outcome     - convenes decide-and-announce: a named person
                       says roll it out or put it back, with the
                       reasons said out loud
                       owner: study-manager      after: read-result
                       by: <days>                automation: never
  carry-out          - human: one version goes to everyone, or the
                       change comes out and the original stands
                       owner: web-producer       after: decide-outcome
                       by: <days>                automation: <level>
  record-learnings   - convenes debrief: the finding, filed with the
                       numbers and the design it rests on
                       owner: study-manager      after: carry-out
                       automation: <level>
run-scoped:
  health - runs collect-and-report              owner: statistician
           every: <cadence>
           from: start-test   until: read-result
  status - runs roll-call                       owner: study-manager
           every: <cadence>
           from: brief-makers   until: carry-out
handoffs:
  take-in-hypothesis -> set-terms [the-hypothesis]: the hypothesis in
    one line the test can settle, and who it is about
  set-terms -> size-test [deciding-measure]: the deciding measure, the
    rate it runs at now, and the smallest improvement worth acting on
  set-terms -> clear-traffic [audience-and-dates]: the audience the
    test runs on, and the dates it needs those visitors for
  size-test -> brief-makers [test-size]: the traffic the test needs,
    the run length, the read date, and the rule saying what would end
    the test early
  clear-traffic -> brief-makers [booked-traffic]: the tests and changes
    already booked on the same visitors, and what was moved to make
    room
  brief-makers -> produce-variants [variant-brief]: the request as
    every agent heard it, and which version each maker is building
  produce-variants -> build-variants [variant-content]: the copy and
    the visuals for every version, at a version
  build-variants -> wire-measurement [served-variants]: each version as
    it will be served, and the rule that decides which visitor sees
    which one
  wire-measurement -> get-sign-offs [measured-variants]: every version
    at a version, with the deciding measure and the guardrail measures
    named against it
  get-sign-offs -> check-setup [approved-variants]: the approved
    versions at the signed version. A later change voids the approval
    and sign-offs run again
  check-setup -> start-test [setup-proof]: a dated record showing every
    version serving and every measure arriving
  start-test -> watch-test [split-start]: the time the split started,
    and the date the result may be read
  watch-test -> read-result [traffic-delivered]: the traffic each
    version got, set against the traffic the test was sized for
  read-result -> decide-outcome [result-reading]: the number on each
    version with the range around it, the size of the difference,
    whether that difference is larger than the noise, and what the
    guardrail measures did
  decide-outcome -> carry-out [outcome-decision]: the decision, the
    person who made it, and the version that stands
  carry-out -> record-learnings [live-version]: what is live now, and
    the numbers the decision rested on
deviations:
  get-sign-offs -> produce-variants [sign-off-changes]: a signer comes
    back with changes, so the version they named is made again
  check-setup -> build-variants [version-will-not-serve]: a version
    does not serve in the dry run, so it is built again
  check-setup -> wire-measurement [numbers-do-not-arrive]: a version's
    numbers do not arrive in the dry run, so the measurement is wired
    again
  watch-test -> get-sign-offs [changed-mid-run]: a version is changed
    while the test is live, which voids the approval and starts the
    traffic count again
  watch-test -> clear-traffic [visitors-taken]: another change lands on
    the same visitors mid-run, so the test is recorded as spoiled and
    the traffic is cleared again before it starts over
  watch-test -> decide-outcome [guardrail-gets-worse]: a guardrail
    measure gets worse while the test is live, so the decision is put
    to a person on the partial numbers and nothing is read at
    read-result
  read-result -> watch-test [traffic-fell-short]: the read date arrives
    with less traffic than the test was sized for, so the result is
    recorded as undecided and a person says whether the test runs on
bindings:
  roster:  <who holds each role - agents claiming the abstract agents
           above, and named people for leadership and legal>
  systems: the website's content system (write), the website (write),
           the traffic splitting system (write),
           analytics platforms (write), the test register (write),
           the calculation record (write), the CRM (read)
  data:    brand guidelines <version>, <your claims register>,
           <your accessibility standard> <version>, the hypothesis as
           it was accepted, the current rate of the deciding measure
policy:
  the deciding measure is not read before the date the test was sized
    for, whoever asks for it
  a test that ends with less traffic than it was sized for is recorded
    as undecided
  only a named person ends a running test early, and the reason is
    recorded with the partial numbers
  sign-off is a human gate and is never delegated to an agent
  a version changed after sign-off goes back through sign-offs, and the
    traffic count starts again
  nothing starts splitting traffic without a recorded go from the named
    owner
measures:
  cycle time: <target> from the hypothesis to the read
  volume: <tests per period>
  quality gate: no result is reported without the range around it and
                the traffic it rests on
```

Paste this into an assistant that can read the web, such as Claude, ChatGPT or Cursor. It reads the specification and the current CrewAI documentation, then writes two files: the flow, and a note on what did not survive the translation. Read the note first. What a runtime cannot express is the part worth arguing about, and this process is a draft to argue with.

Convert the business process below into a runnable CrewAI Flow:
one Python file with a Pydantic state model, one Flow subclass, @start,
@listen, @router and a durable human feedback provider.

The document is a reference process written to the Agent Processes
specification. Read the specification before you start, because it defines
terms that look ordinary and are not:

  https://agentcatalog.com/spec/agent-processes

Sections 6 (the phase graph), 6.5.1 (exception edges), 6.7.1 (deviations),
7 (automation) and 8 (handoffs) are the ones this conversion turns on.

Then read the current documentation for the primitives you will need, rather
than relying on what you remember of the API:

  https://docs.crewai.com/en/concepts/flows
    Flow, @start, @listen, @router, and_, or_, state, kickoff, plot
  https://docs.crewai.com/en/learn/human-feedback-in-flows
    @human_feedback, the provider protocol, from_pending and resume
  https://docs.crewai.com/en/guides/flows/mastering-flow-state
    @persist and what persistence actually promises, which is less than it sounds

WHAT THE DOCUMENT ASKS FOR

These hold wherever the process lands, and they matter more than style.

1. Each phase under `phases:` becomes one step, and keeps its name.

2. `after:` gives the edges. `after: a + b` is a join and waits for BOTH.
   Reading it as "either" is the defect the specification calls out by name.

3. Every handoff carries a key in square brackets. Each key becomes one field
   on the run's state, named exactly as the key with hyphens turned into
   underscores, and the sentence beside it becomes that field's comment. The key
   is the stable name; the sentence is prose that may be rewritten.

4. A phase MUST NOT begin before its inbound handoff exists. Where that is
   checkable, check it in the step rather than assuming it.

5. `automation: never` is a gate a person signs. The run stops there and does
   not continue until a person's decision comes back. Do not turn one into a
   notification, a log line, or an automatic transition, whatever the queue
   looks like.

6. Each line under `deviations:` is a backward or sideways edge, returning to
   the phase named on the right. The key in brackets names it, and that name
   belongs in the code.

7. A phase whose `after:` reads like "X or Y, whichever could not finish" is an
   exception edge: it is entered when those phases FAIL, not when they succeed.
   Do not wire it as an ordinary successor.

8. Anything in angle brackets is a blank the adopting organization fills in.
   Leave each one as a named constant at the top of the file with a TODO. Do not
   invent a value, a threshold or a date.

9. Record the document's `from:` line at the top of the file, so it says which
   reference process and which version it was generated from.

10. Run-scoped lines under `run-scoped:` are work that runs alongside the whole
    process rather than at one point in it, and a run may not close while one is
    unfinished. Say in the code what you did about them, including if the answer
    is that the runtime has nowhere to put them.

HOW THAT LOOKS IN CREWAI FLOWS

11. Build a Flow, not a Crew. A Crew is a team of roles with no graph, no join,
    no persistence handle and no gate, and cannot express this document at all.
    Each phase is one method on a single `Flow` subclass, keeping its name with
    hyphens turned into underscores. A phase that genuinely needs role-based agents
    builds its own Crew inside its own method body, and the Flow stays the graph.

12. Declare the state as a Pydantic model bound as the type parameter,
    `class NegotiateTheAgreement(Flow[NegotiationState])`, and read and write
    `self.state.field`. Never use the untyped dict form: the handoff keys are this
    process's memory, and an untyped dict turns a misspelt key into a handoff that
    is silently absent. Keep the auto-injected `id` field, which is what every
    resume depends on.

13. `after: a` is `@listen(a)`. `after: a + b` is `@listen(and_(a, b))`. Never
    write `or_` where the document writes `+`.

14. Check every inbound handoff at the top of the method and raise if one is
    missing. `@listen` says when a method may run and says nothing about what is
    in hand when it does.

15. The join is the trap, and it is proven rather than theoretical. `and_()`
    empties its accumulator the moment it fires, so re-entering BOTH arms works
    forever, and re-entering ONE arm after it has fired leaves it holding a single
    trigger and waiting for the other for good. The cascade drains, CrewAI prints
    that the flow completed, and `kickoff()` returns normally. So for any joining
    phase that a deviation can send work back into, do not use `and_()` at all:
    make the join a `@router` that both arms trigger, which reads the state fields
    and emits its label only when every inbound handoff is present. A router is
    re-evaluated against durable state every time and is never suppressed by the
    once-fired set.

16. Do not write a phase as `@listen(or_(and_(a, b), "some_label"))`. There is
    one accumulator per listener, shared across every branch of its condition and
    wiped when any branch satisfies, so the label firing while the join is half
    full erases the arm that had already arrived.

17. `automation: never` is `@human_feedback(message=..., provider=...)` stacked
    under the method's `@listen`, with a provider whose `request_feedback` raises
    `HumanFeedbackPending`. The run then persists, returns that object from
    `kickoff()`, and a different process answers later with `from_pending(flow_id,
    persistence)` and `resume(text)`. Do not take the default `ConsoleProvider`,
    which calls `input()`: that gate exists only while somebody is watching a
    terminal, and a run started by a scheduler either hangs or takes an empty
    string.

18. Silence must not approve, and the platform's default is that it does. With
    `emit=[...]` set, an empty resume collapses to `default_outcome`, or to the
    first label when that is unset, with no model consulted and nobody named. Treat
    an empty or unrecognised answer as a refusal in your own router. And write the
    approver's name and the time onto the state yourself, because
    `HumanFeedbackResult` carries the text, the outcome and a timestamp but has no
    field for the person, which the specification requires.

19. Each line under `deviations:` is a `@router` named after the key, returning
    a label named after the same key, with the target subscribing as
    `@listen(or_(normal_trigger, "the_label"))`. Route rather than listen
    directly, because a router is re-evaluated on every cycle while a top-level
    `or_` listener is suppressed after it first fires.

20. An exception edge is a `try` and `except` around the failing phase's body,
    recording the failure on the state and emitting an exception label from a
    router. Wiring it as `@listen(or_(x, y))` fires when those phases SUCCEED, so
    the clearing phase would run on every healthy run.

21. An unimplemented phase is a method with the document's own sentence as its
    docstring and a bare `pass`, which is safe because listeners still fire on a
    `None` return. An unimplemented `@router` is not safe: returning `None` emits
    no label, every phase below it disappears from the run including the gates, and
    the flow reports success. A stub router must return a hard-coded label with a
    TODO beside it, or raise.

22. Turn persistence on with `@persist(SQLiteFlowPersistence(...))`, then treat
    every phase that performs a real act as something that will run twice.
    Persistence saves the state fields and nothing else, so a restart rehydrates
    the data and runs the graph again from `@start`: a flow that had already sent a
    written refusal sends a second one. Guard each acting phase with a state field
    it checks and sets.

23. There are no timers, no deadlines and no cadences, and `run-scoped:` has no
    counterpart at all. Put each `by:` value as a named constant, name the
    run-scoped lines in the module docstring as unimplemented obligations, and say
    in the fidelity note that no deadline in this document is enforced by anything.
    These absences produce no diagnostic whatsoever, which is exactly why they have
    to be written down.

Produce a second file alongside it, `FIDELITY.md`, and treat it as the more
important of the two. The code is for whoever builds this. The fidelity note
is for whoever has to decide whether this platform suits the process at all,
and that is usually a different person who will never read the code.

It has three parts.

**What came across.** Briefly: how many phases became steps, how many handoff
keys became state fields, which gates stop the run, which deviations became
edges. Counts and names, not reassurance.

**What did not, and what was done instead.** One entry per gap. For each one,
say what the document requires, what the platform can actually express, what
you did in its place, and what breaks if somebody later removes your
workaround. This last part matters most: a workaround nobody understands is a
workaround somebody deletes.

**What a person still has to decide.** The blanks are not a translation
failure, they are the point of a reference process, so list what has to be
filled in before this could run against anything real, and say which of those
choices the platform constrains.

Write it in plain English for somebody who has not read the specification, and
do not soften it. A translation of a reference process is a draft to argue
with, not a build artifact, and the honest account of what was lost is the most
useful thing you will produce.

Here is the process document.

```
PROCESS: conversion experiment        id: <team>/conversion-experiment   v1
from: ref/mkt/conversion-experiment v1
owner: <who>                          effective: <date>
trigger: a hypothesis is accepted for testing in <your planning process>
         watch: record=<hypothesis>
                system=<your planning process>
                change=<a hypothesis is accepted for testing>
concurrency: runs may overlap - <how many> tests live on the same
             visitors at once
goal: a change tested against the version it replaces, read on the date
      the test was sized for, and rolled out or reverted by a named
      person
phases:
  take-in-hypothesis - human: write down what the change is meant to
                       do, to whom, and what would count as it having
                       worked
                       owner: study-manager      after: trigger
                       automation: <level>
  set-terms          - human: the change, the audience it is shown to,
                       the one measure that decides, and the measures
                       that must not get worse. <who> confirms them
                       owner: study-manager
                       after: take-in-hypothesis
                       automation: <level>
  size-test          - human: the traffic the test needs, how long that
                       takes, and the date the result may be read
                       owner: statistician       after: set-terms
                       by: <days>                automation: <level>
  clear-traffic      - human: the other tests and the other changes due
                       on the same visitors while this one runs
                       owner: study-manager      after: set-terms
                       by: <days>                automation: <level>
  brief-makers       - convenes briefing: the versions, the deciding
                       measure and the run length, heard by every agent
                       at once
                       owner: study-manager
                       after: size-test + clear-traffic
                       automation: <level>
  produce-variants   - runs build-by-talent: the copy and the visuals
                       for each version being compared
                       owner: study-manager      after: brief-makers
                       by: <days>                automation: <level>
  build-variants     - human: each version assembled in the site, and
                       the split set up to send visitors to them
                       owner: web-producer       after: produce-variants
                       by: <days>                automation: <level>
  wire-measurement   - human: the deciding measure and every guardrail
                       measure, counted separately on each version
                       owner: conversion-tracker after: build-variants
                       automation: <level>
  get-sign-offs      - convenes approval: brand, accessibility and
                       legal sign, as named signers, against every
                       version the test will show
                       owner: <your legal role>  after: wire-measurement
                       by: <days>                automation: never
  check-setup        - runs assessment: a dry run showing each version
                       serving and each of its numbers arriving
                       owner: conversion-tracker after: get-sign-offs
                       by: <days>                automation: <level>
  start-test         - human: the named owner says go and the traffic
                       starts splitting
                       owner: study-manager      after: check-setup
                       automation: <level>
  watch-test         - human: delivery, the split as it is running, and
                       the guardrail measures
                       owner: statistician       after: start-test
                       automation: <level>
  read-result        - runs collect-and-report: the number on each
                       version, the size of the difference, and the
                       range around it
                       owner: statistician       after: watch-test
                       by: the read date         automation: <level>
  decide-outcome     - convenes decide-and-announce: a named person
                       says roll it out or put it back, with the
                       reasons said out loud
                       owner: study-manager      after: read-result
                       by: <days>                automation: never
  carry-out          - human: one version goes to everyone, or the
                       change comes out and the original stands
                       owner: web-producer       after: decide-outcome
                       by: <days>                automation: <level>
  record-learnings   - convenes debrief: the finding, filed with the
                       numbers and the design it rests on
                       owner: study-manager      after: carry-out
                       automation: <level>
run-scoped:
  health - runs collect-and-report              owner: statistician
           every: <cadence>
           from: start-test   until: read-result
  status - runs roll-call                       owner: study-manager
           every: <cadence>
           from: brief-makers   until: carry-out
handoffs:
  take-in-hypothesis -> set-terms [the-hypothesis]: the hypothesis in
    one line the test can settle, and who it is about
  set-terms -> size-test [deciding-measure]: the deciding measure, the
    rate it runs at now, and the smallest improvement worth acting on
  set-terms -> clear-traffic [audience-and-dates]: the audience the
    test runs on, and the dates it needs those visitors for
  size-test -> brief-makers [test-size]: the traffic the test needs,
    the run length, the read date, and the rule saying what would end
    the test early
  clear-traffic -> brief-makers [booked-traffic]: the tests and changes
    already booked on the same visitors, and what was moved to make
    room
  brief-makers -> produce-variants [variant-brief]: the request as
    every agent heard it, and which version each maker is building
  produce-variants -> build-variants [variant-content]: the copy and
    the visuals for every version, at a version
  build-variants -> wire-measurement [served-variants]: each version as
    it will be served, and the rule that decides which visitor sees
    which one
  wire-measurement -> get-sign-offs [measured-variants]: every version
    at a version, with the deciding measure and the guardrail measures
    named against it
  get-sign-offs -> check-setup [approved-variants]: the approved
    versions at the signed version. A later change voids the approval
    and sign-offs run again
  check-setup -> start-test [setup-proof]: a dated record showing every
    version serving and every measure arriving
  start-test -> watch-test [split-start]: the time the split started,
    and the date the result may be read
  watch-test -> read-result [traffic-delivered]: the traffic each
    version got, set against the traffic the test was sized for
  read-result -> decide-outcome [result-reading]: the number on each
    version with the range around it, the size of the difference,
    whether that difference is larger than the noise, and what the
    guardrail measures did
  decide-outcome -> carry-out [outcome-decision]: the decision, the
    person who made it, and the version that stands
  carry-out -> record-learnings [live-version]: what is live now, and
    the numbers the decision rested on
deviations:
  get-sign-offs -> produce-variants [sign-off-changes]: a signer comes
    back with changes, so the version they named is made again
  check-setup -> build-variants [version-will-not-serve]: a version
    does not serve in the dry run, so it is built again
  check-setup -> wire-measurement [numbers-do-not-arrive]: a version's
    numbers do not arrive in the dry run, so the measurement is wired
    again
  watch-test -> get-sign-offs [changed-mid-run]: a version is changed
    while the test is live, which voids the approval and starts the
    traffic count again
  watch-test -> clear-traffic [visitors-taken]: another change lands on
    the same visitors mid-run, so the test is recorded as spoiled and
    the traffic is cleared again before it starts over
  watch-test -> decide-outcome [guardrail-gets-worse]: a guardrail
    measure gets worse while the test is live, so the decision is put
    to a person on the partial numbers and nothing is read at
    read-result
  read-result -> watch-test [traffic-fell-short]: the read date arrives
    with less traffic than the test was sized for, so the result is
    recorded as undecided and a person says whether the test runs on
bindings:
  roster:  <who holds each role - agents claiming the abstract agents
           above, and named people for leadership and legal>
  systems: the website's content system (write), the website (write),
           the traffic splitting system (write),
           analytics platforms (write), the test register (write),
           the calculation record (write), the CRM (read)
  data:    brand guidelines <version>, <your claims register>,
           <your accessibility standard> <version>, the hypothesis as
           it was accepted, the current rate of the deciding measure
policy:
  the deciding measure is not read before the date the test was sized
    for, whoever asks for it
  a test that ends with less traffic than it was sized for is recorded
    as undecided
  only a named person ends a running test early, and the reason is
    recorded with the partial numbers
  sign-off is a human gate and is never delegated to an agent
  a version changed after sign-off goes back through sign-offs, and the
    traffic count starts again
  nothing starts splitting traffic without a recorded go from the named
    owner
measures:
  cycle time: <target> from the hypothesis to the read
  volume: <tests per period>
  quality gate: no result is reported without the range around it and
                the traffic it rests on
```

Paste this into an assistant that can read the web, such as Claude, ChatGPT or Cursor. It reads the specification and the current ADK documentation, then writes two files: the workflow, and a note on what did not survive the translation. Read the note first. What a runtime cannot express is the part worth arguing about, and this process is a draft to argue with.

Convert the business process below into a runnable Google ADK workflow:
one Python file with a Workflow, nodes, routed edges, a JoinNode,
RequestInput gates and a persisting session service.

The document is a reference process written to the Agent Processes
specification. Read the specification before you start, because it defines
terms that look ordinary and are not:

  https://agentcatalog.com/spec/agent-processes

Sections 6 (the phase graph), 6.5.1 (exception edges), 6.7.1 (deviations),
7 (automation) and 8 (handoffs) are the ones this conversion turns on.

Then read the current documentation for the primitives you will need, rather
than relying on what you remember of the API:

  https://adk.dev/graphs/routes/
    nodes, tuple chains, Event(route=), JoinNode, back-edges
  https://adk.dev/graphs/human-input/
    RequestInput and the rerun_on_resume handoff
  https://adk.dev/runtime/resume/
    ResumabilityConfig, resuming by invocation id, at-least-once tools
  https://adk.dev/graphs/data-handling/
    Event.output against state, and the selector syntax in instructions

WHAT THE DOCUMENT ASKS FOR

These hold wherever the process lands, and they matter more than style.

1. Each phase under `phases:` becomes one step, and keeps its name.

2. `after:` gives the edges. `after: a + b` is a join and waits for BOTH.
   Reading it as "either" is the defect the specification calls out by name.

3. Every handoff carries a key in square brackets. Each key becomes one field
   on the run's state, named exactly as the key with hyphens turned into
   underscores, and the sentence beside it becomes that field's comment. The key
   is the stable name; the sentence is prose that may be rewritten.

4. A phase MUST NOT begin before its inbound handoff exists. Where that is
   checkable, check it in the step rather than assuming it.

5. `automation: never` is a gate a person signs. The run stops there and does
   not continue until a person's decision comes back. Do not turn one into a
   notification, a log line, or an automatic transition, whatever the queue
   looks like.

6. Each line under `deviations:` is a backward or sideways edge, returning to
   the phase named on the right. The key in brackets names it, and that name
   belongs in the code.

7. A phase whose `after:` reads like "X or Y, whichever could not finish" is an
   exception edge: it is entered when those phases FAIL, not when they succeed.
   Do not wire it as an ordinary successor.

8. Anything in angle brackets is a blank the adopting organization fills in.
   Leave each one as a named constant at the top of the file with a TODO. Do not
   invent a value, a threshold or a date.

9. Record the document's `from:` line at the top of the file, so it says which
   reference process and which version it was generated from.

10. Run-scoped lines under `run-scoped:` are work that runs alongside the whole
    process rather than at one point in it, and a run may not close while one is
    unfinished. Say in the code what you did about them, including if the answer
    is that the runtime has nowhere to put them.

HOW THAT LOOKS IN GOOGLE ADK

11. Build a `Workflow` from `google.adk.workflow`, and pin `google-adk>=2.0` in
    a comment. Do not use `SequentialAgent`, `ParallelAgent` or `LoopAgent`: they
    are deprecated in favour of the graph, and they carry their own defects around
    state and control flow. The documentation moved to adk.dev, and anything you
    remember about nesting agents rather than drawing a graph is out of date.

12. Each phase is one node keeping its name. Take the node kind from how the
    phase resolves rather than from taste: a `human:` or `system:` phase is a plain
    Python function node, and a `runs` or `convenes` phase is an `Agent`.

13. `after:` gives the edges, written as tuple chains in `edges=[...]`, and the
    trigger is the `"START"` keyword. Take the order only from `after:` lines and
    never from the order the phases are listed in.

14. `after: a + b` is a `JoinNode`, and it must be guarded, because this is the
    worst trap of any runtime here. The join fires when every static predecessor is
    marked COMPLETED, nothing ever un-completes a node, and stored outputs are
    never cleared. So after a deviation re-runs one arm, the join fires the instant
    that arm finishes and hands the next phase LAST PASS'S value for every arm that
    did not re-run. It does not stall, it proceeds with stale data, and nothing
    logs. Stamp each arm's output with a pass counter or a content hash, and have
    the phase after the join compare the stamps and refuse to run when they
    disagree.

15. Each line under `deviations:` is a routed back-edge: a router after the
    phase on the left returning `Event(route=...)`, named after the key in
    brackets, with one arm going back to the phase on the right and one going
    forward. An unconditional cycle raises at construction, which is the one place
    this model checks your work. Nothing budgets a routed cycle, so add your own
    count and stop rather than looping forever.

16. Give every router an explicit `DEFAULT_ROUTE` arm, and route it to a phase
    that stops and asks a person. A route value matching no key writes a log
    warning, ends that branch, and lets the run finish reporting success with the
    rest of the process never having happened.

17. `automation: never` is a `RequestInput` node of its own, never an `Agent`
    asking a question. Decorate it `@node(rerun_on_resume=False)` and yield
    `RequestInput(message=..., payload=..., response_schema=...)`, so the run
    stops, persists, and delivers the person's answer to the node's successor as
    its typed input. A resumed workflow runs its tools at least once, so any
    irreversible act needs its own duplicate guard.

18. Make the gates durable or say plainly that they are not. Wrap the graph in
    `App(..., resumability_config=ResumabilityConfig(is_resumable=True))` and pass
    a persisting session service, never the in-memory one. Note in the file that
    the command line and the web UI cannot resume a run, so whoever releases these
    gates needs an operator surface that somebody has to write.

19. Every `Agent` in the graph gets `mode="single_turn"` and no `sub_agents`.
    A non-empty `sub_agents` list silently adds a transfer tool, and a model that
    uses it runs a different agent in this node's place while the graph's outgoing
    edge fires on schedule regardless: the topology is honoured perfectly and the
    work belongs to somebody else.

20. Model failure as a route, not as an exception. A node that raises does not
    propagate: the failure is caught, recorded, and shuts the workflow down without
    raising to the caller. So a phase that can fail catches its own failure and
    returns `Event(route="could-not-finish")`, and the exception phase hangs off
    that arm.

21. Keep every blank as a named module-level constant and never interpolate one
    into an `instruction=` string. Angle brackets and curly braces are ADK's own
    data selector syntax inside instructions, so a blank pasted verbatim stops
    being a blank and becomes a selector.

22. `by:` and `not-before:` have no expression, and `@node(timeout=)` is not
    one: it is an in-process wall clock that cancels the node and, because failures
    are swallowed, ends the run silently rather than recording a missed deadline.
    Nothing in `run-scoped:` has an expression either, and it must not be faked as
    an ordinary node, because a node has to be reached and has to finish before
    anything downstream starts, which is the opposite of what those lines mean.
    Leave both out of the graph and name them in the fidelity note.

Produce a second file alongside it, `FIDELITY.md`, and treat it as the more
important of the two. The code is for whoever builds this. The fidelity note
is for whoever has to decide whether this platform suits the process at all,
and that is usually a different person who will never read the code.

It has three parts.

**What came across.** Briefly: how many phases became steps, how many handoff
keys became state fields, which gates stop the run, which deviations became
edges. Counts and names, not reassurance.

**What did not, and what was done instead.** One entry per gap. For each one,
say what the document requires, what the platform can actually express, what
you did in its place, and what breaks if somebody later removes your
workaround. This last part matters most: a workaround nobody understands is a
workaround somebody deletes.

**What a person still has to decide.** The blanks are not a translation
failure, they are the point of a reference process, so list what has to be
filled in before this could run against anything real, and say which of those
choices the platform constrains.

Write it in plain English for somebody who has not read the specification, and
do not soften it. A translation of a reference process is a draft to argue
with, not a build artifact, and the honest account of what was lost is the most
useful thing you will produce.

Here is the process document.

```
PROCESS: conversion experiment        id: <team>/conversion-experiment   v1
from: ref/mkt/conversion-experiment v1
owner: <who>                          effective: <date>
trigger: a hypothesis is accepted for testing in <your planning process>
         watch: record=<hypothesis>
                system=<your planning process>
                change=<a hypothesis is accepted for testing>
concurrency: runs may overlap - <how many> tests live on the same
             visitors at once
goal: a change tested against the version it replaces, read on the date
      the test was sized for, and rolled out or reverted by a named
      person
phases:
  take-in-hypothesis - human: write down what the change is meant to
                       do, to whom, and what would count as it having
                       worked
                       owner: study-manager      after: trigger
                       automation: <level>
  set-terms          - human: the change, the audience it is shown to,
                       the one measure that decides, and the measures
                       that must not get worse. <who> confirms them
                       owner: study-manager
                       after: take-in-hypothesis
                       automation: <level>
  size-test          - human: the traffic the test needs, how long that
                       takes, and the date the result may be read
                       owner: statistician       after: set-terms
                       by: <days>                automation: <level>
  clear-traffic      - human: the other tests and the other changes due
                       on the same visitors while this one runs
                       owner: study-manager      after: set-terms
                       by: <days>                automation: <level>
  brief-makers       - convenes briefing: the versions, the deciding
                       measure and the run length, heard by every agent
                       at once
                       owner: study-manager
                       after: size-test + clear-traffic
                       automation: <level>
  produce-variants   - runs build-by-talent: the copy and the visuals
                       for each version being compared
                       owner: study-manager      after: brief-makers
                       by: <days>                automation: <level>
  build-variants     - human: each version assembled in the site, and
                       the split set up to send visitors to them
                       owner: web-producer       after: produce-variants
                       by: <days>                automation: <level>
  wire-measurement   - human: the deciding measure and every guardrail
                       measure, counted separately on each version
                       owner: conversion-tracker after: build-variants
                       automation: <level>
  get-sign-offs      - convenes approval: brand, accessibility and
                       legal sign, as named signers, against every
                       version the test will show
                       owner: <your legal role>  after: wire-measurement
                       by: <days>                automation: never
  check-setup        - runs assessment: a dry run showing each version
                       serving and each of its numbers arriving
                       owner: conversion-tracker after: get-sign-offs
                       by: <days>                automation: <level>
  start-test         - human: the named owner says go and the traffic
                       starts splitting
                       owner: study-manager      after: check-setup
                       automation: <level>
  watch-test         - human: delivery, the split as it is running, and
                       the guardrail measures
                       owner: statistician       after: start-test
                       automation: <level>
  read-result        - runs collect-and-report: the number on each
                       version, the size of the difference, and the
                       range around it
                       owner: statistician       after: watch-test
                       by: the read date         automation: <level>
  decide-outcome     - convenes decide-and-announce: a named person
                       says roll it out or put it back, with the
                       reasons said out loud
                       owner: study-manager      after: read-result
                       by: <days>                automation: never
  carry-out          - human: one version goes to everyone, or the
                       change comes out and the original stands
                       owner: web-producer       after: decide-outcome
                       by: <days>                automation: <level>
  record-learnings   - convenes debrief: the finding, filed with the
                       numbers and the design it rests on
                       owner: study-manager      after: carry-out
                       automation: <level>
run-scoped:
  health - runs collect-and-report              owner: statistician
           every: <cadence>
           from: start-test   until: read-result
  status - runs roll-call                       owner: study-manager
           every: <cadence>
           from: brief-makers   until: carry-out
handoffs:
  take-in-hypothesis -> set-terms [the-hypothesis]: the hypothesis in
    one line the test can settle, and who it is about
  set-terms -> size-test [deciding-measure]: the deciding measure, the
    rate it runs at now, and the smallest improvement worth acting on
  set-terms -> clear-traffic [audience-and-dates]: the audience the
    test runs on, and the dates it needs those visitors for
  size-test -> brief-makers [test-size]: the traffic the test needs,
    the run length, the read date, and the rule saying what would end
    the test early
  clear-traffic -> brief-makers [booked-traffic]: the tests and changes
    already booked on the same visitors, and what was moved to make
    room
  brief-makers -> produce-variants [variant-brief]: the request as
    every agent heard it, and which version each maker is building
  produce-variants -> build-variants [variant-content]: the copy and
    the visuals for every version, at a version
  build-variants -> wire-measurement [served-variants]: each version as
    it will be served, and the rule that decides which visitor sees
    which one
  wire-measurement -> get-sign-offs [measured-variants]: every version
    at a version, with the deciding measure and the guardrail measures
    named against it
  get-sign-offs -> check-setup [approved-variants]: the approved
    versions at the signed version. A later change voids the approval
    and sign-offs run again
  check-setup -> start-test [setup-proof]: a dated record showing every
    version serving and every measure arriving
  start-test -> watch-test [split-start]: the time the split started,
    and the date the result may be read
  watch-test -> read-result [traffic-delivered]: the traffic each
    version got, set against the traffic the test was sized for
  read-result -> decide-outcome [result-reading]: the number on each
    version with the range around it, the size of the difference,
    whether that difference is larger than the noise, and what the
    guardrail measures did
  decide-outcome -> carry-out [outcome-decision]: the decision, the
    person who made it, and the version that stands
  carry-out -> record-learnings [live-version]: what is live now, and
    the numbers the decision rested on
deviations:
  get-sign-offs -> produce-variants [sign-off-changes]: a signer comes
    back with changes, so the version they named is made again
  check-setup -> build-variants [version-will-not-serve]: a version
    does not serve in the dry run, so it is built again
  check-setup -> wire-measurement [numbers-do-not-arrive]: a version's
    numbers do not arrive in the dry run, so the measurement is wired
    again
  watch-test -> get-sign-offs [changed-mid-run]: a version is changed
    while the test is live, which voids the approval and starts the
    traffic count again
  watch-test -> clear-traffic [visitors-taken]: another change lands on
    the same visitors mid-run, so the test is recorded as spoiled and
    the traffic is cleared again before it starts over
  watch-test -> decide-outcome [guardrail-gets-worse]: a guardrail
    measure gets worse while the test is live, so the decision is put
    to a person on the partial numbers and nothing is read at
    read-result
  read-result -> watch-test [traffic-fell-short]: the read date arrives
    with less traffic than the test was sized for, so the result is
    recorded as undecided and a person says whether the test runs on
bindings:
  roster:  <who holds each role - agents claiming the abstract agents
           above, and named people for leadership and legal>
  systems: the website's content system (write), the website (write),
           the traffic splitting system (write),
           analytics platforms (write), the test register (write),
           the calculation record (write), the CRM (read)
  data:    brand guidelines <version>, <your claims register>,
           <your accessibility standard> <version>, the hypothesis as
           it was accepted, the current rate of the deciding measure
policy:
  the deciding measure is not read before the date the test was sized
    for, whoever asks for it
  a test that ends with less traffic than it was sized for is recorded
    as undecided
  only a named person ends a running test early, and the reason is
    recorded with the partial numbers
  sign-off is a human gate and is never delegated to an agent
  a version changed after sign-off goes back through sign-offs, and the
    traffic count starts again
  nothing starts splitting traffic without a recorded go from the named
    owner
measures:
  cycle time: <target> from the hypothesis to the read
  volume: <tests per period>
  quality gate: no result is reported without the range around it and
                the traffic it rests on
```