Measure Brand Health

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: measure brand health         id: <team>/brand-health   v1
from: ref/mkt/brand-health v1
owner: <who>                          effective: <date>
trigger: a tracking cycle comes round on <your tracker's schedule>
         watch: record=<tracking cycle>
                system=<your tracker's schedule>
                change=<a cycle comes round>
concurrency: one wave at a time in the same market. Waves in different
             markets overlap - <how many> in the field at once
goal: awareness, perception and preference read among people outside
      the organization, set beside the promise the brand makes and
      beside the earlier waves, and reported on the date they are due
phases:
  open-the-cycle   - human: the dates of the wave, the markets it
                     covers, and the waves it has to stay comparable to
                     owner: study-manager      after: trigger
                     automation: <level>
  read-the-promise - human: the brand standard at the version in force,
                     and the claims the promise makes
                     owner: standards-keeper   after: open-the-cycle
                     automation: <level>
  settle-measures  - convenes decide-and-announce: what this wave
                     measures - awareness, perception, preference, and
                     the attributes the promise claims
                     owner: decision-coordinator
                     after: read-the-promise   automation: <level>
  competitor-set   - human: the rivals asked about beside the brand,
                     and the reason each one is in the set
                     owner: study-manager      after: settle-measures
                     automation: <level>
  brief-the-wave   - convenes briefing: what the wave measures, the
                     competitor set and the dates, heard by every agent
                     at once
                     owner: study-manager      after: competitor-set
                     automation: <level>
  size-the-sample  - human: how many responses the wave needs in each
                     market and each segment it reports on, and what
                     that number was computed from
                     owner: statistician       after: brief-the-wave
                     by: <days>                automation: <level>
  define-sample    - human: who gets asked, how many of them, and how
                     the drawn sample matches <your market> on the
                     traits the findings are broken down by
                     owner: study-manager      after: size-the-sample
                     by: <days>                automation: <level>
  check-consent    - runs assessment: the drawn sample scored against
                     the consent rules in force, contact by contact
                     owner: consent-manager    after: define-sample
                     automation: <level>
  outside-sample   - runs collect-and-report: the same requirements put
                     to every provider that can supply the people the
                     contact base does not reach, which for a reading
                     of the whole market is most of them
                     owner: supplier-manager   after: define-sample
                     by: <days>                automation: <level>
  cover-the-cost   - runs allocate-and-reconcile: the panel and the
                     incentives, drawn against <which allocation>
                     owner: budget-keeper      after: outside-sample
                     automation: <level>
  carry-questions  - human: last wave's questions at the version they
                     ran under, kept word for word, with every change
                     written down and its reason beside it
                     owner: study-manager      after: brief-the-wave
                     by: <days>                automation: <level>
  get-sign-offs    - convenes approval: legal and the brand owner sign,
                     as named signers, against a version of the sample
                     and a version of the questions
                     owner: <your legal role>
                     after: check-consent + cover-the-cost +
                            carry-questions
                     by: <days>                automation: never
  field-the-wave   - human: the invitations go out and the responses
                     land as they were given
                     owner: study-manager      after: get-sign-offs
                     by: <days>                automation: <level>
  watch-sample     - runs roll-call: how many have answered in each
                     market and each segment, and where the sample is
                     filling more slowly than the wave allowed for
                     owner: study-manager      after: field-the-wave
                     every: <cadence>          automation: <level>
  close-the-wave   - human: asking stops on the date or on the count,
                     and the responses are fixed at a version
                     owner: study-manager      after: watch-sample
                     automation: <level>
  work-out-figures - human: the weighting that brings the sample back
                     to <your market>, and each figure with its method,
                     its exclusions and the range around it
                     owner: statistician       after: close-the-wave
                     by: <days>                automation: <level>
  compare-waves    - human: this wave beside the earlier ones, with a
                     verdict on every movement saying whether it is
                     larger than the noise in the measurement
                     owner: statistician       after: work-out-figures
                     by: <days>                automation: <level>
  read-published   - runs collect-and-report: what outlets, analysts,
                     research firms and review sites published about
                     the brand and the category during the cycle
                     owner: coverage-monitor   after: brief-the-wave
                     every: <cadence>          automation: <level>
  perception-gap   - human: each attribute the wave measured set beside
                     the claim the promise makes about it, naming where
                     what people believe misses what the brand claims
                     owner: study-manager
                     after: compare-waves + read-published
                     by: <days>                automation: <level>
  write-findings   - human: what the wave found, each finding with the
                     responses recorded under it
                     owner: study-manager      after: perception-gap
                     by: <days>                automation: <level>
  check-findings   - runs layered-passes: the numbers pass, every
                     figure against the data and the method beside it
                     owner: statistician       after: write-findings
                     by: <days>                automation: <level>
  report-the-wave  - runs collect-and-report: awareness, perception and
                     preference on their date, complete or not, with
                     the evidence under every line and the version of
                     the promise the figures were read against
                     owner: study-manager      after: check-findings
                     automation: <level>
  record-learnings - convenes debrief: what to repeat, what to avoid
                     owner: study-manager      after: report-the-wave
                     automation: <level>
run-scoped:
  spend  - runs allocate-and-reconcile        owner: budget-keeper
           from: cover-the-cost   until: run close
  status - runs roll-call                     owner: study-manager
           every: <cadence>
           from: brief-the-wave   until: report-the-wave
handoffs:
  open-the-cycle -> read-the-promise [wave-dates]: the dates of the
    wave and the earlier waves this one has to stay comparable to
  read-the-promise -> settle-measures [brand-promise]: the brand
    standard at the version in force, and the claims the promise makes
  settle-measures -> competitor-set [wave-measures]: what the wave
    measures, and the attributes it puts to people
  competitor-set -> brief-the-wave [rivals]: the rivals asked about
    beside the brand, and the reason each one is in the set
  brief-the-wave -> size-the-sample [movement-threshold]: the
    measures, the size of the movement that would matter to a
    decision, and the confidence the wave is being run to
  brief-the-wave -> carry-questions [earlier-questions]: the measures
    as every agent heard them, and the earlier questions at the
    versions they ran under
  brief-the-wave -> read-published [watch-list]: what to watch for
    during the cycle
  size-the-sample -> define-sample [response-counts]: how many
    responses the wave needs in each market and each segment, and what
    that was computed from
  define-sample -> check-consent [drawn-sample]: the drawn sample,
    contact by contact, with the source each contact came from
  define-sample -> outside-sample [sample-shortfall]: the people the
    contact base cannot supply, and what the wave needs them to be
  check-consent -> get-sign-offs [contactable-sample]: the sample that
    may be contacted, the count removed, and the rule behind each
    removal
  outside-sample -> cover-the-cost [provider-quotes]: what each
    provider would charge for the sample, and what it would deliver
  cover-the-cost -> get-sign-offs [wave-cost]: what the wave will
    draw, and the allocation it draws against
  carry-questions -> get-sign-offs [wave-questions]: the questions at
    a version, every change from the last wave marked, and the reason
    for each change
  get-sign-offs -> field-the-wave [signed-wave]: the approved sample
    and the approved questions at their signed versions. A later
    change voids the approval and sign-offs run again
  field-the-wave -> watch-sample [responses]: the responses as they
    arrive, each marked with the version of the questions it answered
  watch-sample -> close-the-wave [fill-counts]: the count answered set
    against the count the wave planned for, market by market
  close-the-wave -> work-out-figures [fixed-responses]: the responses
    fixed at a version, with every response that was removed and the
    rule that removed it
  work-out-figures -> compare-waves [wave-figures]: every figure with
    its method, its weighting, its exclusions and the range around it
  compare-waves -> perception-gap [movement-verdicts]: each measure
    beside its earlier readings, with a verdict on every movement
  read-published -> perception-gap [published-mentions]: what was
    published during the cycle, each mention with its outlet, its date
    and what it said
  perception-gap -> write-findings [promise-gaps]: each attribute set
    beside the claim the promise makes about it, and the version of
    the promise it was read against
  write-findings -> check-findings [draft-findings]: the findings at a
    version, each with the responses recorded under it
  check-findings -> report-the-wave [checked-findings]: the findings
    with every figure checked against the data and the method beside
    it, and every figure that could not be computed marked as such
  report-the-wave -> record-learnings [wave-report]: the report, as
    delivered
deviations:
  check-consent -> define-sample [too-few-contactable]: the consent
    check removes most of the drawn sample, so the sample is drawn
    again or the wave buys the people it cannot reach
  carry-questions -> settle-measures [wording-must-change]: a tracked
    question has to be reworded, so what the wave measures is settled
    again and <who> agrees the change before it is made
  get-sign-offs -> carry-questions [sign-off-changes-questions]: a
    signer asks for changes to the questions, so only what they named
    is carried forward again
  watch-sample -> field-the-wave [sample-filling-slowly]: fewer have
    answered than the wave allowed for, so fielding continues in the
    markets that are short
  work-out-figures -> field-the-wave [sample-fell-short]: the wave
    closed short of what it needed, so it fields again, reports with
    the shortfall named against every finding, or is dropped
  check-findings -> write-findings [figure-does-not-follow]: a figure
    does not follow from the data and the method beside it, so the
    finding is written again
bindings:
  roster:  <who holds each role - agents claiming the abstract agents
           above, and named people for legal, finance, the brand owner
           and leadership>
  systems: the study record (write), the questions and material
           (write), the response record (write), the calculation record
           (write), the survey and interview system (trigger),
           the contact database (read), the consent record (read),
           the sending system (write), the standards store (read),
           the coverage record (write), the supplier record (write),
           the budget record (write), the report store (write),
           the meeting calendar (write)
  data:    brand guidelines <version> - the promise and the attributes
           it claims, <your consent rules> <version>, the earlier waves
           at the versions they ran under, the terms attached to every
           sample bought from outside
policy:
  every figure reported here comes from people outside the
    organization. A number from the department's own systems is never
    reported as a perception figure
  nobody is asked anything until the sample and the questions have been
    signed
  sign-off is a human gate and is never delegated to an agent
  a tracked question is reworded only when <who> agrees, and the wave
    that reworded it reports the old wording and the new one
  the competitor set changes only when <who> agrees, and a wave that
    changed it says so against every share it reports
  a movement inside the noise is reported as no movement
  every finding carries the responses it rests on, and a finding
    resting on fewer responses than the wave needed says so
  every figure carries its method, its weighting, its exclusions and
    the range around it
  responses are kept as they were given, and a response left out of a
    count is left out under a named rule
  a finding is never removed from the report because somebody asked.
    <who> decides, and the decision is recorded with the findings
measures:
  cycle time: <target> from the cycle opening to the reported findings
  comparability: <share> of tracked questions carried forward with
                 their wording unchanged
  completion: <share> of the drawn sample that fills to the count the
              wave planned for
  volume: <waves per period>
  quality gate: no movement is reported as a result without the
                statistician's verdict that it is larger than the noise
```

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: measure brand health         id: <team>/brand-health   v1
from: ref/mkt/brand-health v1
owner: <who>                          effective: <date>
trigger: a tracking cycle comes round on <your tracker's schedule>
         watch: record=<tracking cycle>
                system=<your tracker's schedule>
                change=<a cycle comes round>
concurrency: one wave at a time in the same market. Waves in different
             markets overlap - <how many> in the field at once
goal: awareness, perception and preference read among people outside
      the organization, set beside the promise the brand makes and
      beside the earlier waves, and reported on the date they are due
phases:
  open-the-cycle   - human: the dates of the wave, the markets it
                     covers, and the waves it has to stay comparable to
                     owner: study-manager      after: trigger
                     automation: <level>
  read-the-promise - human: the brand standard at the version in force,
                     and the claims the promise makes
                     owner: standards-keeper   after: open-the-cycle
                     automation: <level>
  settle-measures  - convenes decide-and-announce: what this wave
                     measures - awareness, perception, preference, and
                     the attributes the promise claims
                     owner: decision-coordinator
                     after: read-the-promise   automation: <level>
  competitor-set   - human: the rivals asked about beside the brand,
                     and the reason each one is in the set
                     owner: study-manager      after: settle-measures
                     automation: <level>
  brief-the-wave   - convenes briefing: what the wave measures, the
                     competitor set and the dates, heard by every agent
                     at once
                     owner: study-manager      after: competitor-set
                     automation: <level>
  size-the-sample  - human: how many responses the wave needs in each
                     market and each segment it reports on, and what
                     that number was computed from
                     owner: statistician       after: brief-the-wave
                     by: <days>                automation: <level>
  define-sample    - human: who gets asked, how many of them, and how
                     the drawn sample matches <your market> on the
                     traits the findings are broken down by
                     owner: study-manager      after: size-the-sample
                     by: <days>                automation: <level>
  check-consent    - runs assessment: the drawn sample scored against
                     the consent rules in force, contact by contact
                     owner: consent-manager    after: define-sample
                     automation: <level>
  outside-sample   - runs collect-and-report: the same requirements put
                     to every provider that can supply the people the
                     contact base does not reach, which for a reading
                     of the whole market is most of them
                     owner: supplier-manager   after: define-sample
                     by: <days>                automation: <level>
  cover-the-cost   - runs allocate-and-reconcile: the panel and the
                     incentives, drawn against <which allocation>
                     owner: budget-keeper      after: outside-sample
                     automation: <level>
  carry-questions  - human: last wave's questions at the version they
                     ran under, kept word for word, with every change
                     written down and its reason beside it
                     owner: study-manager      after: brief-the-wave
                     by: <days>                automation: <level>
  get-sign-offs    - convenes approval: legal and the brand owner sign,
                     as named signers, against a version of the sample
                     and a version of the questions
                     owner: <your legal role>
                     after: check-consent + cover-the-cost +
                            carry-questions
                     by: <days>                automation: never
  field-the-wave   - human: the invitations go out and the responses
                     land as they were given
                     owner: study-manager      after: get-sign-offs
                     by: <days>                automation: <level>
  watch-sample     - runs roll-call: how many have answered in each
                     market and each segment, and where the sample is
                     filling more slowly than the wave allowed for
                     owner: study-manager      after: field-the-wave
                     every: <cadence>          automation: <level>
  close-the-wave   - human: asking stops on the date or on the count,
                     and the responses are fixed at a version
                     owner: study-manager      after: watch-sample
                     automation: <level>
  work-out-figures - human: the weighting that brings the sample back
                     to <your market>, and each figure with its method,
                     its exclusions and the range around it
                     owner: statistician       after: close-the-wave
                     by: <days>                automation: <level>
  compare-waves    - human: this wave beside the earlier ones, with a
                     verdict on every movement saying whether it is
                     larger than the noise in the measurement
                     owner: statistician       after: work-out-figures
                     by: <days>                automation: <level>
  read-published   - runs collect-and-report: what outlets, analysts,
                     research firms and review sites published about
                     the brand and the category during the cycle
                     owner: coverage-monitor   after: brief-the-wave
                     every: <cadence>          automation: <level>
  perception-gap   - human: each attribute the wave measured set beside
                     the claim the promise makes about it, naming where
                     what people believe misses what the brand claims
                     owner: study-manager
                     after: compare-waves + read-published
                     by: <days>                automation: <level>
  write-findings   - human: what the wave found, each finding with the
                     responses recorded under it
                     owner: study-manager      after: perception-gap
                     by: <days>                automation: <level>
  check-findings   - runs layered-passes: the numbers pass, every
                     figure against the data and the method beside it
                     owner: statistician       after: write-findings
                     by: <days>                automation: <level>
  report-the-wave  - runs collect-and-report: awareness, perception and
                     preference on their date, complete or not, with
                     the evidence under every line and the version of
                     the promise the figures were read against
                     owner: study-manager      after: check-findings
                     automation: <level>
  record-learnings - convenes debrief: what to repeat, what to avoid
                     owner: study-manager      after: report-the-wave
                     automation: <level>
run-scoped:
  spend  - runs allocate-and-reconcile        owner: budget-keeper
           from: cover-the-cost   until: run close
  status - runs roll-call                     owner: study-manager
           every: <cadence>
           from: brief-the-wave   until: report-the-wave
handoffs:
  open-the-cycle -> read-the-promise [wave-dates]: the dates of the
    wave and the earlier waves this one has to stay comparable to
  read-the-promise -> settle-measures [brand-promise]: the brand
    standard at the version in force, and the claims the promise makes
  settle-measures -> competitor-set [wave-measures]: what the wave
    measures, and the attributes it puts to people
  competitor-set -> brief-the-wave [rivals]: the rivals asked about
    beside the brand, and the reason each one is in the set
  brief-the-wave -> size-the-sample [movement-threshold]: the
    measures, the size of the movement that would matter to a
    decision, and the confidence the wave is being run to
  brief-the-wave -> carry-questions [earlier-questions]: the measures
    as every agent heard them, and the earlier questions at the
    versions they ran under
  brief-the-wave -> read-published [watch-list]: what to watch for
    during the cycle
  size-the-sample -> define-sample [response-counts]: how many
    responses the wave needs in each market and each segment, and what
    that was computed from
  define-sample -> check-consent [drawn-sample]: the drawn sample,
    contact by contact, with the source each contact came from
  define-sample -> outside-sample [sample-shortfall]: the people the
    contact base cannot supply, and what the wave needs them to be
  check-consent -> get-sign-offs [contactable-sample]: the sample that
    may be contacted, the count removed, and the rule behind each
    removal
  outside-sample -> cover-the-cost [provider-quotes]: what each
    provider would charge for the sample, and what it would deliver
  cover-the-cost -> get-sign-offs [wave-cost]: what the wave will
    draw, and the allocation it draws against
  carry-questions -> get-sign-offs [wave-questions]: the questions at
    a version, every change from the last wave marked, and the reason
    for each change
  get-sign-offs -> field-the-wave [signed-wave]: the approved sample
    and the approved questions at their signed versions. A later
    change voids the approval and sign-offs run again
  field-the-wave -> watch-sample [responses]: the responses as they
    arrive, each marked with the version of the questions it answered
  watch-sample -> close-the-wave [fill-counts]: the count answered set
    against the count the wave planned for, market by market
  close-the-wave -> work-out-figures [fixed-responses]: the responses
    fixed at a version, with every response that was removed and the
    rule that removed it
  work-out-figures -> compare-waves [wave-figures]: every figure with
    its method, its weighting, its exclusions and the range around it
  compare-waves -> perception-gap [movement-verdicts]: each measure
    beside its earlier readings, with a verdict on every movement
  read-published -> perception-gap [published-mentions]: what was
    published during the cycle, each mention with its outlet, its date
    and what it said
  perception-gap -> write-findings [promise-gaps]: each attribute set
    beside the claim the promise makes about it, and the version of
    the promise it was read against
  write-findings -> check-findings [draft-findings]: the findings at a
    version, each with the responses recorded under it
  check-findings -> report-the-wave [checked-findings]: the findings
    with every figure checked against the data and the method beside
    it, and every figure that could not be computed marked as such
  report-the-wave -> record-learnings [wave-report]: the report, as
    delivered
deviations:
  check-consent -> define-sample [too-few-contactable]: the consent
    check removes most of the drawn sample, so the sample is drawn
    again or the wave buys the people it cannot reach
  carry-questions -> settle-measures [wording-must-change]: a tracked
    question has to be reworded, so what the wave measures is settled
    again and <who> agrees the change before it is made
  get-sign-offs -> carry-questions [sign-off-changes-questions]: a
    signer asks for changes to the questions, so only what they named
    is carried forward again
  watch-sample -> field-the-wave [sample-filling-slowly]: fewer have
    answered than the wave allowed for, so fielding continues in the
    markets that are short
  work-out-figures -> field-the-wave [sample-fell-short]: the wave
    closed short of what it needed, so it fields again, reports with
    the shortfall named against every finding, or is dropped
  check-findings -> write-findings [figure-does-not-follow]: a figure
    does not follow from the data and the method beside it, so the
    finding is written again
bindings:
  roster:  <who holds each role - agents claiming the abstract agents
           above, and named people for legal, finance, the brand owner
           and leadership>
  systems: the study record (write), the questions and material
           (write), the response record (write), the calculation record
           (write), the survey and interview system (trigger),
           the contact database (read), the consent record (read),
           the sending system (write), the standards store (read),
           the coverage record (write), the supplier record (write),
           the budget record (write), the report store (write),
           the meeting calendar (write)
  data:    brand guidelines <version> - the promise and the attributes
           it claims, <your consent rules> <version>, the earlier waves
           at the versions they ran under, the terms attached to every
           sample bought from outside
policy:
  every figure reported here comes from people outside the
    organization. A number from the department's own systems is never
    reported as a perception figure
  nobody is asked anything until the sample and the questions have been
    signed
  sign-off is a human gate and is never delegated to an agent
  a tracked question is reworded only when <who> agrees, and the wave
    that reworded it reports the old wording and the new one
  the competitor set changes only when <who> agrees, and a wave that
    changed it says so against every share it reports
  a movement inside the noise is reported as no movement
  every finding carries the responses it rests on, and a finding
    resting on fewer responses than the wave needed says so
  every figure carries its method, its weighting, its exclusions and
    the range around it
  responses are kept as they were given, and a response left out of a
    count is left out under a named rule
  a finding is never removed from the report because somebody asked.
    <who> decides, and the decision is recorded with the findings
measures:
  cycle time: <target> from the cycle opening to the reported findings
  comparability: <share> of tracked questions carried forward with
                 their wording unchanged
  completion: <share> of the drawn sample that fills to the count the
              wave planned for
  volume: <waves per period>
  quality gate: no movement is reported as a result without the
                statistician's verdict that it is larger than the noise
```

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: measure brand health         id: <team>/brand-health   v1
from: ref/mkt/brand-health v1
owner: <who>                          effective: <date>
trigger: a tracking cycle comes round on <your tracker's schedule>
         watch: record=<tracking cycle>
                system=<your tracker's schedule>
                change=<a cycle comes round>
concurrency: one wave at a time in the same market. Waves in different
             markets overlap - <how many> in the field at once
goal: awareness, perception and preference read among people outside
      the organization, set beside the promise the brand makes and
      beside the earlier waves, and reported on the date they are due
phases:
  open-the-cycle   - human: the dates of the wave, the markets it
                     covers, and the waves it has to stay comparable to
                     owner: study-manager      after: trigger
                     automation: <level>
  read-the-promise - human: the brand standard at the version in force,
                     and the claims the promise makes
                     owner: standards-keeper   after: open-the-cycle
                     automation: <level>
  settle-measures  - convenes decide-and-announce: what this wave
                     measures - awareness, perception, preference, and
                     the attributes the promise claims
                     owner: decision-coordinator
                     after: read-the-promise   automation: <level>
  competitor-set   - human: the rivals asked about beside the brand,
                     and the reason each one is in the set
                     owner: study-manager      after: settle-measures
                     automation: <level>
  brief-the-wave   - convenes briefing: what the wave measures, the
                     competitor set and the dates, heard by every agent
                     at once
                     owner: study-manager      after: competitor-set
                     automation: <level>
  size-the-sample  - human: how many responses the wave needs in each
                     market and each segment it reports on, and what
                     that number was computed from
                     owner: statistician       after: brief-the-wave
                     by: <days>                automation: <level>
  define-sample    - human: who gets asked, how many of them, and how
                     the drawn sample matches <your market> on the
                     traits the findings are broken down by
                     owner: study-manager      after: size-the-sample
                     by: <days>                automation: <level>
  check-consent    - runs assessment: the drawn sample scored against
                     the consent rules in force, contact by contact
                     owner: consent-manager    after: define-sample
                     automation: <level>
  outside-sample   - runs collect-and-report: the same requirements put
                     to every provider that can supply the people the
                     contact base does not reach, which for a reading
                     of the whole market is most of them
                     owner: supplier-manager   after: define-sample
                     by: <days>                automation: <level>
  cover-the-cost   - runs allocate-and-reconcile: the panel and the
                     incentives, drawn against <which allocation>
                     owner: budget-keeper      after: outside-sample
                     automation: <level>
  carry-questions  - human: last wave's questions at the version they
                     ran under, kept word for word, with every change
                     written down and its reason beside it
                     owner: study-manager      after: brief-the-wave
                     by: <days>                automation: <level>
  get-sign-offs    - convenes approval: legal and the brand owner sign,
                     as named signers, against a version of the sample
                     and a version of the questions
                     owner: <your legal role>
                     after: check-consent + cover-the-cost +
                            carry-questions
                     by: <days>                automation: never
  field-the-wave   - human: the invitations go out and the responses
                     land as they were given
                     owner: study-manager      after: get-sign-offs
                     by: <days>                automation: <level>
  watch-sample     - runs roll-call: how many have answered in each
                     market and each segment, and where the sample is
                     filling more slowly than the wave allowed for
                     owner: study-manager      after: field-the-wave
                     every: <cadence>          automation: <level>
  close-the-wave   - human: asking stops on the date or on the count,
                     and the responses are fixed at a version
                     owner: study-manager      after: watch-sample
                     automation: <level>
  work-out-figures - human: the weighting that brings the sample back
                     to <your market>, and each figure with its method,
                     its exclusions and the range around it
                     owner: statistician       after: close-the-wave
                     by: <days>                automation: <level>
  compare-waves    - human: this wave beside the earlier ones, with a
                     verdict on every movement saying whether it is
                     larger than the noise in the measurement
                     owner: statistician       after: work-out-figures
                     by: <days>                automation: <level>
  read-published   - runs collect-and-report: what outlets, analysts,
                     research firms and review sites published about
                     the brand and the category during the cycle
                     owner: coverage-monitor   after: brief-the-wave
                     every: <cadence>          automation: <level>
  perception-gap   - human: each attribute the wave measured set beside
                     the claim the promise makes about it, naming where
                     what people believe misses what the brand claims
                     owner: study-manager
                     after: compare-waves + read-published
                     by: <days>                automation: <level>
  write-findings   - human: what the wave found, each finding with the
                     responses recorded under it
                     owner: study-manager      after: perception-gap
                     by: <days>                automation: <level>
  check-findings   - runs layered-passes: the numbers pass, every
                     figure against the data and the method beside it
                     owner: statistician       after: write-findings
                     by: <days>                automation: <level>
  report-the-wave  - runs collect-and-report: awareness, perception and
                     preference on their date, complete or not, with
                     the evidence under every line and the version of
                     the promise the figures were read against
                     owner: study-manager      after: check-findings
                     automation: <level>
  record-learnings - convenes debrief: what to repeat, what to avoid
                     owner: study-manager      after: report-the-wave
                     automation: <level>
run-scoped:
  spend  - runs allocate-and-reconcile        owner: budget-keeper
           from: cover-the-cost   until: run close
  status - runs roll-call                     owner: study-manager
           every: <cadence>
           from: brief-the-wave   until: report-the-wave
handoffs:
  open-the-cycle -> read-the-promise [wave-dates]: the dates of the
    wave and the earlier waves this one has to stay comparable to
  read-the-promise -> settle-measures [brand-promise]: the brand
    standard at the version in force, and the claims the promise makes
  settle-measures -> competitor-set [wave-measures]: what the wave
    measures, and the attributes it puts to people
  competitor-set -> brief-the-wave [rivals]: the rivals asked about
    beside the brand, and the reason each one is in the set
  brief-the-wave -> size-the-sample [movement-threshold]: the
    measures, the size of the movement that would matter to a
    decision, and the confidence the wave is being run to
  brief-the-wave -> carry-questions [earlier-questions]: the measures
    as every agent heard them, and the earlier questions at the
    versions they ran under
  brief-the-wave -> read-published [watch-list]: what to watch for
    during the cycle
  size-the-sample -> define-sample [response-counts]: how many
    responses the wave needs in each market and each segment, and what
    that was computed from
  define-sample -> check-consent [drawn-sample]: the drawn sample,
    contact by contact, with the source each contact came from
  define-sample -> outside-sample [sample-shortfall]: the people the
    contact base cannot supply, and what the wave needs them to be
  check-consent -> get-sign-offs [contactable-sample]: the sample that
    may be contacted, the count removed, and the rule behind each
    removal
  outside-sample -> cover-the-cost [provider-quotes]: what each
    provider would charge for the sample, and what it would deliver
  cover-the-cost -> get-sign-offs [wave-cost]: what the wave will
    draw, and the allocation it draws against
  carry-questions -> get-sign-offs [wave-questions]: the questions at
    a version, every change from the last wave marked, and the reason
    for each change
  get-sign-offs -> field-the-wave [signed-wave]: the approved sample
    and the approved questions at their signed versions. A later
    change voids the approval and sign-offs run again
  field-the-wave -> watch-sample [responses]: the responses as they
    arrive, each marked with the version of the questions it answered
  watch-sample -> close-the-wave [fill-counts]: the count answered set
    against the count the wave planned for, market by market
  close-the-wave -> work-out-figures [fixed-responses]: the responses
    fixed at a version, with every response that was removed and the
    rule that removed it
  work-out-figures -> compare-waves [wave-figures]: every figure with
    its method, its weighting, its exclusions and the range around it
  compare-waves -> perception-gap [movement-verdicts]: each measure
    beside its earlier readings, with a verdict on every movement
  read-published -> perception-gap [published-mentions]: what was
    published during the cycle, each mention with its outlet, its date
    and what it said
  perception-gap -> write-findings [promise-gaps]: each attribute set
    beside the claim the promise makes about it, and the version of
    the promise it was read against
  write-findings -> check-findings [draft-findings]: the findings at a
    version, each with the responses recorded under it
  check-findings -> report-the-wave [checked-findings]: the findings
    with every figure checked against the data and the method beside
    it, and every figure that could not be computed marked as such
  report-the-wave -> record-learnings [wave-report]: the report, as
    delivered
deviations:
  check-consent -> define-sample [too-few-contactable]: the consent
    check removes most of the drawn sample, so the sample is drawn
    again or the wave buys the people it cannot reach
  carry-questions -> settle-measures [wording-must-change]: a tracked
    question has to be reworded, so what the wave measures is settled
    again and <who> agrees the change before it is made
  get-sign-offs -> carry-questions [sign-off-changes-questions]: a
    signer asks for changes to the questions, so only what they named
    is carried forward again
  watch-sample -> field-the-wave [sample-filling-slowly]: fewer have
    answered than the wave allowed for, so fielding continues in the
    markets that are short
  work-out-figures -> field-the-wave [sample-fell-short]: the wave
    closed short of what it needed, so it fields again, reports with
    the shortfall named against every finding, or is dropped
  check-findings -> write-findings [figure-does-not-follow]: a figure
    does not follow from the data and the method beside it, so the
    finding is written again
bindings:
  roster:  <who holds each role - agents claiming the abstract agents
           above, and named people for legal, finance, the brand owner
           and leadership>
  systems: the study record (write), the questions and material
           (write), the response record (write), the calculation record
           (write), the survey and interview system (trigger),
           the contact database (read), the consent record (read),
           the sending system (write), the standards store (read),
           the coverage record (write), the supplier record (write),
           the budget record (write), the report store (write),
           the meeting calendar (write)
  data:    brand guidelines <version> - the promise and the attributes
           it claims, <your consent rules> <version>, the earlier waves
           at the versions they ran under, the terms attached to every
           sample bought from outside
policy:
  every figure reported here comes from people outside the
    organization. A number from the department's own systems is never
    reported as a perception figure
  nobody is asked anything until the sample and the questions have been
    signed
  sign-off is a human gate and is never delegated to an agent
  a tracked question is reworded only when <who> agrees, and the wave
    that reworded it reports the old wording and the new one
  the competitor set changes only when <who> agrees, and a wave that
    changed it says so against every share it reports
  a movement inside the noise is reported as no movement
  every finding carries the responses it rests on, and a finding
    resting on fewer responses than the wave needed says so
  every figure carries its method, its weighting, its exclusions and
    the range around it
  responses are kept as they were given, and a response left out of a
    count is left out under a named rule
  a finding is never removed from the report because somebody asked.
    <who> decides, and the decision is recorded with the findings
measures:
  cycle time: <target> from the cycle opening to the reported findings
  comparability: <share> of tracked questions carried forward with
                 their wording unchanged
  completion: <share> of the drawn sample that fills to the count the
              wave planned for
  volume: <waves per period>
  quality gate: no movement is reported as a result without the
                statistician's verdict that it is larger than the noise
```

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: measure brand health         id: <team>/brand-health   v1
from: ref/mkt/brand-health v1
owner: <who>                          effective: <date>
trigger: a tracking cycle comes round on <your tracker's schedule>
         watch: record=<tracking cycle>
                system=<your tracker's schedule>
                change=<a cycle comes round>
concurrency: one wave at a time in the same market. Waves in different
             markets overlap - <how many> in the field at once
goal: awareness, perception and preference read among people outside
      the organization, set beside the promise the brand makes and
      beside the earlier waves, and reported on the date they are due
phases:
  open-the-cycle   - human: the dates of the wave, the markets it
                     covers, and the waves it has to stay comparable to
                     owner: study-manager      after: trigger
                     automation: <level>
  read-the-promise - human: the brand standard at the version in force,
                     and the claims the promise makes
                     owner: standards-keeper   after: open-the-cycle
                     automation: <level>
  settle-measures  - convenes decide-and-announce: what this wave
                     measures - awareness, perception, preference, and
                     the attributes the promise claims
                     owner: decision-coordinator
                     after: read-the-promise   automation: <level>
  competitor-set   - human: the rivals asked about beside the brand,
                     and the reason each one is in the set
                     owner: study-manager      after: settle-measures
                     automation: <level>
  brief-the-wave   - convenes briefing: what the wave measures, the
                     competitor set and the dates, heard by every agent
                     at once
                     owner: study-manager      after: competitor-set
                     automation: <level>
  size-the-sample  - human: how many responses the wave needs in each
                     market and each segment it reports on, and what
                     that number was computed from
                     owner: statistician       after: brief-the-wave
                     by: <days>                automation: <level>
  define-sample    - human: who gets asked, how many of them, and how
                     the drawn sample matches <your market> on the
                     traits the findings are broken down by
                     owner: study-manager      after: size-the-sample
                     by: <days>                automation: <level>
  check-consent    - runs assessment: the drawn sample scored against
                     the consent rules in force, contact by contact
                     owner: consent-manager    after: define-sample
                     automation: <level>
  outside-sample   - runs collect-and-report: the same requirements put
                     to every provider that can supply the people the
                     contact base does not reach, which for a reading
                     of the whole market is most of them
                     owner: supplier-manager   after: define-sample
                     by: <days>                automation: <level>
  cover-the-cost   - runs allocate-and-reconcile: the panel and the
                     incentives, drawn against <which allocation>
                     owner: budget-keeper      after: outside-sample
                     automation: <level>
  carry-questions  - human: last wave's questions at the version they
                     ran under, kept word for word, with every change
                     written down and its reason beside it
                     owner: study-manager      after: brief-the-wave
                     by: <days>                automation: <level>
  get-sign-offs    - convenes approval: legal and the brand owner sign,
                     as named signers, against a version of the sample
                     and a version of the questions
                     owner: <your legal role>
                     after: check-consent + cover-the-cost +
                            carry-questions
                     by: <days>                automation: never
  field-the-wave   - human: the invitations go out and the responses
                     land as they were given
                     owner: study-manager      after: get-sign-offs
                     by: <days>                automation: <level>
  watch-sample     - runs roll-call: how many have answered in each
                     market and each segment, and where the sample is
                     filling more slowly than the wave allowed for
                     owner: study-manager      after: field-the-wave
                     every: <cadence>          automation: <level>
  close-the-wave   - human: asking stops on the date or on the count,
                     and the responses are fixed at a version
                     owner: study-manager      after: watch-sample
                     automation: <level>
  work-out-figures - human: the weighting that brings the sample back
                     to <your market>, and each figure with its method,
                     its exclusions and the range around it
                     owner: statistician       after: close-the-wave
                     by: <days>                automation: <level>
  compare-waves    - human: this wave beside the earlier ones, with a
                     verdict on every movement saying whether it is
                     larger than the noise in the measurement
                     owner: statistician       after: work-out-figures
                     by: <days>                automation: <level>
  read-published   - runs collect-and-report: what outlets, analysts,
                     research firms and review sites published about
                     the brand and the category during the cycle
                     owner: coverage-monitor   after: brief-the-wave
                     every: <cadence>          automation: <level>
  perception-gap   - human: each attribute the wave measured set beside
                     the claim the promise makes about it, naming where
                     what people believe misses what the brand claims
                     owner: study-manager
                     after: compare-waves + read-published
                     by: <days>                automation: <level>
  write-findings   - human: what the wave found, each finding with the
                     responses recorded under it
                     owner: study-manager      after: perception-gap
                     by: <days>                automation: <level>
  check-findings   - runs layered-passes: the numbers pass, every
                     figure against the data and the method beside it
                     owner: statistician       after: write-findings
                     by: <days>                automation: <level>
  report-the-wave  - runs collect-and-report: awareness, perception and
                     preference on their date, complete or not, with
                     the evidence under every line and the version of
                     the promise the figures were read against
                     owner: study-manager      after: check-findings
                     automation: <level>
  record-learnings - convenes debrief: what to repeat, what to avoid
                     owner: study-manager      after: report-the-wave
                     automation: <level>
run-scoped:
  spend  - runs allocate-and-reconcile        owner: budget-keeper
           from: cover-the-cost   until: run close
  status - runs roll-call                     owner: study-manager
           every: <cadence>
           from: brief-the-wave   until: report-the-wave
handoffs:
  open-the-cycle -> read-the-promise [wave-dates]: the dates of the
    wave and the earlier waves this one has to stay comparable to
  read-the-promise -> settle-measures [brand-promise]: the brand
    standard at the version in force, and the claims the promise makes
  settle-measures -> competitor-set [wave-measures]: what the wave
    measures, and the attributes it puts to people
  competitor-set -> brief-the-wave [rivals]: the rivals asked about
    beside the brand, and the reason each one is in the set
  brief-the-wave -> size-the-sample [movement-threshold]: the
    measures, the size of the movement that would matter to a
    decision, and the confidence the wave is being run to
  brief-the-wave -> carry-questions [earlier-questions]: the measures
    as every agent heard them, and the earlier questions at the
    versions they ran under
  brief-the-wave -> read-published [watch-list]: what to watch for
    during the cycle
  size-the-sample -> define-sample [response-counts]: how many
    responses the wave needs in each market and each segment, and what
    that was computed from
  define-sample -> check-consent [drawn-sample]: the drawn sample,
    contact by contact, with the source each contact came from
  define-sample -> outside-sample [sample-shortfall]: the people the
    contact base cannot supply, and what the wave needs them to be
  check-consent -> get-sign-offs [contactable-sample]: the sample that
    may be contacted, the count removed, and the rule behind each
    removal
  outside-sample -> cover-the-cost [provider-quotes]: what each
    provider would charge for the sample, and what it would deliver
  cover-the-cost -> get-sign-offs [wave-cost]: what the wave will
    draw, and the allocation it draws against
  carry-questions -> get-sign-offs [wave-questions]: the questions at
    a version, every change from the last wave marked, and the reason
    for each change
  get-sign-offs -> field-the-wave [signed-wave]: the approved sample
    and the approved questions at their signed versions. A later
    change voids the approval and sign-offs run again
  field-the-wave -> watch-sample [responses]: the responses as they
    arrive, each marked with the version of the questions it answered
  watch-sample -> close-the-wave [fill-counts]: the count answered set
    against the count the wave planned for, market by market
  close-the-wave -> work-out-figures [fixed-responses]: the responses
    fixed at a version, with every response that was removed and the
    rule that removed it
  work-out-figures -> compare-waves [wave-figures]: every figure with
    its method, its weighting, its exclusions and the range around it
  compare-waves -> perception-gap [movement-verdicts]: each measure
    beside its earlier readings, with a verdict on every movement
  read-published -> perception-gap [published-mentions]: what was
    published during the cycle, each mention with its outlet, its date
    and what it said
  perception-gap -> write-findings [promise-gaps]: each attribute set
    beside the claim the promise makes about it, and the version of
    the promise it was read against
  write-findings -> check-findings [draft-findings]: the findings at a
    version, each with the responses recorded under it
  check-findings -> report-the-wave [checked-findings]: the findings
    with every figure checked against the data and the method beside
    it, and every figure that could not be computed marked as such
  report-the-wave -> record-learnings [wave-report]: the report, as
    delivered
deviations:
  check-consent -> define-sample [too-few-contactable]: the consent
    check removes most of the drawn sample, so the sample is drawn
    again or the wave buys the people it cannot reach
  carry-questions -> settle-measures [wording-must-change]: a tracked
    question has to be reworded, so what the wave measures is settled
    again and <who> agrees the change before it is made
  get-sign-offs -> carry-questions [sign-off-changes-questions]: a
    signer asks for changes to the questions, so only what they named
    is carried forward again
  watch-sample -> field-the-wave [sample-filling-slowly]: fewer have
    answered than the wave allowed for, so fielding continues in the
    markets that are short
  work-out-figures -> field-the-wave [sample-fell-short]: the wave
    closed short of what it needed, so it fields again, reports with
    the shortfall named against every finding, or is dropped
  check-findings -> write-findings [figure-does-not-follow]: a figure
    does not follow from the data and the method beside it, so the
    finding is written again
bindings:
  roster:  <who holds each role - agents claiming the abstract agents
           above, and named people for legal, finance, the brand owner
           and leadership>
  systems: the study record (write), the questions and material
           (write), the response record (write), the calculation record
           (write), the survey and interview system (trigger),
           the contact database (read), the consent record (read),
           the sending system (write), the standards store (read),
           the coverage record (write), the supplier record (write),
           the budget record (write), the report store (write),
           the meeting calendar (write)
  data:    brand guidelines <version> - the promise and the attributes
           it claims, <your consent rules> <version>, the earlier waves
           at the versions they ran under, the terms attached to every
           sample bought from outside
policy:
  every figure reported here comes from people outside the
    organization. A number from the department's own systems is never
    reported as a perception figure
  nobody is asked anything until the sample and the questions have been
    signed
  sign-off is a human gate and is never delegated to an agent
  a tracked question is reworded only when <who> agrees, and the wave
    that reworded it reports the old wording and the new one
  the competitor set changes only when <who> agrees, and a wave that
    changed it says so against every share it reports
  a movement inside the noise is reported as no movement
  every finding carries the responses it rests on, and a finding
    resting on fewer responses than the wave needed says so
  every figure carries its method, its weighting, its exclusions and
    the range around it
  responses are kept as they were given, and a response left out of a
    count is left out under a named rule
  a finding is never removed from the report because somebody asked.
    <who> decides, and the decision is recorded with the findings
measures:
  cycle time: <target> from the cycle opening to the reported findings
  comparability: <share> of tracked questions carried forward with
                 their wording unchanged
  completion: <share> of the drawn sample that fills to the count the
              wave planned for
  volume: <waves per period>
  quality gate: no movement is reported as a result without the
                statistician's verdict that it is larger than the noise
```