Certify a Seller

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: certify a seller             id: <team>/certify-a-seller   v1
from: ref/rev/certify-a-seller v1
owner: <who>                          effective: <date>
trigger: a seller is put forward for certification by <your onboarding
         process>, by a manager, or by a standard that has moved
         watch: record=<certification request>
                system=<your learning system>
                change=<a seller is put forward for a job, by an
                onboarding run or by a manager>
         or watch: record=<certification standard>
                system=<your learning system>
                change=<the standard moves to a version that reopens
                certifications>
concurrency: runs may overlap - <how many> sittings in a period, and one
             seller is certified for one job by one run at a time
goal: a signed pass or retake for every seller put forward, scored
      against a written standard at a version, with the evidence kept
      and the expiry date recorded
phases:
  take-in-request  - human: read who is put forward, for which job, at
                     what level, and the date they are needed by
                     owner: certification-check  after: trigger
                     automation: assisted
  name-matters     - human: the parts of the job a customer would
                     notice, listed and agreed with <who>
                     owner: certification-check  after: take-in-request
                     automation: <level>
  set-standard     - convenes decide-and-announce: what a pass looks
                     like for each part, written down before use
                     owner: standards-keeper
                     after: name-matters    by: <days>
                     automation: <level>
  build-assessment - runs build-by-talent: the questions, the exercises
                     and the scenarios that test the standard
                     owner: curriculum-manager   after: set-standard
                     by: <days>                  automation: <level>
  check-assessment - runs assessment: every item traced to the part of
                     the standard it claims to test
                     owner: certification-check  after: build-assessment
                     automation: supervised
  name-assessors   - human: who scores, with <who> confirming that no
                     assessor scores a seller they manage
                     owner: certification-check  after: set-standard
                     automation: <level>
  brief-assessors  - convenes briefing: the standard, the scoring sheet
                     and the worked examples, heard by all at once
                     owner: certification-check
                     after: check-assessment + name-assessors
                     automation: <level>
  schedule-sitting - human: the date, the order of the parts, and what
                     the seller may bring into the room
                     owner: onboarding-manager   after: brief-assessors
                     by: <days>                  automation: <level>
  knowledge-check  - runs assessment: product, pricing and market
                     questions, answered without notes
                     owner: certification-check  after: schedule-sitting
                     automation: <level>
  run-discovery    - runs assessment: a discovery conversation played
                     end to end against <your discovery standard>
                     owner: <your assessor role>
                     after: knowledge-check      automation: never
  run-objections   - runs assessment: the hard questions asked live,
                     drawn from <your objection set>, without warning
                     owner: <your assessor role>
                     after: run-discovery       automation: never
  systems-check    - runs assessment: the seller opens a record, works
                     it to <stage>, and builds a quote unaided
                     owner: sales-enablement-manager
                     after: run-objections       automation: <level>
  score-result     - human: each part scored against the standard, with
                     the evidence written next to the score
                     owner: certification-check
                     after: knowledge-check + run-discovery +
                     run-objections + systems-check
                     by: <days>                  automation: <level>
  decide-result    - convenes approval: <who> signs a pass, a
                     conditional pass or a retake, and says what it
                     covers
                     owner: <your sales manager role>
                     after: score-result         by: <days>
                     automation: never
  give-feedback    - convenes debrief: what passed, what did not, and
                     what the seller does before the retake
                     owner: <your sales manager role>
                     after: decide-result        by: <days>
                     automation: <level>
  record-result    - system: the result, the standard version, the
                     assessors, the evidence and the expiry date
                     owner: certification-check  after: give-feedback
                     automation: <level>
  report-predicted - runs collect-and-report: the scores set against
                     what those sellers went on to do, after <months>
                     owner: analytics            after: record-result
                     automation: assisted
run-scoped:
  sitting-log - runs collect-and-report     owner: certification-check
                every: <cadence>
                from: knowledge-check   until: score-result
  standard    - runs assessment             owner: standards-keeper
                every: <cadence>
                from: set-standard      until: run close
handoffs:
  take-in-request -> name-matters [certification-request]: who is being
    certified, for which job, and the date the certification is needed
    by
  name-matters -> set-standard [what-matters]: the parts of the job
    that matter, each with the reason a customer would notice it
  set-standard -> build-assessment [pass-standard]: the standard at a
    version, with a pass line for every part
  set-standard -> name-assessors [standard-for-assessors]: the
    standard, so the assessors are chosen for what they can actually
    judge
  build-assessment -> check-assessment [draft-assessment]: every
    question and exercise, each one naming the part of the standard it
    tests
  check-assessment -> brief-assessors [approved-assessment]: the
    assessment as approved, and any item removed with the reason it was
    removed
  name-assessors -> brief-assessors [assessor-list]: who scores which
    part, and the conflicts that were ruled out
  brief-assessors -> schedule-sitting [scoring-sheet]: the scoring
    sheet at a version, and the worked examples every assessor saw
  schedule-sitting -> knowledge-check [sitting-plan]: the date, the
    order, and what the seller was told they may bring
  knowledge-check -> run-discovery [knowledge-answers]: the answers as
    given, marked, so the exercise can probe what was shaky
  run-discovery -> run-objections [discovery-record]: the conversation
    as it ran, with what the seller did not ask
  run-objections -> systems-check [objection-record]: the objections as
    answered, with the words the seller used
  systems-check -> score-result [systems-work]: the record and the
    quote as built, and every step the seller needed help with
  score-result -> decide-result [scores-and-evidence]: a score per
    part, the evidence behind each score, and the assessor who gave it
  decide-result -> give-feedback [signed-result]: the signed result,
    what it covers, and any condition attached to a conditional pass
  give-feedback -> record-result [feedback-given]: what the seller was
    told, on what date, and what they said back
  record-result -> report-predicted [certification-record]: the result,
    the standard version and the expiry, at the record every system
    reads
deviations:
  check-assessment -> build-assessment [assessment-off-standard]: items
    have no part of the standard behind them, so the assessment is
    built again and the removals are recorded
  check-assessment -> set-standard [standard-cannot-be-scored]: a part
    of the standard is one two assessors would mark differently, so the
    standard is set again before anybody sits it
  decide-result -> score-result [assessors-disagree]: the assessors do
    not agree, so the scores go back with the evidence and are settled
    against the written standard
  decide-result -> schedule-sitting [retake-booked]: the result is a
    retake, so a sitting is scheduled again for the parts that failed
  give-feedback -> score-result [score-disputed]: the seller disputes a
    score, so the dispute goes to the scoring with the evidence rather
    than to the decision
  report-predicted -> set-standard [standard-did-not-predict]:
    certified sellers do no better than uncertified ones, so the
    standard is set again as an amendment at a new version
bindings:
  roster:  <who holds each role - agents claiming the abstract agents
           above, and named people for the sales manager, the assessors
           and the signer>
  systems: the learning system (write), the enablement library (read),
           the CRM (write, on a practice record),
           the quoting system (write, on a practice record),
           the certification record (write), analytics (read)
  data:    <your certification standard> <version>, <your discovery
           standard>, <your objection set>, <your price book> <version>,
           the assessment at a version, the scoring sheet
policy:
  the standard is written down before the assessment is built, and an
    assessment that tests something the standard does not name is
    changed rather than scored
  no assessor scores a seller they manage or hired
  a pass is signed by a person and is never granted by an agent
  a conditional pass names the condition and the date it expires. An
    expired condition is a retake, not a pass
  every score keeps the evidence it was given on, so a disputed score
    can be reread rather than re-argued
  a certification names the standard version it was scored against. When
    the standard changes, <who> decides which certifications reopen
  a seller who fails retakes only the parts that failed, after <days>
measures:
  cycle time: <days> from the seller being put forward to a signed
             result
  coverage: <target> share of sellers certified before their first
            customer conversation
  volume: <sittings per period>
  quality gate: no customer conversation without a signed pass, and
                <sample size> of scores reread each period against the
                standard
```

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: certify a seller             id: <team>/certify-a-seller   v1
from: ref/rev/certify-a-seller v1
owner: <who>                          effective: <date>
trigger: a seller is put forward for certification by <your onboarding
         process>, by a manager, or by a standard that has moved
         watch: record=<certification request>
                system=<your learning system>
                change=<a seller is put forward for a job, by an
                onboarding run or by a manager>
         or watch: record=<certification standard>
                system=<your learning system>
                change=<the standard moves to a version that reopens
                certifications>
concurrency: runs may overlap - <how many> sittings in a period, and one
             seller is certified for one job by one run at a time
goal: a signed pass or retake for every seller put forward, scored
      against a written standard at a version, with the evidence kept
      and the expiry date recorded
phases:
  take-in-request  - human: read who is put forward, for which job, at
                     what level, and the date they are needed by
                     owner: certification-check  after: trigger
                     automation: assisted
  name-matters     - human: the parts of the job a customer would
                     notice, listed and agreed with <who>
                     owner: certification-check  after: take-in-request
                     automation: <level>
  set-standard     - convenes decide-and-announce: what a pass looks
                     like for each part, written down before use
                     owner: standards-keeper
                     after: name-matters    by: <days>
                     automation: <level>
  build-assessment - runs build-by-talent: the questions, the exercises
                     and the scenarios that test the standard
                     owner: curriculum-manager   after: set-standard
                     by: <days>                  automation: <level>
  check-assessment - runs assessment: every item traced to the part of
                     the standard it claims to test
                     owner: certification-check  after: build-assessment
                     automation: supervised
  name-assessors   - human: who scores, with <who> confirming that no
                     assessor scores a seller they manage
                     owner: certification-check  after: set-standard
                     automation: <level>
  brief-assessors  - convenes briefing: the standard, the scoring sheet
                     and the worked examples, heard by all at once
                     owner: certification-check
                     after: check-assessment + name-assessors
                     automation: <level>
  schedule-sitting - human: the date, the order of the parts, and what
                     the seller may bring into the room
                     owner: onboarding-manager   after: brief-assessors
                     by: <days>                  automation: <level>
  knowledge-check  - runs assessment: product, pricing and market
                     questions, answered without notes
                     owner: certification-check  after: schedule-sitting
                     automation: <level>
  run-discovery    - runs assessment: a discovery conversation played
                     end to end against <your discovery standard>
                     owner: <your assessor role>
                     after: knowledge-check      automation: never
  run-objections   - runs assessment: the hard questions asked live,
                     drawn from <your objection set>, without warning
                     owner: <your assessor role>
                     after: run-discovery       automation: never
  systems-check    - runs assessment: the seller opens a record, works
                     it to <stage>, and builds a quote unaided
                     owner: sales-enablement-manager
                     after: run-objections       automation: <level>
  score-result     - human: each part scored against the standard, with
                     the evidence written next to the score
                     owner: certification-check
                     after: knowledge-check + run-discovery +
                     run-objections + systems-check
                     by: <days>                  automation: <level>
  decide-result    - convenes approval: <who> signs a pass, a
                     conditional pass or a retake, and says what it
                     covers
                     owner: <your sales manager role>
                     after: score-result         by: <days>
                     automation: never
  give-feedback    - convenes debrief: what passed, what did not, and
                     what the seller does before the retake
                     owner: <your sales manager role>
                     after: decide-result        by: <days>
                     automation: <level>
  record-result    - system: the result, the standard version, the
                     assessors, the evidence and the expiry date
                     owner: certification-check  after: give-feedback
                     automation: <level>
  report-predicted - runs collect-and-report: the scores set against
                     what those sellers went on to do, after <months>
                     owner: analytics            after: record-result
                     automation: assisted
run-scoped:
  sitting-log - runs collect-and-report     owner: certification-check
                every: <cadence>
                from: knowledge-check   until: score-result
  standard    - runs assessment             owner: standards-keeper
                every: <cadence>
                from: set-standard      until: run close
handoffs:
  take-in-request -> name-matters [certification-request]: who is being
    certified, for which job, and the date the certification is needed
    by
  name-matters -> set-standard [what-matters]: the parts of the job
    that matter, each with the reason a customer would notice it
  set-standard -> build-assessment [pass-standard]: the standard at a
    version, with a pass line for every part
  set-standard -> name-assessors [standard-for-assessors]: the
    standard, so the assessors are chosen for what they can actually
    judge
  build-assessment -> check-assessment [draft-assessment]: every
    question and exercise, each one naming the part of the standard it
    tests
  check-assessment -> brief-assessors [approved-assessment]: the
    assessment as approved, and any item removed with the reason it was
    removed
  name-assessors -> brief-assessors [assessor-list]: who scores which
    part, and the conflicts that were ruled out
  brief-assessors -> schedule-sitting [scoring-sheet]: the scoring
    sheet at a version, and the worked examples every assessor saw
  schedule-sitting -> knowledge-check [sitting-plan]: the date, the
    order, and what the seller was told they may bring
  knowledge-check -> run-discovery [knowledge-answers]: the answers as
    given, marked, so the exercise can probe what was shaky
  run-discovery -> run-objections [discovery-record]: the conversation
    as it ran, with what the seller did not ask
  run-objections -> systems-check [objection-record]: the objections as
    answered, with the words the seller used
  systems-check -> score-result [systems-work]: the record and the
    quote as built, and every step the seller needed help with
  score-result -> decide-result [scores-and-evidence]: a score per
    part, the evidence behind each score, and the assessor who gave it
  decide-result -> give-feedback [signed-result]: the signed result,
    what it covers, and any condition attached to a conditional pass
  give-feedback -> record-result [feedback-given]: what the seller was
    told, on what date, and what they said back
  record-result -> report-predicted [certification-record]: the result,
    the standard version and the expiry, at the record every system
    reads
deviations:
  check-assessment -> build-assessment [assessment-off-standard]: items
    have no part of the standard behind them, so the assessment is
    built again and the removals are recorded
  check-assessment -> set-standard [standard-cannot-be-scored]: a part
    of the standard is one two assessors would mark differently, so the
    standard is set again before anybody sits it
  decide-result -> score-result [assessors-disagree]: the assessors do
    not agree, so the scores go back with the evidence and are settled
    against the written standard
  decide-result -> schedule-sitting [retake-booked]: the result is a
    retake, so a sitting is scheduled again for the parts that failed
  give-feedback -> score-result [score-disputed]: the seller disputes a
    score, so the dispute goes to the scoring with the evidence rather
    than to the decision
  report-predicted -> set-standard [standard-did-not-predict]:
    certified sellers do no better than uncertified ones, so the
    standard is set again as an amendment at a new version
bindings:
  roster:  <who holds each role - agents claiming the abstract agents
           above, and named people for the sales manager, the assessors
           and the signer>
  systems: the learning system (write), the enablement library (read),
           the CRM (write, on a practice record),
           the quoting system (write, on a practice record),
           the certification record (write), analytics (read)
  data:    <your certification standard> <version>, <your discovery
           standard>, <your objection set>, <your price book> <version>,
           the assessment at a version, the scoring sheet
policy:
  the standard is written down before the assessment is built, and an
    assessment that tests something the standard does not name is
    changed rather than scored
  no assessor scores a seller they manage or hired
  a pass is signed by a person and is never granted by an agent
  a conditional pass names the condition and the date it expires. An
    expired condition is a retake, not a pass
  every score keeps the evidence it was given on, so a disputed score
    can be reread rather than re-argued
  a certification names the standard version it was scored against. When
    the standard changes, <who> decides which certifications reopen
  a seller who fails retakes only the parts that failed, after <days>
measures:
  cycle time: <days> from the seller being put forward to a signed
             result
  coverage: <target> share of sellers certified before their first
            customer conversation
  volume: <sittings per period>
  quality gate: no customer conversation without a signed pass, and
                <sample size> of scores reread each period against the
                standard
```

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: certify a seller             id: <team>/certify-a-seller   v1
from: ref/rev/certify-a-seller v1
owner: <who>                          effective: <date>
trigger: a seller is put forward for certification by <your onboarding
         process>, by a manager, or by a standard that has moved
         watch: record=<certification request>
                system=<your learning system>
                change=<a seller is put forward for a job, by an
                onboarding run or by a manager>
         or watch: record=<certification standard>
                system=<your learning system>
                change=<the standard moves to a version that reopens
                certifications>
concurrency: runs may overlap - <how many> sittings in a period, and one
             seller is certified for one job by one run at a time
goal: a signed pass or retake for every seller put forward, scored
      against a written standard at a version, with the evidence kept
      and the expiry date recorded
phases:
  take-in-request  - human: read who is put forward, for which job, at
                     what level, and the date they are needed by
                     owner: certification-check  after: trigger
                     automation: assisted
  name-matters     - human: the parts of the job a customer would
                     notice, listed and agreed with <who>
                     owner: certification-check  after: take-in-request
                     automation: <level>
  set-standard     - convenes decide-and-announce: what a pass looks
                     like for each part, written down before use
                     owner: standards-keeper
                     after: name-matters    by: <days>
                     automation: <level>
  build-assessment - runs build-by-talent: the questions, the exercises
                     and the scenarios that test the standard
                     owner: curriculum-manager   after: set-standard
                     by: <days>                  automation: <level>
  check-assessment - runs assessment: every item traced to the part of
                     the standard it claims to test
                     owner: certification-check  after: build-assessment
                     automation: supervised
  name-assessors   - human: who scores, with <who> confirming that no
                     assessor scores a seller they manage
                     owner: certification-check  after: set-standard
                     automation: <level>
  brief-assessors  - convenes briefing: the standard, the scoring sheet
                     and the worked examples, heard by all at once
                     owner: certification-check
                     after: check-assessment + name-assessors
                     automation: <level>
  schedule-sitting - human: the date, the order of the parts, and what
                     the seller may bring into the room
                     owner: onboarding-manager   after: brief-assessors
                     by: <days>                  automation: <level>
  knowledge-check  - runs assessment: product, pricing and market
                     questions, answered without notes
                     owner: certification-check  after: schedule-sitting
                     automation: <level>
  run-discovery    - runs assessment: a discovery conversation played
                     end to end against <your discovery standard>
                     owner: <your assessor role>
                     after: knowledge-check      automation: never
  run-objections   - runs assessment: the hard questions asked live,
                     drawn from <your objection set>, without warning
                     owner: <your assessor role>
                     after: run-discovery       automation: never
  systems-check    - runs assessment: the seller opens a record, works
                     it to <stage>, and builds a quote unaided
                     owner: sales-enablement-manager
                     after: run-objections       automation: <level>
  score-result     - human: each part scored against the standard, with
                     the evidence written next to the score
                     owner: certification-check
                     after: knowledge-check + run-discovery +
                     run-objections + systems-check
                     by: <days>                  automation: <level>
  decide-result    - convenes approval: <who> signs a pass, a
                     conditional pass or a retake, and says what it
                     covers
                     owner: <your sales manager role>
                     after: score-result         by: <days>
                     automation: never
  give-feedback    - convenes debrief: what passed, what did not, and
                     what the seller does before the retake
                     owner: <your sales manager role>
                     after: decide-result        by: <days>
                     automation: <level>
  record-result    - system: the result, the standard version, the
                     assessors, the evidence and the expiry date
                     owner: certification-check  after: give-feedback
                     automation: <level>
  report-predicted - runs collect-and-report: the scores set against
                     what those sellers went on to do, after <months>
                     owner: analytics            after: record-result
                     automation: assisted
run-scoped:
  sitting-log - runs collect-and-report     owner: certification-check
                every: <cadence>
                from: knowledge-check   until: score-result
  standard    - runs assessment             owner: standards-keeper
                every: <cadence>
                from: set-standard      until: run close
handoffs:
  take-in-request -> name-matters [certification-request]: who is being
    certified, for which job, and the date the certification is needed
    by
  name-matters -> set-standard [what-matters]: the parts of the job
    that matter, each with the reason a customer would notice it
  set-standard -> build-assessment [pass-standard]: the standard at a
    version, with a pass line for every part
  set-standard -> name-assessors [standard-for-assessors]: the
    standard, so the assessors are chosen for what they can actually
    judge
  build-assessment -> check-assessment [draft-assessment]: every
    question and exercise, each one naming the part of the standard it
    tests
  check-assessment -> brief-assessors [approved-assessment]: the
    assessment as approved, and any item removed with the reason it was
    removed
  name-assessors -> brief-assessors [assessor-list]: who scores which
    part, and the conflicts that were ruled out
  brief-assessors -> schedule-sitting [scoring-sheet]: the scoring
    sheet at a version, and the worked examples every assessor saw
  schedule-sitting -> knowledge-check [sitting-plan]: the date, the
    order, and what the seller was told they may bring
  knowledge-check -> run-discovery [knowledge-answers]: the answers as
    given, marked, so the exercise can probe what was shaky
  run-discovery -> run-objections [discovery-record]: the conversation
    as it ran, with what the seller did not ask
  run-objections -> systems-check [objection-record]: the objections as
    answered, with the words the seller used
  systems-check -> score-result [systems-work]: the record and the
    quote as built, and every step the seller needed help with
  score-result -> decide-result [scores-and-evidence]: a score per
    part, the evidence behind each score, and the assessor who gave it
  decide-result -> give-feedback [signed-result]: the signed result,
    what it covers, and any condition attached to a conditional pass
  give-feedback -> record-result [feedback-given]: what the seller was
    told, on what date, and what they said back
  record-result -> report-predicted [certification-record]: the result,
    the standard version and the expiry, at the record every system
    reads
deviations:
  check-assessment -> build-assessment [assessment-off-standard]: items
    have no part of the standard behind them, so the assessment is
    built again and the removals are recorded
  check-assessment -> set-standard [standard-cannot-be-scored]: a part
    of the standard is one two assessors would mark differently, so the
    standard is set again before anybody sits it
  decide-result -> score-result [assessors-disagree]: the assessors do
    not agree, so the scores go back with the evidence and are settled
    against the written standard
  decide-result -> schedule-sitting [retake-booked]: the result is a
    retake, so a sitting is scheduled again for the parts that failed
  give-feedback -> score-result [score-disputed]: the seller disputes a
    score, so the dispute goes to the scoring with the evidence rather
    than to the decision
  report-predicted -> set-standard [standard-did-not-predict]:
    certified sellers do no better than uncertified ones, so the
    standard is set again as an amendment at a new version
bindings:
  roster:  <who holds each role - agents claiming the abstract agents
           above, and named people for the sales manager, the assessors
           and the signer>
  systems: the learning system (write), the enablement library (read),
           the CRM (write, on a practice record),
           the quoting system (write, on a practice record),
           the certification record (write), analytics (read)
  data:    <your certification standard> <version>, <your discovery
           standard>, <your objection set>, <your price book> <version>,
           the assessment at a version, the scoring sheet
policy:
  the standard is written down before the assessment is built, and an
    assessment that tests something the standard does not name is
    changed rather than scored
  no assessor scores a seller they manage or hired
  a pass is signed by a person and is never granted by an agent
  a conditional pass names the condition and the date it expires. An
    expired condition is a retake, not a pass
  every score keeps the evidence it was given on, so a disputed score
    can be reread rather than re-argued
  a certification names the standard version it was scored against. When
    the standard changes, <who> decides which certifications reopen
  a seller who fails retakes only the parts that failed, after <days>
measures:
  cycle time: <days> from the seller being put forward to a signed
             result
  coverage: <target> share of sellers certified before their first
            customer conversation
  volume: <sittings per period>
  quality gate: no customer conversation without a signed pass, and
                <sample size> of scores reread each period against the
                standard
```

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: certify a seller             id: <team>/certify-a-seller   v1
from: ref/rev/certify-a-seller v1
owner: <who>                          effective: <date>
trigger: a seller is put forward for certification by <your onboarding
         process>, by a manager, or by a standard that has moved
         watch: record=<certification request>
                system=<your learning system>
                change=<a seller is put forward for a job, by an
                onboarding run or by a manager>
         or watch: record=<certification standard>
                system=<your learning system>
                change=<the standard moves to a version that reopens
                certifications>
concurrency: runs may overlap - <how many> sittings in a period, and one
             seller is certified for one job by one run at a time
goal: a signed pass or retake for every seller put forward, scored
      against a written standard at a version, with the evidence kept
      and the expiry date recorded
phases:
  take-in-request  - human: read who is put forward, for which job, at
                     what level, and the date they are needed by
                     owner: certification-check  after: trigger
                     automation: assisted
  name-matters     - human: the parts of the job a customer would
                     notice, listed and agreed with <who>
                     owner: certification-check  after: take-in-request
                     automation: <level>
  set-standard     - convenes decide-and-announce: what a pass looks
                     like for each part, written down before use
                     owner: standards-keeper
                     after: name-matters    by: <days>
                     automation: <level>
  build-assessment - runs build-by-talent: the questions, the exercises
                     and the scenarios that test the standard
                     owner: curriculum-manager   after: set-standard
                     by: <days>                  automation: <level>
  check-assessment - runs assessment: every item traced to the part of
                     the standard it claims to test
                     owner: certification-check  after: build-assessment
                     automation: supervised
  name-assessors   - human: who scores, with <who> confirming that no
                     assessor scores a seller they manage
                     owner: certification-check  after: set-standard
                     automation: <level>
  brief-assessors  - convenes briefing: the standard, the scoring sheet
                     and the worked examples, heard by all at once
                     owner: certification-check
                     after: check-assessment + name-assessors
                     automation: <level>
  schedule-sitting - human: the date, the order of the parts, and what
                     the seller may bring into the room
                     owner: onboarding-manager   after: brief-assessors
                     by: <days>                  automation: <level>
  knowledge-check  - runs assessment: product, pricing and market
                     questions, answered without notes
                     owner: certification-check  after: schedule-sitting
                     automation: <level>
  run-discovery    - runs assessment: a discovery conversation played
                     end to end against <your discovery standard>
                     owner: <your assessor role>
                     after: knowledge-check      automation: never
  run-objections   - runs assessment: the hard questions asked live,
                     drawn from <your objection set>, without warning
                     owner: <your assessor role>
                     after: run-discovery       automation: never
  systems-check    - runs assessment: the seller opens a record, works
                     it to <stage>, and builds a quote unaided
                     owner: sales-enablement-manager
                     after: run-objections       automation: <level>
  score-result     - human: each part scored against the standard, with
                     the evidence written next to the score
                     owner: certification-check
                     after: knowledge-check + run-discovery +
                     run-objections + systems-check
                     by: <days>                  automation: <level>
  decide-result    - convenes approval: <who> signs a pass, a
                     conditional pass or a retake, and says what it
                     covers
                     owner: <your sales manager role>
                     after: score-result         by: <days>
                     automation: never
  give-feedback    - convenes debrief: what passed, what did not, and
                     what the seller does before the retake
                     owner: <your sales manager role>
                     after: decide-result        by: <days>
                     automation: <level>
  record-result    - system: the result, the standard version, the
                     assessors, the evidence and the expiry date
                     owner: certification-check  after: give-feedback
                     automation: <level>
  report-predicted - runs collect-and-report: the scores set against
                     what those sellers went on to do, after <months>
                     owner: analytics            after: record-result
                     automation: assisted
run-scoped:
  sitting-log - runs collect-and-report     owner: certification-check
                every: <cadence>
                from: knowledge-check   until: score-result
  standard    - runs assessment             owner: standards-keeper
                every: <cadence>
                from: set-standard      until: run close
handoffs:
  take-in-request -> name-matters [certification-request]: who is being
    certified, for which job, and the date the certification is needed
    by
  name-matters -> set-standard [what-matters]: the parts of the job
    that matter, each with the reason a customer would notice it
  set-standard -> build-assessment [pass-standard]: the standard at a
    version, with a pass line for every part
  set-standard -> name-assessors [standard-for-assessors]: the
    standard, so the assessors are chosen for what they can actually
    judge
  build-assessment -> check-assessment [draft-assessment]: every
    question and exercise, each one naming the part of the standard it
    tests
  check-assessment -> brief-assessors [approved-assessment]: the
    assessment as approved, and any item removed with the reason it was
    removed
  name-assessors -> brief-assessors [assessor-list]: who scores which
    part, and the conflicts that were ruled out
  brief-assessors -> schedule-sitting [scoring-sheet]: the scoring
    sheet at a version, and the worked examples every assessor saw
  schedule-sitting -> knowledge-check [sitting-plan]: the date, the
    order, and what the seller was told they may bring
  knowledge-check -> run-discovery [knowledge-answers]: the answers as
    given, marked, so the exercise can probe what was shaky
  run-discovery -> run-objections [discovery-record]: the conversation
    as it ran, with what the seller did not ask
  run-objections -> systems-check [objection-record]: the objections as
    answered, with the words the seller used
  systems-check -> score-result [systems-work]: the record and the
    quote as built, and every step the seller needed help with
  score-result -> decide-result [scores-and-evidence]: a score per
    part, the evidence behind each score, and the assessor who gave it
  decide-result -> give-feedback [signed-result]: the signed result,
    what it covers, and any condition attached to a conditional pass
  give-feedback -> record-result [feedback-given]: what the seller was
    told, on what date, and what they said back
  record-result -> report-predicted [certification-record]: the result,
    the standard version and the expiry, at the record every system
    reads
deviations:
  check-assessment -> build-assessment [assessment-off-standard]: items
    have no part of the standard behind them, so the assessment is
    built again and the removals are recorded
  check-assessment -> set-standard [standard-cannot-be-scored]: a part
    of the standard is one two assessors would mark differently, so the
    standard is set again before anybody sits it
  decide-result -> score-result [assessors-disagree]: the assessors do
    not agree, so the scores go back with the evidence and are settled
    against the written standard
  decide-result -> schedule-sitting [retake-booked]: the result is a
    retake, so a sitting is scheduled again for the parts that failed
  give-feedback -> score-result [score-disputed]: the seller disputes a
    score, so the dispute goes to the scoring with the evidence rather
    than to the decision
  report-predicted -> set-standard [standard-did-not-predict]:
    certified sellers do no better than uncertified ones, so the
    standard is set again as an amendment at a new version
bindings:
  roster:  <who holds each role - agents claiming the abstract agents
           above, and named people for the sales manager, the assessors
           and the signer>
  systems: the learning system (write), the enablement library (read),
           the CRM (write, on a practice record),
           the quoting system (write, on a practice record),
           the certification record (write), analytics (read)
  data:    <your certification standard> <version>, <your discovery
           standard>, <your objection set>, <your price book> <version>,
           the assessment at a version, the scoring sheet
policy:
  the standard is written down before the assessment is built, and an
    assessment that tests something the standard does not name is
    changed rather than scored
  no assessor scores a seller they manage or hired
  a pass is signed by a person and is never granted by an agent
  a conditional pass names the condition and the date it expires. An
    expired condition is a retake, not a pass
  every score keeps the evidence it was given on, so a disputed score
    can be reread rather than re-argued
  a certification names the standard version it was scored against. When
    the standard changes, <who> decides which certifications reopen
  a seller who fails retakes only the parts that failed, after <days>
measures:
  cycle time: <days> from the seller being put forward to a signed
             result
  coverage: <target> share of sellers certified before their first
            customer conversation
  volume: <sittings per period>
  quality gate: no customer conversation without a signed pass, and
                <sample size> of scores reread each period against the
                standard
```