Catalog / Business processes / Partners / Performance-to-Tier / End a Partner Relationship
reference process · partners · 17 activities · 12 on the rosterEnd a Partner Relationship
A partner has stopped performing, or one side has given notice. This run ends the relationship without stranding the customers the partner holds. It reads the exit terms in the signed agreement first, takes a decision from a person, and only then lists what the partner is carrying: the customers, the open deals, the deliveries in progress and the money owed in both directions. The notice is served the way the agreement requires, the handover is agreed with the partner where it can be, and every customer hears who serves them next before their support changes. The run closes when nothing is left open and nobody is left holding a contract with nobody behind it.
The walk
The document
One run
Adoption
The activities
What happens in a run
17 activities from a partner has stopped performing, or either side gives notice to the partner is out and no customer is stranded, 4 of them gates a person has to sign. Drag the diagram to move along it.
End a Partner Relationship a partner has stopped performing, or either side gives notice → the partner is out and no customer is stranded
the position is not clear enough to decide the notice does not meet the terms the partner will not take part a customer will not be moved work is still running on that access something is still open a partner has stopped performing, or either side gives notice 1 Take in the Reason to End… what happened, and who is asking for it 2 Read the Exit Terms notice, survival, and what may not be cut off 3 Get the Legal Position what the agreement allows, and what it costs a person signs · never an agent 4 Decide Whether to End It wind down, or one more attempt to repair a person signs · never an agent 5 List the Customers the Pa… every account, contract and renewal date 6 List the Work in Flight open deals, registrations, deliveries, claims 7 Settle What the Money Says commissions, funds, rebates and anything unpaid 8 Write the Wind-Down Plan the dates, the owners, and what stops when 9 Serve the Notice told the way the agreement requires, on a date a person signs · never an agent 10 Agree the Handover with t… who tells each customer, and in what order 11 Tell the Customers each customer hears who serves them next a person signs · never an agent 12 Move the Customers contracts, support and renewals reassigned 13 Finish or Transfer the Wo… nothing open is left with nobody holding it 14 Close Off the Access portal, systems, price lists, leads and badge 15 Pay What Is Owed and Reco… the last settlement, in both directions 16 Confirm the Exit Is Compl… a check that nothing is still open anywhere 17 Record What the Ending Ta… what would have been seen earlier the partner is out and no customer is stranded The roster this process needs
Hover a name to see the activities it holds. A dashed one is a person, and stays one.
The document
The document, with the blanks marked
Everything in amber is yours to fill in: who owns it, when it takes effect, which platforms, which numbers, and who holds each activity. Everything else is the process, and it is the same wherever it is run.
PROCESS: end a partner relationship id: <team> /end-a-partner-relationship v1
from: ref/prt/end-a-partner-relationship v1
owner: <who> effective: <date>
trigger: <your partner review process> reports a partner still behind
after <how many> rounds, a term of the agreement is breached,
or either side gives notice
watch: record=<partner review>
system=<your partner review process>
change=<a review reports a partner still behind after
the set number of rounds>
or watch: record=<the agreement>
system=<where breaches are recorded>
change=<a term of the agreement is breached>
or watch: record=<notice to end>
system=<where notices are served>
change=<either side gives notice>
concurrency: one run per partner, and a partner in this run is out of
every review and tiering round while it is open
goal: the relationship ended on the terms the agreement sets, with
every customer the partner held moved to a named owner before
their support changes, every open deal and delivery finished or
transferred, the money settled both ways, and no access left open
phases:
take-in-reason - human: what happened, who is asking to end it, and
what has already been tried
owner: partner-manager after: trigger
automation: <level>
check-exit-terms - runs collect-and-report: the notice period, the
termination grounds, the clauses that survive, and
what the agreement says may not be cut off
owner: partner-manager after: take-in-reason
by: <days> automation: <level>
legal-read - human: whether the grounds hold, what ending it
costs, and what the company still owes afterwards
owner: <your legal role> after: check-exit-terms
by: <days> automation: never
decide-to-end - convenes decide-and-announce: wind down, or one
more attempt to repair on stated terms and a date,
naming who decided it and on what
owner: <your channel leadership role>
after: legal-read
automation: never
list-customers - runs collect-and-report: every customer the partner
holds, with the contract, the renewal date, the
support arrangement and who at the customer to call
owner: partner-monitor after: decide-to-end
by: <days> automation: <level>
list-in-flight - runs collect-and-report: open deals, registrations
still live, deliveries part done, support cases,
and claims against funds not yet paid
owner: partner-monitor after: decide-to-end
by: <days> automation: <level>
settle-money - runs allocate-and-reconcile: commissions earned,
funds committed, rebates due, and anything the
partner owes back, each line with its evidence
owner: margin-keeper after: decide-to-end
by: <days> automation: <level>
write-plan - human: the dates, the owner of each step, what
stops when, and the last day the partner may sell
owner: partner-manager
after: list-customers + list-in-flight + settle-money
by: <days> automation: <level>
tell-partner - human: the notice served in the form and to the
address the agreement names, on a recorded date,
with the wind-down plan attached
owner: partner-manager after: write-plan
automation: never
agree-handover - convenes briefing: who tells each customer, in what
order, with what said, and what the partner keeps
doing until each customer has moved
owner: partner-manager after: tell-partner
by: <days> automation: <level>
tell-customers - human: each customer hears the change, who serves
them next, from what date, and that their contract
and support continue
owner: <your customer success role>
after: agree-handover
by: <days> automation: never
move-customers - human: contracts, support routing, renewals and
named contacts reassigned to <who> , customer by
customer, with a date against each
owner: partner-manager after: tell-customers
by: <days> automation: <level>
finish-in-flight - human: every open deal, registration, delivery and
claim closed, transferred or paid out under <your
in-flight rules>
owner: partner-manager after: agree-handover
by: <days> automation: <level>
close-access - human: the portal, the systems, the price lists,
the lead flow, the tier and its margins, and the
right to use the name, all ended on a stated date
owner: partner-manager
after: move-customers + finish-in-flight
by: <days> automation: <level>
pay-and-recover - runs allocate-and-reconcile: the final settlement
paid and the amounts recovered, against the lines
the money step agreed
owner: margin-keeper after: close-access
by: <days> automation: <level>
confirm-exit - runs assessment: nothing open in any system, no
customer without an owner, no access still live,
and every surviving obligation written down
owner: partner-monitor after: pay-and-recover
by: <days> automation: <level>
record-learnings - convenes debrief: what the signals were, when they
first showed, and what the program changes so the
next one is seen sooner
owner: partner-manager after: confirm-exit
automation: <level>
run-scoped:
customers - runs roll-call owner: partner-monitor
every: <cadence>
from: tell-customers until: confirm-exit
money - runs allocate-and-reconcile owner: margin-keeper
from: settle-money until: run close
handoffs:
take-in-reason -> check-exit-terms [ending-reason]: what happened,
dated, with the evidence behind it and what was already tried
check-exit-terms -> legal-read [exit-clauses]: the clauses that
apply, quoted from the agreement at the version that was signed
legal-read -> decide-to-end [legal-position]: whether the grounds
hold, what it costs, and what survives the ending
decide-to-end -> list-customers [ending-decision]: the decision and
the date it applies from, so the customer list is taken as of that
date
decide-to-end -> list-in-flight [last-sell-date]: the same decision,
so the last day the partner may sell is known before the lists are
drawn
decide-to-end -> settle-money [money-cut-off]: the same decision, so
the money is counted to a date rather than to an argument
list-customers -> write-plan [customer-list]: every customer, with
the contract, the renewal date and who at the customer has to be
called
list-in-flight -> write-plan [open-work]: everything still open, with
what it is worth and who is waiting on it
settle-money -> write-plan [money-position]: what is owed each way,
with the evidence for every line and every disputed line marked as
disputed
write-plan -> tell-partner [wind-down-plan]: the plan, the dates, and
the last day the partner may sell
tell-partner -> agree-handover [served-notice]: the notice as served,
with the date and the form it was served in
agree-handover -> tell-customers [handover-order]: who tells each
customer, in what order, and what is said, agreed by both sides
where possible
agree-handover -> finish-in-flight [in-flight-split]: what the
partner finishes, what somebody else takes over, and by when
tell-customers -> move-customers [customers-told]: the customers who
have been told, the date, and anything they asked for
move-customers -> close-access [reassigned-customers]: the customers
now held by a named owner, so no access is closed while somebody
still depends on it
finish-in-flight -> close-access [closed-work]: the work closed,
transferred or paid, and anything left open with the reason
close-access -> pay-and-recover [access-ended]: the access ended and
the dates, so the final settlement counts to a real last day
pay-and-recover -> confirm-exit [final-settlement]: what was paid and
recovered, and anything still in dispute
confirm-exit -> record-learnings [exit-confirmation]: the exit as
confirmed, with every item that could not be closed named
deviations:
decide-to-end -> legal-read [position-unclear]: the legal position is
not clear enough to decide on, so what would have to be true is
read out of the agreement again
tell-partner -> check-exit-terms [notice-does-not-count]: the form,
the address or the timing did not match what the agreement
requires, so the terms are read again and the notice served again
agree-handover -> write-plan [partner-will-not-take-part]: the
partner will not agree the handover, so the plan is rewritten for a
one-sided wind-down
tell-customers -> agree-handover [customer-will-not-move]: a customer
will not be moved, so what they asked for goes back to the handover
rather than the customer being moved by force
close-access -> finish-in-flight [access-still-needed]: work is still
running on an access that was closed, so the access is restored for
that work and the work is finished first
confirm-exit -> close-access [something-still-open]: the check finds
something still open, so the access, the customers and the work are
closed off again
bindings:
roster: <who holds each role - agents claiming the abstract agents
above, the partner lead who worked the relationship, the
legal reviewer who reads the agreement, the finance partner
who settles the money, the customer success lead who takes
the customers, and the channel leader who decides>
systems: the partner record (write), the agreement record (read),
the CRM (write), <your deal registration system> (write),
<your finance system> (write), the partner portal (write),
<your price list system> (write),
<your support ticketing system> (write),
the notification channel (write), <your identity system>
(write)
data: the signed agreement at its current version, <your notice
periods>, <your in-flight rules> , the customer list as of
<the decision date> , <your exit checklist>
policy:
the agreement is read before anything is decided, and the run follows
the notice period it sets even when the reason is serious
ending the relationship is decided by a person and is never delegated
to an agent
no customer loses support, a renewal date or a named contact because
the partner is leaving, and no access is closed while a customer
still depends on it
every customer hears the change from <who> before it reaches them,
and hears who serves them next in the same message
a partner is paid what they earned up to the last day, whatever the
reason for ending it
the last day the partner may sell is stated once, in writing, and is
the same date in the plan, the notice and the systems
every obligation that survives the ending is written down and given
an owner inside the company
the run does not close while any customer, deal, delivery or access
is still open, and anything that cannot be closed is named in the
confirmation rather than left out of it
measures:
cycle time: <target> from the decision to the confirmed exit
coverage: <target> share of the partner's customers moved to a named
owner before their support changed
volume: <endings per period> , read as a share of partners under
agreement
quality gate: <sample size> of exits checked each <period> for closed
access, settled money and no customer left unowned
Copy
Take it somewhere
Use this process in LangGraph
close
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.
copy the prompt
345 lines · the document is inside it, so nothing else is needed
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: end a partner relationship id: <team>/end-a-partner-relationship v1
from: ref/prt/end-a-partner-relationship v1
owner: <who> effective: <date>
trigger: <your partner review process> reports a partner still behind
after <how many> rounds, a term of the agreement is breached,
or either side gives notice
watch: record=<partner review>
system=<your partner review process>
change=<a review reports a partner still behind after
the set number of rounds>
or watch: record=<the agreement>
system=<where breaches are recorded>
change=<a term of the agreement is breached>
or watch: record=<notice to end>
system=<where notices are served>
change=<either side gives notice>
concurrency: one run per partner, and a partner in this run is out of
every review and tiering round while it is open
goal: the relationship ended on the terms the agreement sets, with
every customer the partner held moved to a named owner before
their support changes, every open deal and delivery finished or
transferred, the money settled both ways, and no access left open
phases:
take-in-reason - human: what happened, who is asking to end it, and
what has already been tried
owner: partner-manager after: trigger
automation: <level>
check-exit-terms - runs collect-and-report: the notice period, the
termination grounds, the clauses that survive, and
what the agreement says may not be cut off
owner: partner-manager after: take-in-reason
by: <days> automation: <level>
legal-read - human: whether the grounds hold, what ending it
costs, and what the company still owes afterwards
owner: <your legal role> after: check-exit-terms
by: <days> automation: never
decide-to-end - convenes decide-and-announce: wind down, or one
more attempt to repair on stated terms and a date,
naming who decided it and on what
owner: <your channel leadership role>
after: legal-read
automation: never
list-customers - runs collect-and-report: every customer the partner
holds, with the contract, the renewal date, the
support arrangement and who at the customer to call
owner: partner-monitor after: decide-to-end
by: <days> automation: <level>
list-in-flight - runs collect-and-report: open deals, registrations
still live, deliveries part done, support cases,
and claims against funds not yet paid
owner: partner-monitor after: decide-to-end
by: <days> automation: <level>
settle-money - runs allocate-and-reconcile: commissions earned,
funds committed, rebates due, and anything the
partner owes back, each line with its evidence
owner: margin-keeper after: decide-to-end
by: <days> automation: <level>
write-plan - human: the dates, the owner of each step, what
stops when, and the last day the partner may sell
owner: partner-manager
after: list-customers + list-in-flight + settle-money
by: <days> automation: <level>
tell-partner - human: the notice served in the form and to the
address the agreement names, on a recorded date,
with the wind-down plan attached
owner: partner-manager after: write-plan
automation: never
agree-handover - convenes briefing: who tells each customer, in what
order, with what said, and what the partner keeps
doing until each customer has moved
owner: partner-manager after: tell-partner
by: <days> automation: <level>
tell-customers - human: each customer hears the change, who serves
them next, from what date, and that their contract
and support continue
owner: <your customer success role>
after: agree-handover
by: <days> automation: never
move-customers - human: contracts, support routing, renewals and
named contacts reassigned to <who>, customer by
customer, with a date against each
owner: partner-manager after: tell-customers
by: <days> automation: <level>
finish-in-flight - human: every open deal, registration, delivery and
claim closed, transferred or paid out under <your
in-flight rules>
owner: partner-manager after: agree-handover
by: <days> automation: <level>
close-access - human: the portal, the systems, the price lists,
the lead flow, the tier and its margins, and the
right to use the name, all ended on a stated date
owner: partner-manager
after: move-customers + finish-in-flight
by: <days> automation: <level>
pay-and-recover - runs allocate-and-reconcile: the final settlement
paid and the amounts recovered, against the lines
the money step agreed
owner: margin-keeper after: close-access
by: <days> automation: <level>
confirm-exit - runs assessment: nothing open in any system, no
customer without an owner, no access still live,
and every surviving obligation written down
owner: partner-monitor after: pay-and-recover
by: <days> automation: <level>
record-learnings - convenes debrief: what the signals were, when they
first showed, and what the program changes so the
next one is seen sooner
owner: partner-manager after: confirm-exit
automation: <level>
run-scoped:
customers - runs roll-call owner: partner-monitor
every: <cadence>
from: tell-customers until: confirm-exit
money - runs allocate-and-reconcile owner: margin-keeper
from: settle-money until: run close
handoffs:
take-in-reason -> check-exit-terms [ending-reason]: what happened,
dated, with the evidence behind it and what was already tried
check-exit-terms -> legal-read [exit-clauses]: the clauses that
apply, quoted from the agreement at the version that was signed
legal-read -> decide-to-end [legal-position]: whether the grounds
hold, what it costs, and what survives the ending
decide-to-end -> list-customers [ending-decision]: the decision and
the date it applies from, so the customer list is taken as of that
date
decide-to-end -> list-in-flight [last-sell-date]: the same decision,
so the last day the partner may sell is known before the lists are
drawn
decide-to-end -> settle-money [money-cut-off]: the same decision, so
the money is counted to a date rather than to an argument
list-customers -> write-plan [customer-list]: every customer, with
the contract, the renewal date and who at the customer has to be
called
list-in-flight -> write-plan [open-work]: everything still open, with
what it is worth and who is waiting on it
settle-money -> write-plan [money-position]: what is owed each way,
with the evidence for every line and every disputed line marked as
disputed
write-plan -> tell-partner [wind-down-plan]: the plan, the dates, and
the last day the partner may sell
tell-partner -> agree-handover [served-notice]: the notice as served,
with the date and the form it was served in
agree-handover -> tell-customers [handover-order]: who tells each
customer, in what order, and what is said, agreed by both sides
where possible
agree-handover -> finish-in-flight [in-flight-split]: what the
partner finishes, what somebody else takes over, and by when
tell-customers -> move-customers [customers-told]: the customers who
have been told, the date, and anything they asked for
move-customers -> close-access [reassigned-customers]: the customers
now held by a named owner, so no access is closed while somebody
still depends on it
finish-in-flight -> close-access [closed-work]: the work closed,
transferred or paid, and anything left open with the reason
close-access -> pay-and-recover [access-ended]: the access ended and
the dates, so the final settlement counts to a real last day
pay-and-recover -> confirm-exit [final-settlement]: what was paid and
recovered, and anything still in dispute
confirm-exit -> record-learnings [exit-confirmation]: the exit as
confirmed, with every item that could not be closed named
deviations:
decide-to-end -> legal-read [position-unclear]: the legal position is
not clear enough to decide on, so what would have to be true is
read out of the agreement again
tell-partner -> check-exit-terms [notice-does-not-count]: the form,
the address or the timing did not match what the agreement
requires, so the terms are read again and the notice served again
agree-handover -> write-plan [partner-will-not-take-part]: the
partner will not agree the handover, so the plan is rewritten for a
one-sided wind-down
tell-customers -> agree-handover [customer-will-not-move]: a customer
will not be moved, so what they asked for goes back to the handover
rather than the customer being moved by force
close-access -> finish-in-flight [access-still-needed]: work is still
running on an access that was closed, so the access is restored for
that work and the work is finished first
confirm-exit -> close-access [something-still-open]: the check finds
something still open, so the access, the customers and the work are
closed off again
bindings:
roster: <who holds each role - agents claiming the abstract agents
above, the partner lead who worked the relationship, the
legal reviewer who reads the agreement, the finance partner
who settles the money, the customer success lead who takes
the customers, and the channel leader who decides>
systems: the partner record (write), the agreement record (read),
the CRM (write), <your deal registration system> (write),
<your finance system> (write), the partner portal (write),
<your price list system> (write),
<your support ticketing system> (write),
the notification channel (write), <your identity system>
(write)
data: the signed agreement at its current version, <your notice
periods>, <your in-flight rules>, the customer list as of
<the decision date>, <your exit checklist>
policy:
the agreement is read before anything is decided, and the run follows
the notice period it sets even when the reason is serious
ending the relationship is decided by a person and is never delegated
to an agent
no customer loses support, a renewal date or a named contact because
the partner is leaving, and no access is closed while a customer
still depends on it
every customer hears the change from <who> before it reaches them,
and hears who serves them next in the same message
a partner is paid what they earned up to the last day, whatever the
reason for ending it
the last day the partner may sell is stated once, in writing, and is
the same date in the plan, the notice and the systems
every obligation that survives the ending is written down and given
an owner inside the company
the run does not close while any customer, deal, delivery or access
is still open, and anything that cannot be closed is named in the
confirmation rather than left out of it
measures:
cycle time: <target> from the decision to the confirmed exit
coverage: <target> share of the partner's customers moved to a named
owner before their support changed
volume: <endings per period>, read as a share of partners under
agreement
quality gate: <sample size> of exits checked each <period> for closed
access, settled money and no customer left unowned
```
Take it somewhere
Use this process in Microsoft Agent Framework
close
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.
copy the prompt
400 lines · the document is inside it, so nothing else is needed
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: end a partner relationship id: <team>/end-a-partner-relationship v1
from: ref/prt/end-a-partner-relationship v1
owner: <who> effective: <date>
trigger: <your partner review process> reports a partner still behind
after <how many> rounds, a term of the agreement is breached,
or either side gives notice
watch: record=<partner review>
system=<your partner review process>
change=<a review reports a partner still behind after
the set number of rounds>
or watch: record=<the agreement>
system=<where breaches are recorded>
change=<a term of the agreement is breached>
or watch: record=<notice to end>
system=<where notices are served>
change=<either side gives notice>
concurrency: one run per partner, and a partner in this run is out of
every review and tiering round while it is open
goal: the relationship ended on the terms the agreement sets, with
every customer the partner held moved to a named owner before
their support changes, every open deal and delivery finished or
transferred, the money settled both ways, and no access left open
phases:
take-in-reason - human: what happened, who is asking to end it, and
what has already been tried
owner: partner-manager after: trigger
automation: <level>
check-exit-terms - runs collect-and-report: the notice period, the
termination grounds, the clauses that survive, and
what the agreement says may not be cut off
owner: partner-manager after: take-in-reason
by: <days> automation: <level>
legal-read - human: whether the grounds hold, what ending it
costs, and what the company still owes afterwards
owner: <your legal role> after: check-exit-terms
by: <days> automation: never
decide-to-end - convenes decide-and-announce: wind down, or one
more attempt to repair on stated terms and a date,
naming who decided it and on what
owner: <your channel leadership role>
after: legal-read
automation: never
list-customers - runs collect-and-report: every customer the partner
holds, with the contract, the renewal date, the
support arrangement and who at the customer to call
owner: partner-monitor after: decide-to-end
by: <days> automation: <level>
list-in-flight - runs collect-and-report: open deals, registrations
still live, deliveries part done, support cases,
and claims against funds not yet paid
owner: partner-monitor after: decide-to-end
by: <days> automation: <level>
settle-money - runs allocate-and-reconcile: commissions earned,
funds committed, rebates due, and anything the
partner owes back, each line with its evidence
owner: margin-keeper after: decide-to-end
by: <days> automation: <level>
write-plan - human: the dates, the owner of each step, what
stops when, and the last day the partner may sell
owner: partner-manager
after: list-customers + list-in-flight + settle-money
by: <days> automation: <level>
tell-partner - human: the notice served in the form and to the
address the agreement names, on a recorded date,
with the wind-down plan attached
owner: partner-manager after: write-plan
automation: never
agree-handover - convenes briefing: who tells each customer, in what
order, with what said, and what the partner keeps
doing until each customer has moved
owner: partner-manager after: tell-partner
by: <days> automation: <level>
tell-customers - human: each customer hears the change, who serves
them next, from what date, and that their contract
and support continue
owner: <your customer success role>
after: agree-handover
by: <days> automation: never
move-customers - human: contracts, support routing, renewals and
named contacts reassigned to <who>, customer by
customer, with a date against each
owner: partner-manager after: tell-customers
by: <days> automation: <level>
finish-in-flight - human: every open deal, registration, delivery and
claim closed, transferred or paid out under <your
in-flight rules>
owner: partner-manager after: agree-handover
by: <days> automation: <level>
close-access - human: the portal, the systems, the price lists,
the lead flow, the tier and its margins, and the
right to use the name, all ended on a stated date
owner: partner-manager
after: move-customers + finish-in-flight
by: <days> automation: <level>
pay-and-recover - runs allocate-and-reconcile: the final settlement
paid and the amounts recovered, against the lines
the money step agreed
owner: margin-keeper after: close-access
by: <days> automation: <level>
confirm-exit - runs assessment: nothing open in any system, no
customer without an owner, no access still live,
and every surviving obligation written down
owner: partner-monitor after: pay-and-recover
by: <days> automation: <level>
record-learnings - convenes debrief: what the signals were, when they
first showed, and what the program changes so the
next one is seen sooner
owner: partner-manager after: confirm-exit
automation: <level>
run-scoped:
customers - runs roll-call owner: partner-monitor
every: <cadence>
from: tell-customers until: confirm-exit
money - runs allocate-and-reconcile owner: margin-keeper
from: settle-money until: run close
handoffs:
take-in-reason -> check-exit-terms [ending-reason]: what happened,
dated, with the evidence behind it and what was already tried
check-exit-terms -> legal-read [exit-clauses]: the clauses that
apply, quoted from the agreement at the version that was signed
legal-read -> decide-to-end [legal-position]: whether the grounds
hold, what it costs, and what survives the ending
decide-to-end -> list-customers [ending-decision]: the decision and
the date it applies from, so the customer list is taken as of that
date
decide-to-end -> list-in-flight [last-sell-date]: the same decision,
so the last day the partner may sell is known before the lists are
drawn
decide-to-end -> settle-money [money-cut-off]: the same decision, so
the money is counted to a date rather than to an argument
list-customers -> write-plan [customer-list]: every customer, with
the contract, the renewal date and who at the customer has to be
called
list-in-flight -> write-plan [open-work]: everything still open, with
what it is worth and who is waiting on it
settle-money -> write-plan [money-position]: what is owed each way,
with the evidence for every line and every disputed line marked as
disputed
write-plan -> tell-partner [wind-down-plan]: the plan, the dates, and
the last day the partner may sell
tell-partner -> agree-handover [served-notice]: the notice as served,
with the date and the form it was served in
agree-handover -> tell-customers [handover-order]: who tells each
customer, in what order, and what is said, agreed by both sides
where possible
agree-handover -> finish-in-flight [in-flight-split]: what the
partner finishes, what somebody else takes over, and by when
tell-customers -> move-customers [customers-told]: the customers who
have been told, the date, and anything they asked for
move-customers -> close-access [reassigned-customers]: the customers
now held by a named owner, so no access is closed while somebody
still depends on it
finish-in-flight -> close-access [closed-work]: the work closed,
transferred or paid, and anything left open with the reason
close-access -> pay-and-recover [access-ended]: the access ended and
the dates, so the final settlement counts to a real last day
pay-and-recover -> confirm-exit [final-settlement]: what was paid and
recovered, and anything still in dispute
confirm-exit -> record-learnings [exit-confirmation]: the exit as
confirmed, with every item that could not be closed named
deviations:
decide-to-end -> legal-read [position-unclear]: the legal position is
not clear enough to decide on, so what would have to be true is
read out of the agreement again
tell-partner -> check-exit-terms [notice-does-not-count]: the form,
the address or the timing did not match what the agreement
requires, so the terms are read again and the notice served again
agree-handover -> write-plan [partner-will-not-take-part]: the
partner will not agree the handover, so the plan is rewritten for a
one-sided wind-down
tell-customers -> agree-handover [customer-will-not-move]: a customer
will not be moved, so what they asked for goes back to the handover
rather than the customer being moved by force
close-access -> finish-in-flight [access-still-needed]: work is still
running on an access that was closed, so the access is restored for
that work and the work is finished first
confirm-exit -> close-access [something-still-open]: the check finds
something still open, so the access, the customers and the work are
closed off again
bindings:
roster: <who holds each role - agents claiming the abstract agents
above, the partner lead who worked the relationship, the
legal reviewer who reads the agreement, the finance partner
who settles the money, the customer success lead who takes
the customers, and the channel leader who decides>
systems: the partner record (write), the agreement record (read),
the CRM (write), <your deal registration system> (write),
<your finance system> (write), the partner portal (write),
<your price list system> (write),
<your support ticketing system> (write),
the notification channel (write), <your identity system>
(write)
data: the signed agreement at its current version, <your notice
periods>, <your in-flight rules>, the customer list as of
<the decision date>, <your exit checklist>
policy:
the agreement is read before anything is decided, and the run follows
the notice period it sets even when the reason is serious
ending the relationship is decided by a person and is never delegated
to an agent
no customer loses support, a renewal date or a named contact because
the partner is leaving, and no access is closed while a customer
still depends on it
every customer hears the change from <who> before it reaches them,
and hears who serves them next in the same message
a partner is paid what they earned up to the last day, whatever the
reason for ending it
the last day the partner may sell is stated once, in writing, and is
the same date in the plan, the notice and the systems
every obligation that survives the ending is written down and given
an owner inside the company
the run does not close while any customer, deal, delivery or access
is still open, and anything that cannot be closed is named in the
confirmation rather than left out of it
measures:
cycle time: <target> from the decision to the confirmed exit
coverage: <target> share of the partner's customers moved to a named
owner before their support changed
volume: <endings per period>, read as a share of partners under
agreement
quality gate: <sample size> of exits checked each <period> for closed
access, settled money and no customer left unowned
```
Take it somewhere
Use this process in CrewAI Flows
close
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.
copy the prompt
405 lines · the document is inside it, so nothing else is needed
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: end a partner relationship id: <team>/end-a-partner-relationship v1
from: ref/prt/end-a-partner-relationship v1
owner: <who> effective: <date>
trigger: <your partner review process> reports a partner still behind
after <how many> rounds, a term of the agreement is breached,
or either side gives notice
watch: record=<partner review>
system=<your partner review process>
change=<a review reports a partner still behind after
the set number of rounds>
or watch: record=<the agreement>
system=<where breaches are recorded>
change=<a term of the agreement is breached>
or watch: record=<notice to end>
system=<where notices are served>
change=<either side gives notice>
concurrency: one run per partner, and a partner in this run is out of
every review and tiering round while it is open
goal: the relationship ended on the terms the agreement sets, with
every customer the partner held moved to a named owner before
their support changes, every open deal and delivery finished or
transferred, the money settled both ways, and no access left open
phases:
take-in-reason - human: what happened, who is asking to end it, and
what has already been tried
owner: partner-manager after: trigger
automation: <level>
check-exit-terms - runs collect-and-report: the notice period, the
termination grounds, the clauses that survive, and
what the agreement says may not be cut off
owner: partner-manager after: take-in-reason
by: <days> automation: <level>
legal-read - human: whether the grounds hold, what ending it
costs, and what the company still owes afterwards
owner: <your legal role> after: check-exit-terms
by: <days> automation: never
decide-to-end - convenes decide-and-announce: wind down, or one
more attempt to repair on stated terms and a date,
naming who decided it and on what
owner: <your channel leadership role>
after: legal-read
automation: never
list-customers - runs collect-and-report: every customer the partner
holds, with the contract, the renewal date, the
support arrangement and who at the customer to call
owner: partner-monitor after: decide-to-end
by: <days> automation: <level>
list-in-flight - runs collect-and-report: open deals, registrations
still live, deliveries part done, support cases,
and claims against funds not yet paid
owner: partner-monitor after: decide-to-end
by: <days> automation: <level>
settle-money - runs allocate-and-reconcile: commissions earned,
funds committed, rebates due, and anything the
partner owes back, each line with its evidence
owner: margin-keeper after: decide-to-end
by: <days> automation: <level>
write-plan - human: the dates, the owner of each step, what
stops when, and the last day the partner may sell
owner: partner-manager
after: list-customers + list-in-flight + settle-money
by: <days> automation: <level>
tell-partner - human: the notice served in the form and to the
address the agreement names, on a recorded date,
with the wind-down plan attached
owner: partner-manager after: write-plan
automation: never
agree-handover - convenes briefing: who tells each customer, in what
order, with what said, and what the partner keeps
doing until each customer has moved
owner: partner-manager after: tell-partner
by: <days> automation: <level>
tell-customers - human: each customer hears the change, who serves
them next, from what date, and that their contract
and support continue
owner: <your customer success role>
after: agree-handover
by: <days> automation: never
move-customers - human: contracts, support routing, renewals and
named contacts reassigned to <who>, customer by
customer, with a date against each
owner: partner-manager after: tell-customers
by: <days> automation: <level>
finish-in-flight - human: every open deal, registration, delivery and
claim closed, transferred or paid out under <your
in-flight rules>
owner: partner-manager after: agree-handover
by: <days> automation: <level>
close-access - human: the portal, the systems, the price lists,
the lead flow, the tier and its margins, and the
right to use the name, all ended on a stated date
owner: partner-manager
after: move-customers + finish-in-flight
by: <days> automation: <level>
pay-and-recover - runs allocate-and-reconcile: the final settlement
paid and the amounts recovered, against the lines
the money step agreed
owner: margin-keeper after: close-access
by: <days> automation: <level>
confirm-exit - runs assessment: nothing open in any system, no
customer without an owner, no access still live,
and every surviving obligation written down
owner: partner-monitor after: pay-and-recover
by: <days> automation: <level>
record-learnings - convenes debrief: what the signals were, when they
first showed, and what the program changes so the
next one is seen sooner
owner: partner-manager after: confirm-exit
automation: <level>
run-scoped:
customers - runs roll-call owner: partner-monitor
every: <cadence>
from: tell-customers until: confirm-exit
money - runs allocate-and-reconcile owner: margin-keeper
from: settle-money until: run close
handoffs:
take-in-reason -> check-exit-terms [ending-reason]: what happened,
dated, with the evidence behind it and what was already tried
check-exit-terms -> legal-read [exit-clauses]: the clauses that
apply, quoted from the agreement at the version that was signed
legal-read -> decide-to-end [legal-position]: whether the grounds
hold, what it costs, and what survives the ending
decide-to-end -> list-customers [ending-decision]: the decision and
the date it applies from, so the customer list is taken as of that
date
decide-to-end -> list-in-flight [last-sell-date]: the same decision,
so the last day the partner may sell is known before the lists are
drawn
decide-to-end -> settle-money [money-cut-off]: the same decision, so
the money is counted to a date rather than to an argument
list-customers -> write-plan [customer-list]: every customer, with
the contract, the renewal date and who at the customer has to be
called
list-in-flight -> write-plan [open-work]: everything still open, with
what it is worth and who is waiting on it
settle-money -> write-plan [money-position]: what is owed each way,
with the evidence for every line and every disputed line marked as
disputed
write-plan -> tell-partner [wind-down-plan]: the plan, the dates, and
the last day the partner may sell
tell-partner -> agree-handover [served-notice]: the notice as served,
with the date and the form it was served in
agree-handover -> tell-customers [handover-order]: who tells each
customer, in what order, and what is said, agreed by both sides
where possible
agree-handover -> finish-in-flight [in-flight-split]: what the
partner finishes, what somebody else takes over, and by when
tell-customers -> move-customers [customers-told]: the customers who
have been told, the date, and anything they asked for
move-customers -> close-access [reassigned-customers]: the customers
now held by a named owner, so no access is closed while somebody
still depends on it
finish-in-flight -> close-access [closed-work]: the work closed,
transferred or paid, and anything left open with the reason
close-access -> pay-and-recover [access-ended]: the access ended and
the dates, so the final settlement counts to a real last day
pay-and-recover -> confirm-exit [final-settlement]: what was paid and
recovered, and anything still in dispute
confirm-exit -> record-learnings [exit-confirmation]: the exit as
confirmed, with every item that could not be closed named
deviations:
decide-to-end -> legal-read [position-unclear]: the legal position is
not clear enough to decide on, so what would have to be true is
read out of the agreement again
tell-partner -> check-exit-terms [notice-does-not-count]: the form,
the address or the timing did not match what the agreement
requires, so the terms are read again and the notice served again
agree-handover -> write-plan [partner-will-not-take-part]: the
partner will not agree the handover, so the plan is rewritten for a
one-sided wind-down
tell-customers -> agree-handover [customer-will-not-move]: a customer
will not be moved, so what they asked for goes back to the handover
rather than the customer being moved by force
close-access -> finish-in-flight [access-still-needed]: work is still
running on an access that was closed, so the access is restored for
that work and the work is finished first
confirm-exit -> close-access [something-still-open]: the check finds
something still open, so the access, the customers and the work are
closed off again
bindings:
roster: <who holds each role - agents claiming the abstract agents
above, the partner lead who worked the relationship, the
legal reviewer who reads the agreement, the finance partner
who settles the money, the customer success lead who takes
the customers, and the channel leader who decides>
systems: the partner record (write), the agreement record (read),
the CRM (write), <your deal registration system> (write),
<your finance system> (write), the partner portal (write),
<your price list system> (write),
<your support ticketing system> (write),
the notification channel (write), <your identity system>
(write)
data: the signed agreement at its current version, <your notice
periods>, <your in-flight rules>, the customer list as of
<the decision date>, <your exit checklist>
policy:
the agreement is read before anything is decided, and the run follows
the notice period it sets even when the reason is serious
ending the relationship is decided by a person and is never delegated
to an agent
no customer loses support, a renewal date or a named contact because
the partner is leaving, and no access is closed while a customer
still depends on it
every customer hears the change from <who> before it reaches them,
and hears who serves them next in the same message
a partner is paid what they earned up to the last day, whatever the
reason for ending it
the last day the partner may sell is stated once, in writing, and is
the same date in the plan, the notice and the systems
every obligation that survives the ending is written down and given
an owner inside the company
the run does not close while any customer, deal, delivery or access
is still open, and anything that cannot be closed is named in the
confirmation rather than left out of it
measures:
cycle time: <target> from the decision to the confirmed exit
coverage: <target> share of the partner's customers moved to a named
owner before their support changed
volume: <endings per period>, read as a share of partners under
agreement
quality gate: <sample size> of exits checked each <period> for closed
access, settled money and no customer left unowned
```
Take it somewhere
Use this process in Google ADK
close
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.
copy the prompt
396 lines · the document is inside it, so nothing else is needed
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: end a partner relationship id: <team>/end-a-partner-relationship v1
from: ref/prt/end-a-partner-relationship v1
owner: <who> effective: <date>
trigger: <your partner review process> reports a partner still behind
after <how many> rounds, a term of the agreement is breached,
or either side gives notice
watch: record=<partner review>
system=<your partner review process>
change=<a review reports a partner still behind after
the set number of rounds>
or watch: record=<the agreement>
system=<where breaches are recorded>
change=<a term of the agreement is breached>
or watch: record=<notice to end>
system=<where notices are served>
change=<either side gives notice>
concurrency: one run per partner, and a partner in this run is out of
every review and tiering round while it is open
goal: the relationship ended on the terms the agreement sets, with
every customer the partner held moved to a named owner before
their support changes, every open deal and delivery finished or
transferred, the money settled both ways, and no access left open
phases:
take-in-reason - human: what happened, who is asking to end it, and
what has already been tried
owner: partner-manager after: trigger
automation: <level>
check-exit-terms - runs collect-and-report: the notice period, the
termination grounds, the clauses that survive, and
what the agreement says may not be cut off
owner: partner-manager after: take-in-reason
by: <days> automation: <level>
legal-read - human: whether the grounds hold, what ending it
costs, and what the company still owes afterwards
owner: <your legal role> after: check-exit-terms
by: <days> automation: never
decide-to-end - convenes decide-and-announce: wind down, or one
more attempt to repair on stated terms and a date,
naming who decided it and on what
owner: <your channel leadership role>
after: legal-read
automation: never
list-customers - runs collect-and-report: every customer the partner
holds, with the contract, the renewal date, the
support arrangement and who at the customer to call
owner: partner-monitor after: decide-to-end
by: <days> automation: <level>
list-in-flight - runs collect-and-report: open deals, registrations
still live, deliveries part done, support cases,
and claims against funds not yet paid
owner: partner-monitor after: decide-to-end
by: <days> automation: <level>
settle-money - runs allocate-and-reconcile: commissions earned,
funds committed, rebates due, and anything the
partner owes back, each line with its evidence
owner: margin-keeper after: decide-to-end
by: <days> automation: <level>
write-plan - human: the dates, the owner of each step, what
stops when, and the last day the partner may sell
owner: partner-manager
after: list-customers + list-in-flight + settle-money
by: <days> automation: <level>
tell-partner - human: the notice served in the form and to the
address the agreement names, on a recorded date,
with the wind-down plan attached
owner: partner-manager after: write-plan
automation: never
agree-handover - convenes briefing: who tells each customer, in what
order, with what said, and what the partner keeps
doing until each customer has moved
owner: partner-manager after: tell-partner
by: <days> automation: <level>
tell-customers - human: each customer hears the change, who serves
them next, from what date, and that their contract
and support continue
owner: <your customer success role>
after: agree-handover
by: <days> automation: never
move-customers - human: contracts, support routing, renewals and
named contacts reassigned to <who>, customer by
customer, with a date against each
owner: partner-manager after: tell-customers
by: <days> automation: <level>
finish-in-flight - human: every open deal, registration, delivery and
claim closed, transferred or paid out under <your
in-flight rules>
owner: partner-manager after: agree-handover
by: <days> automation: <level>
close-access - human: the portal, the systems, the price lists,
the lead flow, the tier and its margins, and the
right to use the name, all ended on a stated date
owner: partner-manager
after: move-customers + finish-in-flight
by: <days> automation: <level>
pay-and-recover - runs allocate-and-reconcile: the final settlement
paid and the amounts recovered, against the lines
the money step agreed
owner: margin-keeper after: close-access
by: <days> automation: <level>
confirm-exit - runs assessment: nothing open in any system, no
customer without an owner, no access still live,
and every surviving obligation written down
owner: partner-monitor after: pay-and-recover
by: <days> automation: <level>
record-learnings - convenes debrief: what the signals were, when they
first showed, and what the program changes so the
next one is seen sooner
owner: partner-manager after: confirm-exit
automation: <level>
run-scoped:
customers - runs roll-call owner: partner-monitor
every: <cadence>
from: tell-customers until: confirm-exit
money - runs allocate-and-reconcile owner: margin-keeper
from: settle-money until: run close
handoffs:
take-in-reason -> check-exit-terms [ending-reason]: what happened,
dated, with the evidence behind it and what was already tried
check-exit-terms -> legal-read [exit-clauses]: the clauses that
apply, quoted from the agreement at the version that was signed
legal-read -> decide-to-end [legal-position]: whether the grounds
hold, what it costs, and what survives the ending
decide-to-end -> list-customers [ending-decision]: the decision and
the date it applies from, so the customer list is taken as of that
date
decide-to-end -> list-in-flight [last-sell-date]: the same decision,
so the last day the partner may sell is known before the lists are
drawn
decide-to-end -> settle-money [money-cut-off]: the same decision, so
the money is counted to a date rather than to an argument
list-customers -> write-plan [customer-list]: every customer, with
the contract, the renewal date and who at the customer has to be
called
list-in-flight -> write-plan [open-work]: everything still open, with
what it is worth and who is waiting on it
settle-money -> write-plan [money-position]: what is owed each way,
with the evidence for every line and every disputed line marked as
disputed
write-plan -> tell-partner [wind-down-plan]: the plan, the dates, and
the last day the partner may sell
tell-partner -> agree-handover [served-notice]: the notice as served,
with the date and the form it was served in
agree-handover -> tell-customers [handover-order]: who tells each
customer, in what order, and what is said, agreed by both sides
where possible
agree-handover -> finish-in-flight [in-flight-split]: what the
partner finishes, what somebody else takes over, and by when
tell-customers -> move-customers [customers-told]: the customers who
have been told, the date, and anything they asked for
move-customers -> close-access [reassigned-customers]: the customers
now held by a named owner, so no access is closed while somebody
still depends on it
finish-in-flight -> close-access [closed-work]: the work closed,
transferred or paid, and anything left open with the reason
close-access -> pay-and-recover [access-ended]: the access ended and
the dates, so the final settlement counts to a real last day
pay-and-recover -> confirm-exit [final-settlement]: what was paid and
recovered, and anything still in dispute
confirm-exit -> record-learnings [exit-confirmation]: the exit as
confirmed, with every item that could not be closed named
deviations:
decide-to-end -> legal-read [position-unclear]: the legal position is
not clear enough to decide on, so what would have to be true is
read out of the agreement again
tell-partner -> check-exit-terms [notice-does-not-count]: the form,
the address or the timing did not match what the agreement
requires, so the terms are read again and the notice served again
agree-handover -> write-plan [partner-will-not-take-part]: the
partner will not agree the handover, so the plan is rewritten for a
one-sided wind-down
tell-customers -> agree-handover [customer-will-not-move]: a customer
will not be moved, so what they asked for goes back to the handover
rather than the customer being moved by force
close-access -> finish-in-flight [access-still-needed]: work is still
running on an access that was closed, so the access is restored for
that work and the work is finished first
confirm-exit -> close-access [something-still-open]: the check finds
something still open, so the access, the customers and the work are
closed off again
bindings:
roster: <who holds each role - agents claiming the abstract agents
above, the partner lead who worked the relationship, the
legal reviewer who reads the agreement, the finance partner
who settles the money, the customer success lead who takes
the customers, and the channel leader who decides>
systems: the partner record (write), the agreement record (read),
the CRM (write), <your deal registration system> (write),
<your finance system> (write), the partner portal (write),
<your price list system> (write),
<your support ticketing system> (write),
the notification channel (write), <your identity system>
(write)
data: the signed agreement at its current version, <your notice
periods>, <your in-flight rules>, the customer list as of
<the decision date>, <your exit checklist>
policy:
the agreement is read before anything is decided, and the run follows
the notice period it sets even when the reason is serious
ending the relationship is decided by a person and is never delegated
to an agent
no customer loses support, a renewal date or a named contact because
the partner is leaving, and no access is closed while a customer
still depends on it
every customer hears the change from <who> before it reaches them,
and hears who serves them next in the same message
a partner is paid what they earned up to the last day, whatever the
reason for ending it
the last day the partner may sell is stated once, in writing, and is
the same date in the plan, the notice and the systems
every obligation that survives the ending is written down and given
an owner inside the company
the run does not close while any customer, deal, delivery or access
is still open, and anything that cannot be closed is named in the
confirmation rather than left out of it
measures:
cycle time: <target> from the decision to the confirmed exit
coverage: <target> share of the partner's customers moved to a named
owner before their support changed
volume: <endings per period>, read as a share of partners under
agreement
quality gate: <sample size> of exits checked each <period> for closed
access, settled money and no customer left unowned
```
One run
A simulation of one run
The activities are on the left, whoever is doing the active one is on the right, and the record of the run builds up as it goes.
This run is built from the same rows as the diagram above: the left column is the activity list, the captions are the activity lines, the cast is the roster, and the labels on the wires are what the handoffs say actually passes.
Adoption
What you fill in
58 blanks to fill. Everything else is the process.
this process
from: ref/prt/end-a-partner-relationship v1
Copy this line into your own document. It never claims this process is running anywhere; it records which draft yours started from, and it is what lets the catalog tell you when this one changes.
The header. Your own id, an owner, and the date it takes effect. One line records where it came from, and that line is what lets the catalog tell you when this reference process changes.
The roster. Which agent takes each activity, and which person takes each of the human ones. The process already names what it needs, so this is a lookup rather than a design exercise.
The numbers. Dates, budgets, cadences, and the targets in the measures block. Nothing here can be a reference value, because a target nobody chose is a target nobody meets.