Catalog / Business processes / Partners / Plan-to-Commitment / Review a Joint Plan
reference process · partners · 17 activities · 11 on the rosterReview a Joint Plan
The review date arrives and somebody puts the numbers in front of both sides. Each measure the plan named is pulled, checked against what the partner counts, and settled to one figure before anyone meets. Every commitment is read out with its owner, its date and its state. The meeting then does the one thing a plan cannot do for itself: it names the gaps out loud, changes the targets or the accounts or the inputs, and closes the commitments nobody is going to do. What changed is signed, recorded and published, and the next review is dated.
The walk
The document
One run
Adoption
The activities
What happens in a run
17 activities from the review date named in the plan arrives to the plan is amended or called dead, and both sides hold the record, 2 of them gates a person has to sign. Drag the diagram to move along it.
Review a Joint Plan the review date named in the plan arrives → the plan is amended or called dead, and both sides hold the record
the two sides count a measure differently a number nobody can source a side has not read the pack the pack does not show the gap the decision needs a number nobody brought a sponsor will not sign the change the review date named in the plan arrives 1 Open the Review the cadence fires and the review is put on calendars 2 Pull the Numbers the measures the plan named, at today's values 3 Check the Numbers Both Si… our figures set against the partner's figures 4 Settle the Differences one number per measure, agreed before the meeting 5 Read the Commitments every commitment with its owner, date and state 6 Read the Accounts what moved on the accounts the plan named 7 Build the Review Pack the numbers, the commitments and the gaps, in one pack 8 Send the Pack Before the … both sides read the same pack before they meet 9 Hold the Review both sides in the room with the numbers in front 10 Name the Gaps Out Loud every measure behind target, with the reason 11 Decide What Changes targets, accounts, inputs, or nothing changes 12 Say Which Commitments Are… the ones nobody will do are closed, with reasons 13 Write the Amendment the plan changed at a new version 14 Re-Sign the Changed Lines the sponsors sign what changed a person signs · never an agent 15 Record the Decisions and … the decisions, the owners and the new dates 16 Publish the Review Record both sides can read what was decided 17 Set the Next Review the next review is dated, or the plan is called dead a person signs · never an agent the plan is amended or called dead, and both sides hold the record 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: joint plan review id: <team> /review-a-joint-plan v1
from: ref/prt/review-a-joint-plan v1
owner: <who> effective: <date>
trigger: a review date recorded in a signed joint plan arrives, or
<who> calls a review out of cadence
watch: record=<joint plan>
system=<your shared plan location>
change=<the review date recorded in the signed plan
arrives>
or watch: record=<joint plan>
system=<your shared plan location>
change=<a review is called out of cadence>
concurrency: runs may overlap - <how many> reviews run at once, and one
plan is reviewed by one run at a time
goal: every measure in the plan settled to one number both sides
accept, every commitment marked met, moved or dead, the plan
amended or confirmed at a version, and the next review dated
phases:
open-review - system: the review is opened against the signed
plan and put on the calendar of everyone the plan
names
owner: commitment-keeper after: trigger
by: <days> automation: <level>
pull-numbers - runs collect-and-report: each measure the plan
defined, at today's value, from the system the
plan named for it
owner: analytics after: open-review
by: <days> automation: <level>
compare-numbers - runs assessment: our figure set against the
partner's figure, measure by measure, with the
gap between them shown rather than averaged
owner: analytics after: pull-numbers
by: <days> automation: <level>
settle-difference - human: one number per measure, agreed with <who>
on the partner's side before anybody meets
owner: partner-manager after: compare-numbers
by: <days> automation: <level>
read-commitments - runs roll-call: every commitment in the plan, its
owner, its date, and whether it is met, running,
late or untouched
owner: commitment-keeper after: open-review
automation: <level>
read-accounts - runs collect-and-report: what moved on each named
account since the last review, dated
owner: partner-monitor after: open-review
by: <days> automation: <level>
build-pack - runs build-by-talent: the settled numbers, the
commitments and the gaps, in one pack both sides
will read from
owner: reporting-manager
after: settle-difference + read-commitments +
read-accounts
by: <days> automation: <level>
send-pack - system: the pack goes to both sides at least
<days> before the meeting
owner: reporting-manager after: build-pack
automation: <level>
hold-review - convenes debrief: both sides walk the pack, with
the people the plan named in the room
owner: partner-manager after: send-pack
automation: <level>
name-gaps - human: every measure behind target said out loud,
with the reason and the person closest to it
owner: partner-manager after: hold-review
automation: <level>
decide-changes - convenes decide-and-announce: what changes in the
plan, or that nothing does. <who> decides for our
side and their sponsor decides for theirs
owner: joint-planner after: name-gaps
automation: <level>
close-dead - human: the commitments nobody is going to do are
closed, each with the reason and the date it was
given up on
owner: commitment-keeper after: decide-changes
automation: <level>
write-amendment - runs build-by-talent: the plan rewritten at a new
version, with the changed lines marked against
the version they replace
owner: joint-planner
after: decide-changes + close-dead
by: <days> automation: <level>
re-sign - convenes approval: the sponsors sign the changed
lines, as named signers, against the new version
owner: <your partner leadership role>
after: write-amendment
by: <days> automation: never
record-decisions - system: the decisions, the closed commitments,
the new owners and the new dates, written to the
commitment tracker
owner: commitment-keeper after: re-sign
automation: <level>
publish-record - human: the review record lands at <your shared
location> beside the plan it reviewed
owner: reporting-manager after: record-decisions
by: <days> automation: <level>
set-next-review - human: the next review is dated and on both
calendars, or the plan is called dead and <who>
is told
owner: partner-manager after: publish-record
automation: never
run-scoped:
attendance - runs roll-call owner: partner-manager
every: <cadence>
from: send-pack until: hold-review
gaps - runs collect-and-report owner: analytics
every: <cadence>
from: record-decisions until: the next review opens
handoffs:
open-review -> pull-numbers [plan-and-measures]: the signed plan at
its version, and the measures it defined
open-review -> read-commitments [recorded-commitments]: the same
plan, and every commitment recorded when it was signed
open-review -> read-accounts [named-accounts]: the accounts and
segments the plan named
pull-numbers -> compare-numbers [our-figures]: each measure at its
value, with the system and the date it was read
compare-numbers -> settle-difference [measure-differences]: the gap
between the two sides per measure, with the definition each side
was computing to
settle-difference -> build-pack [settled-numbers]: one number per
measure, and the measures the two sides could not settle, marked as
unsettled rather than dropped
read-commitments -> build-pack [commitment-states]: every commitment,
its owner, its date and its state, with the late ones counted
read-accounts -> build-pack [account-movement]: what moved on each
named account, dated
build-pack -> send-pack [review-pack]: the pack at a version, with
every number naming where it came from
send-pack -> hold-review [pack-receipts]: the pack, and who on each
side received it and when
hold-review -> name-gaps [what-was-said]: what both sides said about
each measure, including the numbers nobody defended
name-gaps -> decide-changes [gaps-and-reasons]: every measure behind
target, its reason, and the person closest to it
decide-changes -> close-dead [changes-decided]: what changes, and
which commitments the change makes pointless
decide-changes -> write-amendment [sponsor-decisions]: the decisions
as both sponsors announced them
close-dead -> write-amendment [dead-commitments]: the commitments
closed, each with its reason, so the amendment does not carry them
forward
write-amendment -> re-sign [amended-plan]: the new version, with the
changed lines marked against the version they replace
re-sign -> record-decisions [signed-amendment]: the signed amendment,
the signers, and the date. An unsigned change is not recorded as
agreed
record-decisions -> publish-record [tracked-decisions]: the
decisions, the owners and the new dates as they now stand in the
tracker
publish-record -> set-next-review [published-record]: the record at
its address, and who on each side has been given it
deviations:
compare-numbers -> pull-numbers [counted-differently]: the two sides
count a measure differently, so the measure is pulled again with
the definition each side computed to
settle-difference -> pull-numbers [number-cannot-be-sourced]: a
number nobody can source, so the measure goes back to be pulled
from a system that produces it or is marked unsettled
hold-review -> send-pack [pack-not-read]: a side has not read the
pack, so the pack goes out again and the meeting waits for it
name-gaps -> build-pack [gap-not-in-pack]: the pack does not show a
gap the room can see, so the pack is built again around it
decide-changes -> pull-numbers [number-not-brought]: the decision
needs a number nobody brought, so that measure is pulled before the
change is decided
re-sign -> decide-changes [sponsor-will-not-sign]: a sponsor will not
sign the change, so what they objected to goes back to the decision
bindings:
roster: <who holds each role - agents claiming the abstract agents
above, and named people for the partner lead, the sales
leader, the partner's operations contact and the two
executive sponsors>
systems: the CRM (read), the partner record (write),
the commitment tracker (write), the partner portal (read),
the shared plan location (write),
the calendar of every attendee (write), analytics (read)
data: the signed joint plan <version> , the measure definitions it
carries, <your territory map> , the record of the previous
review
policy:
the numbers are settled before the meeting, and a measure the two
sides cannot settle goes into the pack as unsettled rather than as
either side's figure
the pack reaches both sides at least <days> before the meeting, and a
review whose pack was late is rescheduled rather than held blind
every measure behind target is named out loud, and a review that
reports only what went well is not a review
a commitment is met, moved or dead. Nothing stays open by silence
a commitment moved twice is escalated to <who> rather than moved a
third time
a change to the plan is signed by both sponsors before it is recorded
as agreed
<how many> consecutive reviews with no measure met sends the plan to
<who> for a decision on whether the partnership continues
measures:
cycle time: <target> from the review date to the published record
coverage: <target> share of commitments carrying a current state
volume: <reviews per period>
quality gate: no review is held without a settled number for every
measure or a note saying why it is unsettled
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
323 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: joint plan review id: <team>/review-a-joint-plan v1
from: ref/prt/review-a-joint-plan v1
owner: <who> effective: <date>
trigger: a review date recorded in a signed joint plan arrives, or
<who> calls a review out of cadence
watch: record=<joint plan>
system=<your shared plan location>
change=<the review date recorded in the signed plan
arrives>
or watch: record=<joint plan>
system=<your shared plan location>
change=<a review is called out of cadence>
concurrency: runs may overlap - <how many> reviews run at once, and one
plan is reviewed by one run at a time
goal: every measure in the plan settled to one number both sides
accept, every commitment marked met, moved or dead, the plan
amended or confirmed at a version, and the next review dated
phases:
open-review - system: the review is opened against the signed
plan and put on the calendar of everyone the plan
names
owner: commitment-keeper after: trigger
by: <days> automation: <level>
pull-numbers - runs collect-and-report: each measure the plan
defined, at today's value, from the system the
plan named for it
owner: analytics after: open-review
by: <days> automation: <level>
compare-numbers - runs assessment: our figure set against the
partner's figure, measure by measure, with the
gap between them shown rather than averaged
owner: analytics after: pull-numbers
by: <days> automation: <level>
settle-difference - human: one number per measure, agreed with <who>
on the partner's side before anybody meets
owner: partner-manager after: compare-numbers
by: <days> automation: <level>
read-commitments - runs roll-call: every commitment in the plan, its
owner, its date, and whether it is met, running,
late or untouched
owner: commitment-keeper after: open-review
automation: <level>
read-accounts - runs collect-and-report: what moved on each named
account since the last review, dated
owner: partner-monitor after: open-review
by: <days> automation: <level>
build-pack - runs build-by-talent: the settled numbers, the
commitments and the gaps, in one pack both sides
will read from
owner: reporting-manager
after: settle-difference + read-commitments +
read-accounts
by: <days> automation: <level>
send-pack - system: the pack goes to both sides at least
<days> before the meeting
owner: reporting-manager after: build-pack
automation: <level>
hold-review - convenes debrief: both sides walk the pack, with
the people the plan named in the room
owner: partner-manager after: send-pack
automation: <level>
name-gaps - human: every measure behind target said out loud,
with the reason and the person closest to it
owner: partner-manager after: hold-review
automation: <level>
decide-changes - convenes decide-and-announce: what changes in the
plan, or that nothing does. <who> decides for our
side and their sponsor decides for theirs
owner: joint-planner after: name-gaps
automation: <level>
close-dead - human: the commitments nobody is going to do are
closed, each with the reason and the date it was
given up on
owner: commitment-keeper after: decide-changes
automation: <level>
write-amendment - runs build-by-talent: the plan rewritten at a new
version, with the changed lines marked against
the version they replace
owner: joint-planner
after: decide-changes + close-dead
by: <days> automation: <level>
re-sign - convenes approval: the sponsors sign the changed
lines, as named signers, against the new version
owner: <your partner leadership role>
after: write-amendment
by: <days> automation: never
record-decisions - system: the decisions, the closed commitments,
the new owners and the new dates, written to the
commitment tracker
owner: commitment-keeper after: re-sign
automation: <level>
publish-record - human: the review record lands at <your shared
location> beside the plan it reviewed
owner: reporting-manager after: record-decisions
by: <days> automation: <level>
set-next-review - human: the next review is dated and on both
calendars, or the plan is called dead and <who>
is told
owner: partner-manager after: publish-record
automation: never
run-scoped:
attendance - runs roll-call owner: partner-manager
every: <cadence>
from: send-pack until: hold-review
gaps - runs collect-and-report owner: analytics
every: <cadence>
from: record-decisions until: the next review opens
handoffs:
open-review -> pull-numbers [plan-and-measures]: the signed plan at
its version, and the measures it defined
open-review -> read-commitments [recorded-commitments]: the same
plan, and every commitment recorded when it was signed
open-review -> read-accounts [named-accounts]: the accounts and
segments the plan named
pull-numbers -> compare-numbers [our-figures]: each measure at its
value, with the system and the date it was read
compare-numbers -> settle-difference [measure-differences]: the gap
between the two sides per measure, with the definition each side
was computing to
settle-difference -> build-pack [settled-numbers]: one number per
measure, and the measures the two sides could not settle, marked as
unsettled rather than dropped
read-commitments -> build-pack [commitment-states]: every commitment,
its owner, its date and its state, with the late ones counted
read-accounts -> build-pack [account-movement]: what moved on each
named account, dated
build-pack -> send-pack [review-pack]: the pack at a version, with
every number naming where it came from
send-pack -> hold-review [pack-receipts]: the pack, and who on each
side received it and when
hold-review -> name-gaps [what-was-said]: what both sides said about
each measure, including the numbers nobody defended
name-gaps -> decide-changes [gaps-and-reasons]: every measure behind
target, its reason, and the person closest to it
decide-changes -> close-dead [changes-decided]: what changes, and
which commitments the change makes pointless
decide-changes -> write-amendment [sponsor-decisions]: the decisions
as both sponsors announced them
close-dead -> write-amendment [dead-commitments]: the commitments
closed, each with its reason, so the amendment does not carry them
forward
write-amendment -> re-sign [amended-plan]: the new version, with the
changed lines marked against the version they replace
re-sign -> record-decisions [signed-amendment]: the signed amendment,
the signers, and the date. An unsigned change is not recorded as
agreed
record-decisions -> publish-record [tracked-decisions]: the
decisions, the owners and the new dates as they now stand in the
tracker
publish-record -> set-next-review [published-record]: the record at
its address, and who on each side has been given it
deviations:
compare-numbers -> pull-numbers [counted-differently]: the two sides
count a measure differently, so the measure is pulled again with
the definition each side computed to
settle-difference -> pull-numbers [number-cannot-be-sourced]: a
number nobody can source, so the measure goes back to be pulled
from a system that produces it or is marked unsettled
hold-review -> send-pack [pack-not-read]: a side has not read the
pack, so the pack goes out again and the meeting waits for it
name-gaps -> build-pack [gap-not-in-pack]: the pack does not show a
gap the room can see, so the pack is built again around it
decide-changes -> pull-numbers [number-not-brought]: the decision
needs a number nobody brought, so that measure is pulled before the
change is decided
re-sign -> decide-changes [sponsor-will-not-sign]: a sponsor will not
sign the change, so what they objected to goes back to the decision
bindings:
roster: <who holds each role - agents claiming the abstract agents
above, and named people for the partner lead, the sales
leader, the partner's operations contact and the two
executive sponsors>
systems: the CRM (read), the partner record (write),
the commitment tracker (write), the partner portal (read),
the shared plan location (write),
the calendar of every attendee (write), analytics (read)
data: the signed joint plan <version>, the measure definitions it
carries, <your territory map>, the record of the previous
review
policy:
the numbers are settled before the meeting, and a measure the two
sides cannot settle goes into the pack as unsettled rather than as
either side's figure
the pack reaches both sides at least <days> before the meeting, and a
review whose pack was late is rescheduled rather than held blind
every measure behind target is named out loud, and a review that
reports only what went well is not a review
a commitment is met, moved or dead. Nothing stays open by silence
a commitment moved twice is escalated to <who> rather than moved a
third time
a change to the plan is signed by both sponsors before it is recorded
as agreed
<how many> consecutive reviews with no measure met sends the plan to
<who> for a decision on whether the partnership continues
measures:
cycle time: <target> from the review date to the published record
coverage: <target> share of commitments carrying a current state
volume: <reviews per period>
quality gate: no review is held without a settled number for every
measure or a note saying why it is unsettled
```
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
378 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: joint plan review id: <team>/review-a-joint-plan v1
from: ref/prt/review-a-joint-plan v1
owner: <who> effective: <date>
trigger: a review date recorded in a signed joint plan arrives, or
<who> calls a review out of cadence
watch: record=<joint plan>
system=<your shared plan location>
change=<the review date recorded in the signed plan
arrives>
or watch: record=<joint plan>
system=<your shared plan location>
change=<a review is called out of cadence>
concurrency: runs may overlap - <how many> reviews run at once, and one
plan is reviewed by one run at a time
goal: every measure in the plan settled to one number both sides
accept, every commitment marked met, moved or dead, the plan
amended or confirmed at a version, and the next review dated
phases:
open-review - system: the review is opened against the signed
plan and put on the calendar of everyone the plan
names
owner: commitment-keeper after: trigger
by: <days> automation: <level>
pull-numbers - runs collect-and-report: each measure the plan
defined, at today's value, from the system the
plan named for it
owner: analytics after: open-review
by: <days> automation: <level>
compare-numbers - runs assessment: our figure set against the
partner's figure, measure by measure, with the
gap between them shown rather than averaged
owner: analytics after: pull-numbers
by: <days> automation: <level>
settle-difference - human: one number per measure, agreed with <who>
on the partner's side before anybody meets
owner: partner-manager after: compare-numbers
by: <days> automation: <level>
read-commitments - runs roll-call: every commitment in the plan, its
owner, its date, and whether it is met, running,
late or untouched
owner: commitment-keeper after: open-review
automation: <level>
read-accounts - runs collect-and-report: what moved on each named
account since the last review, dated
owner: partner-monitor after: open-review
by: <days> automation: <level>
build-pack - runs build-by-talent: the settled numbers, the
commitments and the gaps, in one pack both sides
will read from
owner: reporting-manager
after: settle-difference + read-commitments +
read-accounts
by: <days> automation: <level>
send-pack - system: the pack goes to both sides at least
<days> before the meeting
owner: reporting-manager after: build-pack
automation: <level>
hold-review - convenes debrief: both sides walk the pack, with
the people the plan named in the room
owner: partner-manager after: send-pack
automation: <level>
name-gaps - human: every measure behind target said out loud,
with the reason and the person closest to it
owner: partner-manager after: hold-review
automation: <level>
decide-changes - convenes decide-and-announce: what changes in the
plan, or that nothing does. <who> decides for our
side and their sponsor decides for theirs
owner: joint-planner after: name-gaps
automation: <level>
close-dead - human: the commitments nobody is going to do are
closed, each with the reason and the date it was
given up on
owner: commitment-keeper after: decide-changes
automation: <level>
write-amendment - runs build-by-talent: the plan rewritten at a new
version, with the changed lines marked against
the version they replace
owner: joint-planner
after: decide-changes + close-dead
by: <days> automation: <level>
re-sign - convenes approval: the sponsors sign the changed
lines, as named signers, against the new version
owner: <your partner leadership role>
after: write-amendment
by: <days> automation: never
record-decisions - system: the decisions, the closed commitments,
the new owners and the new dates, written to the
commitment tracker
owner: commitment-keeper after: re-sign
automation: <level>
publish-record - human: the review record lands at <your shared
location> beside the plan it reviewed
owner: reporting-manager after: record-decisions
by: <days> automation: <level>
set-next-review - human: the next review is dated and on both
calendars, or the plan is called dead and <who>
is told
owner: partner-manager after: publish-record
automation: never
run-scoped:
attendance - runs roll-call owner: partner-manager
every: <cadence>
from: send-pack until: hold-review
gaps - runs collect-and-report owner: analytics
every: <cadence>
from: record-decisions until: the next review opens
handoffs:
open-review -> pull-numbers [plan-and-measures]: the signed plan at
its version, and the measures it defined
open-review -> read-commitments [recorded-commitments]: the same
plan, and every commitment recorded when it was signed
open-review -> read-accounts [named-accounts]: the accounts and
segments the plan named
pull-numbers -> compare-numbers [our-figures]: each measure at its
value, with the system and the date it was read
compare-numbers -> settle-difference [measure-differences]: the gap
between the two sides per measure, with the definition each side
was computing to
settle-difference -> build-pack [settled-numbers]: one number per
measure, and the measures the two sides could not settle, marked as
unsettled rather than dropped
read-commitments -> build-pack [commitment-states]: every commitment,
its owner, its date and its state, with the late ones counted
read-accounts -> build-pack [account-movement]: what moved on each
named account, dated
build-pack -> send-pack [review-pack]: the pack at a version, with
every number naming where it came from
send-pack -> hold-review [pack-receipts]: the pack, and who on each
side received it and when
hold-review -> name-gaps [what-was-said]: what both sides said about
each measure, including the numbers nobody defended
name-gaps -> decide-changes [gaps-and-reasons]: every measure behind
target, its reason, and the person closest to it
decide-changes -> close-dead [changes-decided]: what changes, and
which commitments the change makes pointless
decide-changes -> write-amendment [sponsor-decisions]: the decisions
as both sponsors announced them
close-dead -> write-amendment [dead-commitments]: the commitments
closed, each with its reason, so the amendment does not carry them
forward
write-amendment -> re-sign [amended-plan]: the new version, with the
changed lines marked against the version they replace
re-sign -> record-decisions [signed-amendment]: the signed amendment,
the signers, and the date. An unsigned change is not recorded as
agreed
record-decisions -> publish-record [tracked-decisions]: the
decisions, the owners and the new dates as they now stand in the
tracker
publish-record -> set-next-review [published-record]: the record at
its address, and who on each side has been given it
deviations:
compare-numbers -> pull-numbers [counted-differently]: the two sides
count a measure differently, so the measure is pulled again with
the definition each side computed to
settle-difference -> pull-numbers [number-cannot-be-sourced]: a
number nobody can source, so the measure goes back to be pulled
from a system that produces it or is marked unsettled
hold-review -> send-pack [pack-not-read]: a side has not read the
pack, so the pack goes out again and the meeting waits for it
name-gaps -> build-pack [gap-not-in-pack]: the pack does not show a
gap the room can see, so the pack is built again around it
decide-changes -> pull-numbers [number-not-brought]: the decision
needs a number nobody brought, so that measure is pulled before the
change is decided
re-sign -> decide-changes [sponsor-will-not-sign]: a sponsor will not
sign the change, so what they objected to goes back to the decision
bindings:
roster: <who holds each role - agents claiming the abstract agents
above, and named people for the partner lead, the sales
leader, the partner's operations contact and the two
executive sponsors>
systems: the CRM (read), the partner record (write),
the commitment tracker (write), the partner portal (read),
the shared plan location (write),
the calendar of every attendee (write), analytics (read)
data: the signed joint plan <version>, the measure definitions it
carries, <your territory map>, the record of the previous
review
policy:
the numbers are settled before the meeting, and a measure the two
sides cannot settle goes into the pack as unsettled rather than as
either side's figure
the pack reaches both sides at least <days> before the meeting, and a
review whose pack was late is rescheduled rather than held blind
every measure behind target is named out loud, and a review that
reports only what went well is not a review
a commitment is met, moved or dead. Nothing stays open by silence
a commitment moved twice is escalated to <who> rather than moved a
third time
a change to the plan is signed by both sponsors before it is recorded
as agreed
<how many> consecutive reviews with no measure met sends the plan to
<who> for a decision on whether the partnership continues
measures:
cycle time: <target> from the review date to the published record
coverage: <target> share of commitments carrying a current state
volume: <reviews per period>
quality gate: no review is held without a settled number for every
measure or a note saying why it is unsettled
```
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
383 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: joint plan review id: <team>/review-a-joint-plan v1
from: ref/prt/review-a-joint-plan v1
owner: <who> effective: <date>
trigger: a review date recorded in a signed joint plan arrives, or
<who> calls a review out of cadence
watch: record=<joint plan>
system=<your shared plan location>
change=<the review date recorded in the signed plan
arrives>
or watch: record=<joint plan>
system=<your shared plan location>
change=<a review is called out of cadence>
concurrency: runs may overlap - <how many> reviews run at once, and one
plan is reviewed by one run at a time
goal: every measure in the plan settled to one number both sides
accept, every commitment marked met, moved or dead, the plan
amended or confirmed at a version, and the next review dated
phases:
open-review - system: the review is opened against the signed
plan and put on the calendar of everyone the plan
names
owner: commitment-keeper after: trigger
by: <days> automation: <level>
pull-numbers - runs collect-and-report: each measure the plan
defined, at today's value, from the system the
plan named for it
owner: analytics after: open-review
by: <days> automation: <level>
compare-numbers - runs assessment: our figure set against the
partner's figure, measure by measure, with the
gap between them shown rather than averaged
owner: analytics after: pull-numbers
by: <days> automation: <level>
settle-difference - human: one number per measure, agreed with <who>
on the partner's side before anybody meets
owner: partner-manager after: compare-numbers
by: <days> automation: <level>
read-commitments - runs roll-call: every commitment in the plan, its
owner, its date, and whether it is met, running,
late or untouched
owner: commitment-keeper after: open-review
automation: <level>
read-accounts - runs collect-and-report: what moved on each named
account since the last review, dated
owner: partner-monitor after: open-review
by: <days> automation: <level>
build-pack - runs build-by-talent: the settled numbers, the
commitments and the gaps, in one pack both sides
will read from
owner: reporting-manager
after: settle-difference + read-commitments +
read-accounts
by: <days> automation: <level>
send-pack - system: the pack goes to both sides at least
<days> before the meeting
owner: reporting-manager after: build-pack
automation: <level>
hold-review - convenes debrief: both sides walk the pack, with
the people the plan named in the room
owner: partner-manager after: send-pack
automation: <level>
name-gaps - human: every measure behind target said out loud,
with the reason and the person closest to it
owner: partner-manager after: hold-review
automation: <level>
decide-changes - convenes decide-and-announce: what changes in the
plan, or that nothing does. <who> decides for our
side and their sponsor decides for theirs
owner: joint-planner after: name-gaps
automation: <level>
close-dead - human: the commitments nobody is going to do are
closed, each with the reason and the date it was
given up on
owner: commitment-keeper after: decide-changes
automation: <level>
write-amendment - runs build-by-talent: the plan rewritten at a new
version, with the changed lines marked against
the version they replace
owner: joint-planner
after: decide-changes + close-dead
by: <days> automation: <level>
re-sign - convenes approval: the sponsors sign the changed
lines, as named signers, against the new version
owner: <your partner leadership role>
after: write-amendment
by: <days> automation: never
record-decisions - system: the decisions, the closed commitments,
the new owners and the new dates, written to the
commitment tracker
owner: commitment-keeper after: re-sign
automation: <level>
publish-record - human: the review record lands at <your shared
location> beside the plan it reviewed
owner: reporting-manager after: record-decisions
by: <days> automation: <level>
set-next-review - human: the next review is dated and on both
calendars, or the plan is called dead and <who>
is told
owner: partner-manager after: publish-record
automation: never
run-scoped:
attendance - runs roll-call owner: partner-manager
every: <cadence>
from: send-pack until: hold-review
gaps - runs collect-and-report owner: analytics
every: <cadence>
from: record-decisions until: the next review opens
handoffs:
open-review -> pull-numbers [plan-and-measures]: the signed plan at
its version, and the measures it defined
open-review -> read-commitments [recorded-commitments]: the same
plan, and every commitment recorded when it was signed
open-review -> read-accounts [named-accounts]: the accounts and
segments the plan named
pull-numbers -> compare-numbers [our-figures]: each measure at its
value, with the system and the date it was read
compare-numbers -> settle-difference [measure-differences]: the gap
between the two sides per measure, with the definition each side
was computing to
settle-difference -> build-pack [settled-numbers]: one number per
measure, and the measures the two sides could not settle, marked as
unsettled rather than dropped
read-commitments -> build-pack [commitment-states]: every commitment,
its owner, its date and its state, with the late ones counted
read-accounts -> build-pack [account-movement]: what moved on each
named account, dated
build-pack -> send-pack [review-pack]: the pack at a version, with
every number naming where it came from
send-pack -> hold-review [pack-receipts]: the pack, and who on each
side received it and when
hold-review -> name-gaps [what-was-said]: what both sides said about
each measure, including the numbers nobody defended
name-gaps -> decide-changes [gaps-and-reasons]: every measure behind
target, its reason, and the person closest to it
decide-changes -> close-dead [changes-decided]: what changes, and
which commitments the change makes pointless
decide-changes -> write-amendment [sponsor-decisions]: the decisions
as both sponsors announced them
close-dead -> write-amendment [dead-commitments]: the commitments
closed, each with its reason, so the amendment does not carry them
forward
write-amendment -> re-sign [amended-plan]: the new version, with the
changed lines marked against the version they replace
re-sign -> record-decisions [signed-amendment]: the signed amendment,
the signers, and the date. An unsigned change is not recorded as
agreed
record-decisions -> publish-record [tracked-decisions]: the
decisions, the owners and the new dates as they now stand in the
tracker
publish-record -> set-next-review [published-record]: the record at
its address, and who on each side has been given it
deviations:
compare-numbers -> pull-numbers [counted-differently]: the two sides
count a measure differently, so the measure is pulled again with
the definition each side computed to
settle-difference -> pull-numbers [number-cannot-be-sourced]: a
number nobody can source, so the measure goes back to be pulled
from a system that produces it or is marked unsettled
hold-review -> send-pack [pack-not-read]: a side has not read the
pack, so the pack goes out again and the meeting waits for it
name-gaps -> build-pack [gap-not-in-pack]: the pack does not show a
gap the room can see, so the pack is built again around it
decide-changes -> pull-numbers [number-not-brought]: the decision
needs a number nobody brought, so that measure is pulled before the
change is decided
re-sign -> decide-changes [sponsor-will-not-sign]: a sponsor will not
sign the change, so what they objected to goes back to the decision
bindings:
roster: <who holds each role - agents claiming the abstract agents
above, and named people for the partner lead, the sales
leader, the partner's operations contact and the two
executive sponsors>
systems: the CRM (read), the partner record (write),
the commitment tracker (write), the partner portal (read),
the shared plan location (write),
the calendar of every attendee (write), analytics (read)
data: the signed joint plan <version>, the measure definitions it
carries, <your territory map>, the record of the previous
review
policy:
the numbers are settled before the meeting, and a measure the two
sides cannot settle goes into the pack as unsettled rather than as
either side's figure
the pack reaches both sides at least <days> before the meeting, and a
review whose pack was late is rescheduled rather than held blind
every measure behind target is named out loud, and a review that
reports only what went well is not a review
a commitment is met, moved or dead. Nothing stays open by silence
a commitment moved twice is escalated to <who> rather than moved a
third time
a change to the plan is signed by both sponsors before it is recorded
as agreed
<how many> consecutive reviews with no measure met sends the plan to
<who> for a decision on whether the partnership continues
measures:
cycle time: <target> from the review date to the published record
coverage: <target> share of commitments carrying a current state
volume: <reviews per period>
quality gate: no review is held without a settled number for every
measure or a note saying why it is unsettled
```
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
374 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: joint plan review id: <team>/review-a-joint-plan v1
from: ref/prt/review-a-joint-plan v1
owner: <who> effective: <date>
trigger: a review date recorded in a signed joint plan arrives, or
<who> calls a review out of cadence
watch: record=<joint plan>
system=<your shared plan location>
change=<the review date recorded in the signed plan
arrives>
or watch: record=<joint plan>
system=<your shared plan location>
change=<a review is called out of cadence>
concurrency: runs may overlap - <how many> reviews run at once, and one
plan is reviewed by one run at a time
goal: every measure in the plan settled to one number both sides
accept, every commitment marked met, moved or dead, the plan
amended or confirmed at a version, and the next review dated
phases:
open-review - system: the review is opened against the signed
plan and put on the calendar of everyone the plan
names
owner: commitment-keeper after: trigger
by: <days> automation: <level>
pull-numbers - runs collect-and-report: each measure the plan
defined, at today's value, from the system the
plan named for it
owner: analytics after: open-review
by: <days> automation: <level>
compare-numbers - runs assessment: our figure set against the
partner's figure, measure by measure, with the
gap between them shown rather than averaged
owner: analytics after: pull-numbers
by: <days> automation: <level>
settle-difference - human: one number per measure, agreed with <who>
on the partner's side before anybody meets
owner: partner-manager after: compare-numbers
by: <days> automation: <level>
read-commitments - runs roll-call: every commitment in the plan, its
owner, its date, and whether it is met, running,
late or untouched
owner: commitment-keeper after: open-review
automation: <level>
read-accounts - runs collect-and-report: what moved on each named
account since the last review, dated
owner: partner-monitor after: open-review
by: <days> automation: <level>
build-pack - runs build-by-talent: the settled numbers, the
commitments and the gaps, in one pack both sides
will read from
owner: reporting-manager
after: settle-difference + read-commitments +
read-accounts
by: <days> automation: <level>
send-pack - system: the pack goes to both sides at least
<days> before the meeting
owner: reporting-manager after: build-pack
automation: <level>
hold-review - convenes debrief: both sides walk the pack, with
the people the plan named in the room
owner: partner-manager after: send-pack
automation: <level>
name-gaps - human: every measure behind target said out loud,
with the reason and the person closest to it
owner: partner-manager after: hold-review
automation: <level>
decide-changes - convenes decide-and-announce: what changes in the
plan, or that nothing does. <who> decides for our
side and their sponsor decides for theirs
owner: joint-planner after: name-gaps
automation: <level>
close-dead - human: the commitments nobody is going to do are
closed, each with the reason and the date it was
given up on
owner: commitment-keeper after: decide-changes
automation: <level>
write-amendment - runs build-by-talent: the plan rewritten at a new
version, with the changed lines marked against
the version they replace
owner: joint-planner
after: decide-changes + close-dead
by: <days> automation: <level>
re-sign - convenes approval: the sponsors sign the changed
lines, as named signers, against the new version
owner: <your partner leadership role>
after: write-amendment
by: <days> automation: never
record-decisions - system: the decisions, the closed commitments,
the new owners and the new dates, written to the
commitment tracker
owner: commitment-keeper after: re-sign
automation: <level>
publish-record - human: the review record lands at <your shared
location> beside the plan it reviewed
owner: reporting-manager after: record-decisions
by: <days> automation: <level>
set-next-review - human: the next review is dated and on both
calendars, or the plan is called dead and <who>
is told
owner: partner-manager after: publish-record
automation: never
run-scoped:
attendance - runs roll-call owner: partner-manager
every: <cadence>
from: send-pack until: hold-review
gaps - runs collect-and-report owner: analytics
every: <cadence>
from: record-decisions until: the next review opens
handoffs:
open-review -> pull-numbers [plan-and-measures]: the signed plan at
its version, and the measures it defined
open-review -> read-commitments [recorded-commitments]: the same
plan, and every commitment recorded when it was signed
open-review -> read-accounts [named-accounts]: the accounts and
segments the plan named
pull-numbers -> compare-numbers [our-figures]: each measure at its
value, with the system and the date it was read
compare-numbers -> settle-difference [measure-differences]: the gap
between the two sides per measure, with the definition each side
was computing to
settle-difference -> build-pack [settled-numbers]: one number per
measure, and the measures the two sides could not settle, marked as
unsettled rather than dropped
read-commitments -> build-pack [commitment-states]: every commitment,
its owner, its date and its state, with the late ones counted
read-accounts -> build-pack [account-movement]: what moved on each
named account, dated
build-pack -> send-pack [review-pack]: the pack at a version, with
every number naming where it came from
send-pack -> hold-review [pack-receipts]: the pack, and who on each
side received it and when
hold-review -> name-gaps [what-was-said]: what both sides said about
each measure, including the numbers nobody defended
name-gaps -> decide-changes [gaps-and-reasons]: every measure behind
target, its reason, and the person closest to it
decide-changes -> close-dead [changes-decided]: what changes, and
which commitments the change makes pointless
decide-changes -> write-amendment [sponsor-decisions]: the decisions
as both sponsors announced them
close-dead -> write-amendment [dead-commitments]: the commitments
closed, each with its reason, so the amendment does not carry them
forward
write-amendment -> re-sign [amended-plan]: the new version, with the
changed lines marked against the version they replace
re-sign -> record-decisions [signed-amendment]: the signed amendment,
the signers, and the date. An unsigned change is not recorded as
agreed
record-decisions -> publish-record [tracked-decisions]: the
decisions, the owners and the new dates as they now stand in the
tracker
publish-record -> set-next-review [published-record]: the record at
its address, and who on each side has been given it
deviations:
compare-numbers -> pull-numbers [counted-differently]: the two sides
count a measure differently, so the measure is pulled again with
the definition each side computed to
settle-difference -> pull-numbers [number-cannot-be-sourced]: a
number nobody can source, so the measure goes back to be pulled
from a system that produces it or is marked unsettled
hold-review -> send-pack [pack-not-read]: a side has not read the
pack, so the pack goes out again and the meeting waits for it
name-gaps -> build-pack [gap-not-in-pack]: the pack does not show a
gap the room can see, so the pack is built again around it
decide-changes -> pull-numbers [number-not-brought]: the decision
needs a number nobody brought, so that measure is pulled before the
change is decided
re-sign -> decide-changes [sponsor-will-not-sign]: a sponsor will not
sign the change, so what they objected to goes back to the decision
bindings:
roster: <who holds each role - agents claiming the abstract agents
above, and named people for the partner lead, the sales
leader, the partner's operations contact and the two
executive sponsors>
systems: the CRM (read), the partner record (write),
the commitment tracker (write), the partner portal (read),
the shared plan location (write),
the calendar of every attendee (write), analytics (read)
data: the signed joint plan <version>, the measure definitions it
carries, <your territory map>, the record of the previous
review
policy:
the numbers are settled before the meeting, and a measure the two
sides cannot settle goes into the pack as unsettled rather than as
either side's figure
the pack reaches both sides at least <days> before the meeting, and a
review whose pack was late is rescheduled rather than held blind
every measure behind target is named out loud, and a review that
reports only what went well is not a review
a commitment is met, moved or dead. Nothing stays open by silence
a commitment moved twice is escalated to <who> rather than moved a
third time
a change to the plan is signed by both sponsors before it is recorded
as agreed
<how many> consecutive reviews with no measure met sends the plan to
<who> for a decision on whether the partnership continues
measures:
cycle time: <target> from the review date to the published record
coverage: <target> share of commitments carrying a current state
volume: <reviews per period>
quality gate: no review is held without a settled number for every
measure or a note saying why it is unsettled
```
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
50 blanks to fill. Everything else is the process.
this process
from: ref/prt/review-a-joint-plan 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.