Catalog / Business processes / Partners / Prospect-to-Partner / Sign a Partner Agreement
reference process · partners · 17 activities · 9 on the roster
Sign a Partner Agreement
A candidate has been qualified and both sides want to work together. This process writes the terms that govern that, negotiates them, and gets them signed. The conditions the qualification attached to the candidate are carried into the paper as obligations rather than left in a report nobody reads again. Concessions are approved inside the company before they are offered. The final text is read against the agreed list term by term before anyone signs. What leaves the run is an executed agreement, filed, with the people who have to work it holding the same version.
The walk
The document
One run
Adoption
The activities
What happens in a run
17 activities from a qualified candidate and the company agree to paper the deal to an executed agreement, filed, held by everyone who works it, 5 of them gates a person has to sign. Drag the diagram to move along it.
Sign a Partner Agreement a qualified candidate and the company agree to paper the deal → an executed agreement, filed, held by everyone who works it
the draft drops a condition the markup is not the whole of it a concession is refused inside an ask sits below the floor the paper does not say what was agreed the screening finds something new a signer will not sign as drafted a qualified candidate and the company agree to paper the deal 1 Take in the Qualified Can… the decision, the conditions and the evidence 2 Set What the Agreement Mu… the rights given and the duties owed, both ways 3 Carry the Conditions Acro… every qualification condition becomes a term 4 Choose the Paper to Start… which template, which schedules, which country a person signs · never an agent 5 Set the Terms and the Flo… margin, fees, targets, and what we will not go below a person signs · never an agent 6 Draft the Agreement the first full draft, with its schedules attached 7 Review It Before It Goes … legal, finance and the partner lead read it first a person signs · never an agent 8 Send the Draft and Take t… the draft goes out at a version and comes back 9 List Every Change They As… the markup gathered into one numbered list 10 Price and Sort the Changes each change marked give, trade or refuse 11 Approve the Concessions I… cleared inside before any of it is offered a person signs · never an agent 12 Negotiate the Open Terms the list worked through with the partner 13 Settle the Schedules territory, products, targets, support and prices 14 Check the Paper Against t… the final text read against the agreed list 15 Clear the Partner for Sig… the entity that signs is screened once more 16 Sign the Agreement both sides sign, in the order the paper sets a person signs · never an agent 17 Record It and Hand It On the executed copy filed and given to the people an executed agreement, filed, held by everyone who works it
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.
Use in LangGraph
Use in Agent Framework
Use in CrewAI
Use in Google ADK
PROCESS: sign a partner agreement id: <team> /sign-a-partner-agreement v1
from: ref/prt/sign-a-partner-agreement v1
owner: <who> effective: <date>
trigger: a candidate is marked qualified in <your partner record> and
both sides agree to paper the relationship
watch: record=<candidate> system=<your partner record>
change=<a candidate is marked qualified and both sides
agree to paper the relationship>
concurrency: runs may overlap - <how many> agreements live at once,
and one partner is papered by one run at a time
goal: an executed agreement whose terms match the agreed list line for
line, every qualification condition written in as an obligation,
and every concession carrying a named approver
phases:
take-in-candidate - human: read the qualification decision, the
conditions attached to it, and the evidence
behind both
owner: agreement-writer after: trigger
automation: <level>
set-what-it-does - convenes decide-and-announce: what each side
may do, must do and may not do, written before
any template is opened
owner: <your partner leadership role>
after: take-in-candidate
by: <days> automation: <level>
carry-conditions - human: every condition the qualification
attached, rewritten as a term with a date, a
measure and a consequence
owner: agreement-writer
after: set-what-it-does automation: <level>
choose-paper - convenes decide-and-announce: which template,
which schedules, which country's law, and what
the partner's own paper may not replace
owner: <your legal role>
after: set-what-it-does
by: <days> automation: never
set-commercials - convenes decide-and-announce: margin, fees,
targets, payment terms, and the floor below
which <who> refuses to sign
owner: <your finance role>
after: set-what-it-does
by: <days> automation: never
draft - runs build-by-talent: the full draft with its
schedules, every term traceable to the agreed
list or to the template
owner: agreement-writer
after: carry-conditions + choose-paper +
set-commercials
by: <days> automation: <level>
review-inside - convenes approval: legal, finance and the
partner lead sign the draft as named signers
before it leaves the company
owner: <your legal role> after: draft
by: <days> automation: never
send-and-take-markup - human: the draft goes to the partner at a
version, and their markup comes back against
that same version
owner: partner-manager after: review-inside
by: <days> automation: <level>
list-changes - runs collect-and-report: every requested
change gathered into one numbered list, in the
partner's own wording, clause by clause
owner: agreement-writer
after: send-and-take-markup
by: <days> automation: <level>
price-and-sort - runs assessment: each change marked give,
trade or refuse, with what it costs and what
we ask for in return
owner: agreement-writer after: list-changes
by: <days> automation: <level>
approve-concessions - convenes approval: the give and trade list
signed inside, by the people whose numbers it
moves, before any of it is offered
owner: <your finance role>
after: price-and-sort
by: <days> automation: never
negotiate-open-terms - human: the numbered list worked through with
the partner, against the approved positions
and the floor
owner: <your partner leadership role>
after: approve-concessions
automation: <level>
settle-schedules - convenes decide-and-announce: territory,
products, targets, support duties and prices,
each agreed by the person who owns it
owner: partner-manager
after: negotiate-open-terms
by: <days> automation: <level>
check-paper - runs assessment: the final text read against
the agreed list term by term, and every
difference named
owner: agreement-writer
after: settle-schedules
by: <days> automation: <level>
clear-for-signature - runs assessment: the entity that will sign
screened again, and its signing authority
confirmed against <your screening service>
owner: supplier-check after: check-paper
by: <days> automation: <level>
sign - convenes approval: both sides sign, in the
order the paper sets, and each signature is
dated and kept
owner: <your signing authority>
after: clear-for-signature
by: <days> automation: never
record-and-hand-on - human: the executed copy filed, the terms
written into the partner record, and the
people who must work them told
owner: partner-manager after: sign
by: <days> automation: <level>
run-scoped:
concessions - runs allocate-and-reconcile
owner: agreement-writer
from: price-and-sort until: run close
status - runs roll-call
owner: partner-manager
every: <cadence>
from: send-and-take-markup until: run close
handoffs:
take-in-candidate -> set-what-it-does [qualification-decision]: the
qualification decision, the conditions attached to it, and the
claims left unproven
set-what-it-does -> carry-conditions [rights-and-duties]: what each
side may do, must do and may not do, at a version both our own
people hold
set-what-it-does -> choose-paper [agreement-purpose]: the same
statement, so the template is picked for the relationship rather
than out of habit
set-what-it-does -> set-commercials [duties-taken-on]: the duties
each side takes on, so the money is set against real obligations
carry-conditions -> draft [conditions-as-terms]: every condition as a
term, with the date it bites, the measure it is read against, and
what happens if it is missed
choose-paper -> draft [template-and-schedules]: the template at a
version, the schedules it needs, and the clauses that may not be
changed
set-commercials -> draft [commercial-terms]: margin, fees, targets,
payment terms, and the floor, with the person who set the floor
named
draft -> review-inside [first-draft]: the full draft, every term
traced to the agreed list or to the template it came from
review-inside -> send-and-take-markup [approved-draft]: the draft at
the signed internal version, and the reviewers who signed it
send-and-take-markup -> list-changes [partner-markup]: the partner's
markup, against the version it was sent at, with the date it came
back
list-changes -> price-and-sort [numbered-changes]: every requested
change numbered, in the partner's own words, clause by clause
price-and-sort -> approve-concessions [change-costing]: what each
change costs, who carries it, and what we ask for in return
approve-concessions -> negotiate-open-terms [approved-positions]: the
approved give and trade positions, each with its approver and the
date
negotiate-open-terms -> settle-schedules [closed-changes]: every
change closed as given, traded or refused, with the person on each
side who agreed
settle-schedules -> check-paper [settled-schedules]: the schedules as
settled, each naming the person who owns the number in it
check-paper -> clear-for-signature [text-against-agreed]: the final
text, the agreed list, and every difference between the two
clear-for-signature -> sign [signing-entity-cleared]: the entity that
signs, its screening result at a date, and the person confirmed to
sign for it
sign -> record-and-hand-on [executed-agreement]: the executed
agreement, the signatures with their dates, and the version that
was signed
deviations:
review-inside -> draft [condition-dropped]: the draft drops a
qualification condition, so it is drafted again with the condition
written in or with a named decision to drop it
list-changes -> send-and-take-markup [markup-incomplete]: the markup
is not the whole of what they want changed, so it goes back for a
complete markup against the version that was sent
approve-concessions -> price-and-sort [concession-refused]: an
approver refuses a concession, so the change is priced and sorted
again against the floor
negotiate-open-terms -> set-commercials [ask-below-floor]: an ask
sits below the floor, so the floor and the commercial terms are set
again before anything is offered
check-paper -> negotiate-open-terms [paper-disagrees]: the final text
and the agreed list differ, so the difference goes back to the
table rather than into the drafting
clear-for-signature -> negotiate-open-terms [screening-finds-new]:
the screening before signature finds something new, so signature is
held and the terms are worked again
sign -> negotiate-open-terms [signer-will-not-sign]: a signer will
not sign as drafted, so the terms behind the refusal go back to the
table
bindings:
roster: <who holds each role - agents claiming the abstract agents
above, and named people for the partner lead, the legal
reviewer, the finance partner, the sales leader and the
person who signs>
systems: the contract system (write), the partner record (write),
the signing service (write), the approval system (write),
<your screening service> (read),
the pricing model (read, cap: <n> margin),
the shared workspace with the partner (write)
data: <your partner agreement template> <version> , <your standard
terms> <version> , <your margin policy> <version> , the
qualification decision and its conditions, the agreed list
policy:
every condition the qualification attached appears in the agreement
as a term with a date and a consequence, or the run records who
decided to drop it
no concession is offered to the partner before it is approved
inside, and the approval names a person
a term below the floor is refused, and only <who> may move the floor
the draft that goes out is a version, and a markup against any other
version goes back for a fresh markup
legal and finance review is a human gate and is never delegated to
an agent
nothing is signed while the final text and the agreed list differ on
any term
the screening runs again on the entity that actually signs, within
<days> of signature
the executed copy is filed within <days> , and the terms that other
processes rely on are written into the partner record
measures:
cycle time: <target> from a qualified candidate to an executed
agreement
drift: <target> for the gap between the draft as sent and the
agreement as signed
volume: <agreements per period>
quality gate: no agreement is executed with an unapproved concession
in it or a qualification condition missing from it
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
349 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: sign a partner agreement id: <team>/sign-a-partner-agreement v1
from: ref/prt/sign-a-partner-agreement v1
owner: <who> effective: <date>
trigger: a candidate is marked qualified in <your partner record> and
both sides agree to paper the relationship
watch: record=<candidate> system=<your partner record>
change=<a candidate is marked qualified and both sides
agree to paper the relationship>
concurrency: runs may overlap - <how many> agreements live at once,
and one partner is papered by one run at a time
goal: an executed agreement whose terms match the agreed list line for
line, every qualification condition written in as an obligation,
and every concession carrying a named approver
phases:
take-in-candidate - human: read the qualification decision, the
conditions attached to it, and the evidence
behind both
owner: agreement-writer after: trigger
automation: <level>
set-what-it-does - convenes decide-and-announce: what each side
may do, must do and may not do, written before
any template is opened
owner: <your partner leadership role>
after: take-in-candidate
by: <days> automation: <level>
carry-conditions - human: every condition the qualification
attached, rewritten as a term with a date, a
measure and a consequence
owner: agreement-writer
after: set-what-it-does automation: <level>
choose-paper - convenes decide-and-announce: which template,
which schedules, which country's law, and what
the partner's own paper may not replace
owner: <your legal role>
after: set-what-it-does
by: <days> automation: never
set-commercials - convenes decide-and-announce: margin, fees,
targets, payment terms, and the floor below
which <who> refuses to sign
owner: <your finance role>
after: set-what-it-does
by: <days> automation: never
draft - runs build-by-talent: the full draft with its
schedules, every term traceable to the agreed
list or to the template
owner: agreement-writer
after: carry-conditions + choose-paper +
set-commercials
by: <days> automation: <level>
review-inside - convenes approval: legal, finance and the
partner lead sign the draft as named signers
before it leaves the company
owner: <your legal role> after: draft
by: <days> automation: never
send-and-take-markup - human: the draft goes to the partner at a
version, and their markup comes back against
that same version
owner: partner-manager after: review-inside
by: <days> automation: <level>
list-changes - runs collect-and-report: every requested
change gathered into one numbered list, in the
partner's own wording, clause by clause
owner: agreement-writer
after: send-and-take-markup
by: <days> automation: <level>
price-and-sort - runs assessment: each change marked give,
trade or refuse, with what it costs and what
we ask for in return
owner: agreement-writer after: list-changes
by: <days> automation: <level>
approve-concessions - convenes approval: the give and trade list
signed inside, by the people whose numbers it
moves, before any of it is offered
owner: <your finance role>
after: price-and-sort
by: <days> automation: never
negotiate-open-terms - human: the numbered list worked through with
the partner, against the approved positions
and the floor
owner: <your partner leadership role>
after: approve-concessions
automation: <level>
settle-schedules - convenes decide-and-announce: territory,
products, targets, support duties and prices,
each agreed by the person who owns it
owner: partner-manager
after: negotiate-open-terms
by: <days> automation: <level>
check-paper - runs assessment: the final text read against
the agreed list term by term, and every
difference named
owner: agreement-writer
after: settle-schedules
by: <days> automation: <level>
clear-for-signature - runs assessment: the entity that will sign
screened again, and its signing authority
confirmed against <your screening service>
owner: supplier-check after: check-paper
by: <days> automation: <level>
sign - convenes approval: both sides sign, in the
order the paper sets, and each signature is
dated and kept
owner: <your signing authority>
after: clear-for-signature
by: <days> automation: never
record-and-hand-on - human: the executed copy filed, the terms
written into the partner record, and the
people who must work them told
owner: partner-manager after: sign
by: <days> automation: <level>
run-scoped:
concessions - runs allocate-and-reconcile
owner: agreement-writer
from: price-and-sort until: run close
status - runs roll-call
owner: partner-manager
every: <cadence>
from: send-and-take-markup until: run close
handoffs:
take-in-candidate -> set-what-it-does [qualification-decision]: the
qualification decision, the conditions attached to it, and the
claims left unproven
set-what-it-does -> carry-conditions [rights-and-duties]: what each
side may do, must do and may not do, at a version both our own
people hold
set-what-it-does -> choose-paper [agreement-purpose]: the same
statement, so the template is picked for the relationship rather
than out of habit
set-what-it-does -> set-commercials [duties-taken-on]: the duties
each side takes on, so the money is set against real obligations
carry-conditions -> draft [conditions-as-terms]: every condition as a
term, with the date it bites, the measure it is read against, and
what happens if it is missed
choose-paper -> draft [template-and-schedules]: the template at a
version, the schedules it needs, and the clauses that may not be
changed
set-commercials -> draft [commercial-terms]: margin, fees, targets,
payment terms, and the floor, with the person who set the floor
named
draft -> review-inside [first-draft]: the full draft, every term
traced to the agreed list or to the template it came from
review-inside -> send-and-take-markup [approved-draft]: the draft at
the signed internal version, and the reviewers who signed it
send-and-take-markup -> list-changes [partner-markup]: the partner's
markup, against the version it was sent at, with the date it came
back
list-changes -> price-and-sort [numbered-changes]: every requested
change numbered, in the partner's own words, clause by clause
price-and-sort -> approve-concessions [change-costing]: what each
change costs, who carries it, and what we ask for in return
approve-concessions -> negotiate-open-terms [approved-positions]: the
approved give and trade positions, each with its approver and the
date
negotiate-open-terms -> settle-schedules [closed-changes]: every
change closed as given, traded or refused, with the person on each
side who agreed
settle-schedules -> check-paper [settled-schedules]: the schedules as
settled, each naming the person who owns the number in it
check-paper -> clear-for-signature [text-against-agreed]: the final
text, the agreed list, and every difference between the two
clear-for-signature -> sign [signing-entity-cleared]: the entity that
signs, its screening result at a date, and the person confirmed to
sign for it
sign -> record-and-hand-on [executed-agreement]: the executed
agreement, the signatures with their dates, and the version that
was signed
deviations:
review-inside -> draft [condition-dropped]: the draft drops a
qualification condition, so it is drafted again with the condition
written in or with a named decision to drop it
list-changes -> send-and-take-markup [markup-incomplete]: the markup
is not the whole of what they want changed, so it goes back for a
complete markup against the version that was sent
approve-concessions -> price-and-sort [concession-refused]: an
approver refuses a concession, so the change is priced and sorted
again against the floor
negotiate-open-terms -> set-commercials [ask-below-floor]: an ask
sits below the floor, so the floor and the commercial terms are set
again before anything is offered
check-paper -> negotiate-open-terms [paper-disagrees]: the final text
and the agreed list differ, so the difference goes back to the
table rather than into the drafting
clear-for-signature -> negotiate-open-terms [screening-finds-new]:
the screening before signature finds something new, so signature is
held and the terms are worked again
sign -> negotiate-open-terms [signer-will-not-sign]: a signer will
not sign as drafted, so the terms behind the refusal go back to the
table
bindings:
roster: <who holds each role - agents claiming the abstract agents
above, and named people for the partner lead, the legal
reviewer, the finance partner, the sales leader and the
person who signs>
systems: the contract system (write), the partner record (write),
the signing service (write), the approval system (write),
<your screening service> (read),
the pricing model (read, cap: <n> margin),
the shared workspace with the partner (write)
data: <your partner agreement template> <version>, <your standard
terms> <version>, <your margin policy> <version>, the
qualification decision and its conditions, the agreed list
policy:
every condition the qualification attached appears in the agreement
as a term with a date and a consequence, or the run records who
decided to drop it
no concession is offered to the partner before it is approved
inside, and the approval names a person
a term below the floor is refused, and only <who> may move the floor
the draft that goes out is a version, and a markup against any other
version goes back for a fresh markup
legal and finance review is a human gate and is never delegated to
an agent
nothing is signed while the final text and the agreed list differ on
any term
the screening runs again on the entity that actually signs, within
<days> of signature
the executed copy is filed within <days>, and the terms that other
processes rely on are written into the partner record
measures:
cycle time: <target> from a qualified candidate to an executed
agreement
drift: <target> for the gap between the draft as sent and the
agreement as signed
volume: <agreements per period>
quality gate: no agreement is executed with an unapproved concession
in it or a qualification condition missing from it
```
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
404 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: sign a partner agreement id: <team>/sign-a-partner-agreement v1
from: ref/prt/sign-a-partner-agreement v1
owner: <who> effective: <date>
trigger: a candidate is marked qualified in <your partner record> and
both sides agree to paper the relationship
watch: record=<candidate> system=<your partner record>
change=<a candidate is marked qualified and both sides
agree to paper the relationship>
concurrency: runs may overlap - <how many> agreements live at once,
and one partner is papered by one run at a time
goal: an executed agreement whose terms match the agreed list line for
line, every qualification condition written in as an obligation,
and every concession carrying a named approver
phases:
take-in-candidate - human: read the qualification decision, the
conditions attached to it, and the evidence
behind both
owner: agreement-writer after: trigger
automation: <level>
set-what-it-does - convenes decide-and-announce: what each side
may do, must do and may not do, written before
any template is opened
owner: <your partner leadership role>
after: take-in-candidate
by: <days> automation: <level>
carry-conditions - human: every condition the qualification
attached, rewritten as a term with a date, a
measure and a consequence
owner: agreement-writer
after: set-what-it-does automation: <level>
choose-paper - convenes decide-and-announce: which template,
which schedules, which country's law, and what
the partner's own paper may not replace
owner: <your legal role>
after: set-what-it-does
by: <days> automation: never
set-commercials - convenes decide-and-announce: margin, fees,
targets, payment terms, and the floor below
which <who> refuses to sign
owner: <your finance role>
after: set-what-it-does
by: <days> automation: never
draft - runs build-by-talent: the full draft with its
schedules, every term traceable to the agreed
list or to the template
owner: agreement-writer
after: carry-conditions + choose-paper +
set-commercials
by: <days> automation: <level>
review-inside - convenes approval: legal, finance and the
partner lead sign the draft as named signers
before it leaves the company
owner: <your legal role> after: draft
by: <days> automation: never
send-and-take-markup - human: the draft goes to the partner at a
version, and their markup comes back against
that same version
owner: partner-manager after: review-inside
by: <days> automation: <level>
list-changes - runs collect-and-report: every requested
change gathered into one numbered list, in the
partner's own wording, clause by clause
owner: agreement-writer
after: send-and-take-markup
by: <days> automation: <level>
price-and-sort - runs assessment: each change marked give,
trade or refuse, with what it costs and what
we ask for in return
owner: agreement-writer after: list-changes
by: <days> automation: <level>
approve-concessions - convenes approval: the give and trade list
signed inside, by the people whose numbers it
moves, before any of it is offered
owner: <your finance role>
after: price-and-sort
by: <days> automation: never
negotiate-open-terms - human: the numbered list worked through with
the partner, against the approved positions
and the floor
owner: <your partner leadership role>
after: approve-concessions
automation: <level>
settle-schedules - convenes decide-and-announce: territory,
products, targets, support duties and prices,
each agreed by the person who owns it
owner: partner-manager
after: negotiate-open-terms
by: <days> automation: <level>
check-paper - runs assessment: the final text read against
the agreed list term by term, and every
difference named
owner: agreement-writer
after: settle-schedules
by: <days> automation: <level>
clear-for-signature - runs assessment: the entity that will sign
screened again, and its signing authority
confirmed against <your screening service>
owner: supplier-check after: check-paper
by: <days> automation: <level>
sign - convenes approval: both sides sign, in the
order the paper sets, and each signature is
dated and kept
owner: <your signing authority>
after: clear-for-signature
by: <days> automation: never
record-and-hand-on - human: the executed copy filed, the terms
written into the partner record, and the
people who must work them told
owner: partner-manager after: sign
by: <days> automation: <level>
run-scoped:
concessions - runs allocate-and-reconcile
owner: agreement-writer
from: price-and-sort until: run close
status - runs roll-call
owner: partner-manager
every: <cadence>
from: send-and-take-markup until: run close
handoffs:
take-in-candidate -> set-what-it-does [qualification-decision]: the
qualification decision, the conditions attached to it, and the
claims left unproven
set-what-it-does -> carry-conditions [rights-and-duties]: what each
side may do, must do and may not do, at a version both our own
people hold
set-what-it-does -> choose-paper [agreement-purpose]: the same
statement, so the template is picked for the relationship rather
than out of habit
set-what-it-does -> set-commercials [duties-taken-on]: the duties
each side takes on, so the money is set against real obligations
carry-conditions -> draft [conditions-as-terms]: every condition as a
term, with the date it bites, the measure it is read against, and
what happens if it is missed
choose-paper -> draft [template-and-schedules]: the template at a
version, the schedules it needs, and the clauses that may not be
changed
set-commercials -> draft [commercial-terms]: margin, fees, targets,
payment terms, and the floor, with the person who set the floor
named
draft -> review-inside [first-draft]: the full draft, every term
traced to the agreed list or to the template it came from
review-inside -> send-and-take-markup [approved-draft]: the draft at
the signed internal version, and the reviewers who signed it
send-and-take-markup -> list-changes [partner-markup]: the partner's
markup, against the version it was sent at, with the date it came
back
list-changes -> price-and-sort [numbered-changes]: every requested
change numbered, in the partner's own words, clause by clause
price-and-sort -> approve-concessions [change-costing]: what each
change costs, who carries it, and what we ask for in return
approve-concessions -> negotiate-open-terms [approved-positions]: the
approved give and trade positions, each with its approver and the
date
negotiate-open-terms -> settle-schedules [closed-changes]: every
change closed as given, traded or refused, with the person on each
side who agreed
settle-schedules -> check-paper [settled-schedules]: the schedules as
settled, each naming the person who owns the number in it
check-paper -> clear-for-signature [text-against-agreed]: the final
text, the agreed list, and every difference between the two
clear-for-signature -> sign [signing-entity-cleared]: the entity that
signs, its screening result at a date, and the person confirmed to
sign for it
sign -> record-and-hand-on [executed-agreement]: the executed
agreement, the signatures with their dates, and the version that
was signed
deviations:
review-inside -> draft [condition-dropped]: the draft drops a
qualification condition, so it is drafted again with the condition
written in or with a named decision to drop it
list-changes -> send-and-take-markup [markup-incomplete]: the markup
is not the whole of what they want changed, so it goes back for a
complete markup against the version that was sent
approve-concessions -> price-and-sort [concession-refused]: an
approver refuses a concession, so the change is priced and sorted
again against the floor
negotiate-open-terms -> set-commercials [ask-below-floor]: an ask
sits below the floor, so the floor and the commercial terms are set
again before anything is offered
check-paper -> negotiate-open-terms [paper-disagrees]: the final text
and the agreed list differ, so the difference goes back to the
table rather than into the drafting
clear-for-signature -> negotiate-open-terms [screening-finds-new]:
the screening before signature finds something new, so signature is
held and the terms are worked again
sign -> negotiate-open-terms [signer-will-not-sign]: a signer will
not sign as drafted, so the terms behind the refusal go back to the
table
bindings:
roster: <who holds each role - agents claiming the abstract agents
above, and named people for the partner lead, the legal
reviewer, the finance partner, the sales leader and the
person who signs>
systems: the contract system (write), the partner record (write),
the signing service (write), the approval system (write),
<your screening service> (read),
the pricing model (read, cap: <n> margin),
the shared workspace with the partner (write)
data: <your partner agreement template> <version>, <your standard
terms> <version>, <your margin policy> <version>, the
qualification decision and its conditions, the agreed list
policy:
every condition the qualification attached appears in the agreement
as a term with a date and a consequence, or the run records who
decided to drop it
no concession is offered to the partner before it is approved
inside, and the approval names a person
a term below the floor is refused, and only <who> may move the floor
the draft that goes out is a version, and a markup against any other
version goes back for a fresh markup
legal and finance review is a human gate and is never delegated to
an agent
nothing is signed while the final text and the agreed list differ on
any term
the screening runs again on the entity that actually signs, within
<days> of signature
the executed copy is filed within <days>, and the terms that other
processes rely on are written into the partner record
measures:
cycle time: <target> from a qualified candidate to an executed
agreement
drift: <target> for the gap between the draft as sent and the
agreement as signed
volume: <agreements per period>
quality gate: no agreement is executed with an unapproved concession
in it or a qualification condition missing from it
```
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
409 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: sign a partner agreement id: <team>/sign-a-partner-agreement v1
from: ref/prt/sign-a-partner-agreement v1
owner: <who> effective: <date>
trigger: a candidate is marked qualified in <your partner record> and
both sides agree to paper the relationship
watch: record=<candidate> system=<your partner record>
change=<a candidate is marked qualified and both sides
agree to paper the relationship>
concurrency: runs may overlap - <how many> agreements live at once,
and one partner is papered by one run at a time
goal: an executed agreement whose terms match the agreed list line for
line, every qualification condition written in as an obligation,
and every concession carrying a named approver
phases:
take-in-candidate - human: read the qualification decision, the
conditions attached to it, and the evidence
behind both
owner: agreement-writer after: trigger
automation: <level>
set-what-it-does - convenes decide-and-announce: what each side
may do, must do and may not do, written before
any template is opened
owner: <your partner leadership role>
after: take-in-candidate
by: <days> automation: <level>
carry-conditions - human: every condition the qualification
attached, rewritten as a term with a date, a
measure and a consequence
owner: agreement-writer
after: set-what-it-does automation: <level>
choose-paper - convenes decide-and-announce: which template,
which schedules, which country's law, and what
the partner's own paper may not replace
owner: <your legal role>
after: set-what-it-does
by: <days> automation: never
set-commercials - convenes decide-and-announce: margin, fees,
targets, payment terms, and the floor below
which <who> refuses to sign
owner: <your finance role>
after: set-what-it-does
by: <days> automation: never
draft - runs build-by-talent: the full draft with its
schedules, every term traceable to the agreed
list or to the template
owner: agreement-writer
after: carry-conditions + choose-paper +
set-commercials
by: <days> automation: <level>
review-inside - convenes approval: legal, finance and the
partner lead sign the draft as named signers
before it leaves the company
owner: <your legal role> after: draft
by: <days> automation: never
send-and-take-markup - human: the draft goes to the partner at a
version, and their markup comes back against
that same version
owner: partner-manager after: review-inside
by: <days> automation: <level>
list-changes - runs collect-and-report: every requested
change gathered into one numbered list, in the
partner's own wording, clause by clause
owner: agreement-writer
after: send-and-take-markup
by: <days> automation: <level>
price-and-sort - runs assessment: each change marked give,
trade or refuse, with what it costs and what
we ask for in return
owner: agreement-writer after: list-changes
by: <days> automation: <level>
approve-concessions - convenes approval: the give and trade list
signed inside, by the people whose numbers it
moves, before any of it is offered
owner: <your finance role>
after: price-and-sort
by: <days> automation: never
negotiate-open-terms - human: the numbered list worked through with
the partner, against the approved positions
and the floor
owner: <your partner leadership role>
after: approve-concessions
automation: <level>
settle-schedules - convenes decide-and-announce: territory,
products, targets, support duties and prices,
each agreed by the person who owns it
owner: partner-manager
after: negotiate-open-terms
by: <days> automation: <level>
check-paper - runs assessment: the final text read against
the agreed list term by term, and every
difference named
owner: agreement-writer
after: settle-schedules
by: <days> automation: <level>
clear-for-signature - runs assessment: the entity that will sign
screened again, and its signing authority
confirmed against <your screening service>
owner: supplier-check after: check-paper
by: <days> automation: <level>
sign - convenes approval: both sides sign, in the
order the paper sets, and each signature is
dated and kept
owner: <your signing authority>
after: clear-for-signature
by: <days> automation: never
record-and-hand-on - human: the executed copy filed, the terms
written into the partner record, and the
people who must work them told
owner: partner-manager after: sign
by: <days> automation: <level>
run-scoped:
concessions - runs allocate-and-reconcile
owner: agreement-writer
from: price-and-sort until: run close
status - runs roll-call
owner: partner-manager
every: <cadence>
from: send-and-take-markup until: run close
handoffs:
take-in-candidate -> set-what-it-does [qualification-decision]: the
qualification decision, the conditions attached to it, and the
claims left unproven
set-what-it-does -> carry-conditions [rights-and-duties]: what each
side may do, must do and may not do, at a version both our own
people hold
set-what-it-does -> choose-paper [agreement-purpose]: the same
statement, so the template is picked for the relationship rather
than out of habit
set-what-it-does -> set-commercials [duties-taken-on]: the duties
each side takes on, so the money is set against real obligations
carry-conditions -> draft [conditions-as-terms]: every condition as a
term, with the date it bites, the measure it is read against, and
what happens if it is missed
choose-paper -> draft [template-and-schedules]: the template at a
version, the schedules it needs, and the clauses that may not be
changed
set-commercials -> draft [commercial-terms]: margin, fees, targets,
payment terms, and the floor, with the person who set the floor
named
draft -> review-inside [first-draft]: the full draft, every term
traced to the agreed list or to the template it came from
review-inside -> send-and-take-markup [approved-draft]: the draft at
the signed internal version, and the reviewers who signed it
send-and-take-markup -> list-changes [partner-markup]: the partner's
markup, against the version it was sent at, with the date it came
back
list-changes -> price-and-sort [numbered-changes]: every requested
change numbered, in the partner's own words, clause by clause
price-and-sort -> approve-concessions [change-costing]: what each
change costs, who carries it, and what we ask for in return
approve-concessions -> negotiate-open-terms [approved-positions]: the
approved give and trade positions, each with its approver and the
date
negotiate-open-terms -> settle-schedules [closed-changes]: every
change closed as given, traded or refused, with the person on each
side who agreed
settle-schedules -> check-paper [settled-schedules]: the schedules as
settled, each naming the person who owns the number in it
check-paper -> clear-for-signature [text-against-agreed]: the final
text, the agreed list, and every difference between the two
clear-for-signature -> sign [signing-entity-cleared]: the entity that
signs, its screening result at a date, and the person confirmed to
sign for it
sign -> record-and-hand-on [executed-agreement]: the executed
agreement, the signatures with their dates, and the version that
was signed
deviations:
review-inside -> draft [condition-dropped]: the draft drops a
qualification condition, so it is drafted again with the condition
written in or with a named decision to drop it
list-changes -> send-and-take-markup [markup-incomplete]: the markup
is not the whole of what they want changed, so it goes back for a
complete markup against the version that was sent
approve-concessions -> price-and-sort [concession-refused]: an
approver refuses a concession, so the change is priced and sorted
again against the floor
negotiate-open-terms -> set-commercials [ask-below-floor]: an ask
sits below the floor, so the floor and the commercial terms are set
again before anything is offered
check-paper -> negotiate-open-terms [paper-disagrees]: the final text
and the agreed list differ, so the difference goes back to the
table rather than into the drafting
clear-for-signature -> negotiate-open-terms [screening-finds-new]:
the screening before signature finds something new, so signature is
held and the terms are worked again
sign -> negotiate-open-terms [signer-will-not-sign]: a signer will
not sign as drafted, so the terms behind the refusal go back to the
table
bindings:
roster: <who holds each role - agents claiming the abstract agents
above, and named people for the partner lead, the legal
reviewer, the finance partner, the sales leader and the
person who signs>
systems: the contract system (write), the partner record (write),
the signing service (write), the approval system (write),
<your screening service> (read),
the pricing model (read, cap: <n> margin),
the shared workspace with the partner (write)
data: <your partner agreement template> <version>, <your standard
terms> <version>, <your margin policy> <version>, the
qualification decision and its conditions, the agreed list
policy:
every condition the qualification attached appears in the agreement
as a term with a date and a consequence, or the run records who
decided to drop it
no concession is offered to the partner before it is approved
inside, and the approval names a person
a term below the floor is refused, and only <who> may move the floor
the draft that goes out is a version, and a markup against any other
version goes back for a fresh markup
legal and finance review is a human gate and is never delegated to
an agent
nothing is signed while the final text and the agreed list differ on
any term
the screening runs again on the entity that actually signs, within
<days> of signature
the executed copy is filed within <days>, and the terms that other
processes rely on are written into the partner record
measures:
cycle time: <target> from a qualified candidate to an executed
agreement
drift: <target> for the gap between the draft as sent and the
agreement as signed
volume: <agreements per period>
quality gate: no agreement is executed with an unapproved concession
in it or a qualification condition missing from it
```
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
400 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: sign a partner agreement id: <team>/sign-a-partner-agreement v1
from: ref/prt/sign-a-partner-agreement v1
owner: <who> effective: <date>
trigger: a candidate is marked qualified in <your partner record> and
both sides agree to paper the relationship
watch: record=<candidate> system=<your partner record>
change=<a candidate is marked qualified and both sides
agree to paper the relationship>
concurrency: runs may overlap - <how many> agreements live at once,
and one partner is papered by one run at a time
goal: an executed agreement whose terms match the agreed list line for
line, every qualification condition written in as an obligation,
and every concession carrying a named approver
phases:
take-in-candidate - human: read the qualification decision, the
conditions attached to it, and the evidence
behind both
owner: agreement-writer after: trigger
automation: <level>
set-what-it-does - convenes decide-and-announce: what each side
may do, must do and may not do, written before
any template is opened
owner: <your partner leadership role>
after: take-in-candidate
by: <days> automation: <level>
carry-conditions - human: every condition the qualification
attached, rewritten as a term with a date, a
measure and a consequence
owner: agreement-writer
after: set-what-it-does automation: <level>
choose-paper - convenes decide-and-announce: which template,
which schedules, which country's law, and what
the partner's own paper may not replace
owner: <your legal role>
after: set-what-it-does
by: <days> automation: never
set-commercials - convenes decide-and-announce: margin, fees,
targets, payment terms, and the floor below
which <who> refuses to sign
owner: <your finance role>
after: set-what-it-does
by: <days> automation: never
draft - runs build-by-talent: the full draft with its
schedules, every term traceable to the agreed
list or to the template
owner: agreement-writer
after: carry-conditions + choose-paper +
set-commercials
by: <days> automation: <level>
review-inside - convenes approval: legal, finance and the
partner lead sign the draft as named signers
before it leaves the company
owner: <your legal role> after: draft
by: <days> automation: never
send-and-take-markup - human: the draft goes to the partner at a
version, and their markup comes back against
that same version
owner: partner-manager after: review-inside
by: <days> automation: <level>
list-changes - runs collect-and-report: every requested
change gathered into one numbered list, in the
partner's own wording, clause by clause
owner: agreement-writer
after: send-and-take-markup
by: <days> automation: <level>
price-and-sort - runs assessment: each change marked give,
trade or refuse, with what it costs and what
we ask for in return
owner: agreement-writer after: list-changes
by: <days> automation: <level>
approve-concessions - convenes approval: the give and trade list
signed inside, by the people whose numbers it
moves, before any of it is offered
owner: <your finance role>
after: price-and-sort
by: <days> automation: never
negotiate-open-terms - human: the numbered list worked through with
the partner, against the approved positions
and the floor
owner: <your partner leadership role>
after: approve-concessions
automation: <level>
settle-schedules - convenes decide-and-announce: territory,
products, targets, support duties and prices,
each agreed by the person who owns it
owner: partner-manager
after: negotiate-open-terms
by: <days> automation: <level>
check-paper - runs assessment: the final text read against
the agreed list term by term, and every
difference named
owner: agreement-writer
after: settle-schedules
by: <days> automation: <level>
clear-for-signature - runs assessment: the entity that will sign
screened again, and its signing authority
confirmed against <your screening service>
owner: supplier-check after: check-paper
by: <days> automation: <level>
sign - convenes approval: both sides sign, in the
order the paper sets, and each signature is
dated and kept
owner: <your signing authority>
after: clear-for-signature
by: <days> automation: never
record-and-hand-on - human: the executed copy filed, the terms
written into the partner record, and the
people who must work them told
owner: partner-manager after: sign
by: <days> automation: <level>
run-scoped:
concessions - runs allocate-and-reconcile
owner: agreement-writer
from: price-and-sort until: run close
status - runs roll-call
owner: partner-manager
every: <cadence>
from: send-and-take-markup until: run close
handoffs:
take-in-candidate -> set-what-it-does [qualification-decision]: the
qualification decision, the conditions attached to it, and the
claims left unproven
set-what-it-does -> carry-conditions [rights-and-duties]: what each
side may do, must do and may not do, at a version both our own
people hold
set-what-it-does -> choose-paper [agreement-purpose]: the same
statement, so the template is picked for the relationship rather
than out of habit
set-what-it-does -> set-commercials [duties-taken-on]: the duties
each side takes on, so the money is set against real obligations
carry-conditions -> draft [conditions-as-terms]: every condition as a
term, with the date it bites, the measure it is read against, and
what happens if it is missed
choose-paper -> draft [template-and-schedules]: the template at a
version, the schedules it needs, and the clauses that may not be
changed
set-commercials -> draft [commercial-terms]: margin, fees, targets,
payment terms, and the floor, with the person who set the floor
named
draft -> review-inside [first-draft]: the full draft, every term
traced to the agreed list or to the template it came from
review-inside -> send-and-take-markup [approved-draft]: the draft at
the signed internal version, and the reviewers who signed it
send-and-take-markup -> list-changes [partner-markup]: the partner's
markup, against the version it was sent at, with the date it came
back
list-changes -> price-and-sort [numbered-changes]: every requested
change numbered, in the partner's own words, clause by clause
price-and-sort -> approve-concessions [change-costing]: what each
change costs, who carries it, and what we ask for in return
approve-concessions -> negotiate-open-terms [approved-positions]: the
approved give and trade positions, each with its approver and the
date
negotiate-open-terms -> settle-schedules [closed-changes]: every
change closed as given, traded or refused, with the person on each
side who agreed
settle-schedules -> check-paper [settled-schedules]: the schedules as
settled, each naming the person who owns the number in it
check-paper -> clear-for-signature [text-against-agreed]: the final
text, the agreed list, and every difference between the two
clear-for-signature -> sign [signing-entity-cleared]: the entity that
signs, its screening result at a date, and the person confirmed to
sign for it
sign -> record-and-hand-on [executed-agreement]: the executed
agreement, the signatures with their dates, and the version that
was signed
deviations:
review-inside -> draft [condition-dropped]: the draft drops a
qualification condition, so it is drafted again with the condition
written in or with a named decision to drop it
list-changes -> send-and-take-markup [markup-incomplete]: the markup
is not the whole of what they want changed, so it goes back for a
complete markup against the version that was sent
approve-concessions -> price-and-sort [concession-refused]: an
approver refuses a concession, so the change is priced and sorted
again against the floor
negotiate-open-terms -> set-commercials [ask-below-floor]: an ask
sits below the floor, so the floor and the commercial terms are set
again before anything is offered
check-paper -> negotiate-open-terms [paper-disagrees]: the final text
and the agreed list differ, so the difference goes back to the
table rather than into the drafting
clear-for-signature -> negotiate-open-terms [screening-finds-new]:
the screening before signature finds something new, so signature is
held and the terms are worked again
sign -> negotiate-open-terms [signer-will-not-sign]: a signer will
not sign as drafted, so the terms behind the refusal go back to the
table
bindings:
roster: <who holds each role - agents claiming the abstract agents
above, and named people for the partner lead, the legal
reviewer, the finance partner, the sales leader and the
person who signs>
systems: the contract system (write), the partner record (write),
the signing service (write), the approval system (write),
<your screening service> (read),
the pricing model (read, cap: <n> margin),
the shared workspace with the partner (write)
data: <your partner agreement template> <version>, <your standard
terms> <version>, <your margin policy> <version>, the
qualification decision and its conditions, the agreed list
policy:
every condition the qualification attached appears in the agreement
as a term with a date and a consequence, or the run records who
decided to drop it
no concession is offered to the partner before it is approved
inside, and the approval names a person
a term below the floor is refused, and only <who> may move the floor
the draft that goes out is a version, and a markup against any other
version goes back for a fresh markup
legal and finance review is a human gate and is never delegated to
an agent
nothing is signed while the final text and the agreed list differ on
any term
the screening runs again on the entity that actually signs, within
<days> of signature
the executed copy is filed within <days>, and the terms that other
processes rely on are written into the partner record
measures:
cycle time: <target> from a qualified candidate to an executed
agreement
drift: <target> for the gap between the draft as sent and the
agreement as signed
volume: <agreements per period>
quality gate: no agreement is executed with an unapproved concession
in it or a qualification condition missing from it
```
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
56 blanks to fill. Everything else is the process.
this process
from: ref/prt/sign-a-partner-agreement 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.