Catalog / Business processes / Sales / Signature-to-Handover / Hand over to Delivery
reference process · sales · 16 activities · 9 on the rosterHand over to Delivery
An order is booked, and the run moves the relationship from the person who sold it to the person who will deliver it. Everything the sale learned is collected into one account picture: what the customer bought, what was promised, who decides and who pays, and where the account already stands. What the contract binds is separated from what was merely said, so nobody inherits a promise they cannot keep. The seller and the new owner meet before the customer hears anything, the customer is introduced to the new owner once rather than three times, and the first working session is in diaries before the run closes.
The walk
The document
One run
Adoption
The activities
What happens in a run
16 activities from an order is booked to somebody other than the seller owns the relationship, one of them a gate a person has to sign. Drag the diagram to move along it.
Hand over to Delivery an order is booked → somebody other than the seller owns the relationship
a promise the contract does not carry the package is missing what it must carry the new owner will not take it the sponsor at the customer has changed the customer never confirms an order is booked 1 Take in the Booked Order what was sold, on what terms, and starting when 2 Name Who Now Owns the Rel… the person the customer deals with from now on a person signs · never an agent 3 Collect What the Sale Lea… notes, mail and calls gathered into one place 4 Write the Account Picture who the customer is and what they bought 5 Record What Was Promised every commitment made during the sale, written down 6 Separate the Contract fro… what the contract binds, and what was only said 7 Map Who Is Who at the Cus… who decides, who pays, who uses it every day 8 Read Where the Account St… usage, support history, and anything still open 9 Check the Package Is Comp… the package scored against what it must carry 10 Hold the Internal Handover the seller and the new owner in one conversation 11 Agree Who Says What to th… one message to the customer, not three 12 Introduce the New Owner t… the customer hears who they now deal with 13 Schedule the Start the first working session put in diaries 14 Confirm the Customer Acce… the customer says they know who to call 15 Close Out the Sales Side what the seller still owes, and what they do not 16 Record What the Sale Did … the gaps, so the next handover is fuller somebody other than the seller owns the relationship 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: hand over to delivery id: <team> /hand-over-to-delivery v1
from: ref/sls/hand-over-to-delivery v1
owner: <who> effective: <date>
trigger: an order is booked in <your order system>
watch: record=<order> system=<your order system>
change=<an order is recorded as booked>
concurrency: runs may overlap - <how many> handovers open at once, and
one account is handed over by one run at a time
goal: the customer deals with a named person other than the seller
within <days> of booking, that person holds everything the sale
learned, and the first working session is in diaries
phases:
take-in-order - runs collect-and-report: what was sold, on what
terms, at what price, starting when, and who signed
owner: handover-coordinator after: trigger
by: <hours> automation: <level>
name-new-owner - convenes decide-and-announce: the person who owns
the relationship from now on, named in writing,
with the date they take it
owner: <your delivery leadership role>
after: take-in-order
by: <days> automation: never
collect-the-sale - runs collect-and-report: the notes, the mail, the
call records, the proposal, the answers to the
buyer's questions, gathered into one place
owner: handover-coordinator after: take-in-order
by: <days> automation: <level>
picture - runs build-by-talent: who the customer is, what
they are trying to do, what they bought and why
they bought it
owner: handover-coordinator after: collect-the-sale
automation: <level>
record-promises - human: every commitment made during the sale,
written down one per line with who made it, when,
and to whom
owner: <your sales role> after: collect-the-sale
automation: <level>
mark-binding - runs assessment: each recorded promise marked as
carried by the agreement, carried by a side letter,
or said and not binding
owner: signature-manager after: record-promises
by: <days> automation: <level>
map-people - runs collect-and-report: who decides, who pays, who
uses it every day, who blocked the deal, and how
each one prefers to be reached
owner: handover-coordinator after: collect-the-sale
automation: <level>
standing - runs roll-call: product usage, support history,
open tickets, anything in dispute, and where the
account sits in its renewal cycle
owner: account-monitor after: take-in-order
by: <days> automation: <level>
check-package - runs assessment: the handover package scored
against <your handover checklist> at a version,
naming what is missing rather than what is present
owner: order-check
after: picture + mark-binding + map-people + standing
automation: <level>
internal-brief - convenes briefing: the seller walks the new owner
through the account, and the new owner asks the
questions the package did not answer
owner: handover-coordinator
after: name-new-owner + check-package
by: <days> automation: <level>
agree-message - convenes decide-and-announce: what the customer is
told, by whom, on what date, and through which
channel
owner: handover-coordinator after: internal-brief
automation: <level>
introduce-owner - human: the seller introduces the new owner to the
customer, and stays in the conversation until the
customer answers the new owner directly
owner: <your sales role> after: agree-message
by: <days> automation: <level>
schedule-start - human: the first working session is agreed with the
customer and put in diaries on both sides
owner: <your delivery role> after: introduce-owner
by: <days> automation: <level>
confirm-accepted - human: the customer confirms they know who they now
deal with and how to reach them, and the confirmation
is recorded with its date
owner: handover-coordinator after: schedule-start
by: <days> automation: <level>
close-seller - human: what the seller still owes is listed with a
date against each item, and everything else moves
to the new owner
owner: handover-coordinator after: confirm-accepted
automation: <level>
record-gaps - convenes debrief: what the new owner had to ask the
customer again, and what the sale should have
captured the first time
owner: handover-coordinator after: close-seller
automation: <level>
run-scoped:
open-promises - runs allocate-and-reconcile owner: handover-coordinator
from: record-promises until: run close
status - runs roll-call owner: handover-coordinator
every: <cadence>
from: take-in-order until: confirm-accepted
handoffs:
take-in-order -> name-new-owner [what-was-sold]: what was sold and
when it starts, so the person named can actually deliver it
take-in-order -> collect-the-sale [order-and-opportunity]: the
order, its identifier, and the opportunity every note hangs off
take-in-order -> standing [account-and-entity]: the account and the
entity, so standing is read for the party that bought
collect-the-sale -> picture [sale-material]: everything the sale
produced, in one place, with the date on each item
collect-the-sale -> record-promises [notes-and-calls]: the notes and
the call records the promises are read out of
collect-the-sale -> map-people [names-from-the-sale]: the names that
appeared during the sale, and what each one did
record-promises -> mark-binding [promise-list]: the promises as the
seller remembers them, one per line
mark-binding -> check-package [marked-promises]: each promise marked
binding or not binding, with the clause behind every binding one
picture -> check-package [account-picture]: the picture as written,
with the source behind every claim in it
map-people -> check-package [people-map]: the people, their roles,
and how each one is reached
standing -> check-package [account-standing]: the account's
standing, dated, with the system every line came from
check-package -> internal-brief [package-score]: the scored package,
with what is missing named and the checklist version it was scored
against
name-new-owner -> internal-brief [new-owner]: the new owner, and the
date they take the relationship
internal-brief -> agree-message [open-questions]: the questions the
package did not answer, and the answers the seller gave in the
room
agree-message -> introduce-owner [the-message-plan]: who says what,
on what date, through which channel
introduce-owner -> schedule-start [customer-reply]: the customer's
answer, and whoever at the customer replied
schedule-start -> confirm-accepted [session-in-diaries]: the session
in diaries on both sides, with the people invited to it
confirm-accepted -> close-seller [customer-confirmation]: the
customer's confirmation, dated, with what they were told
close-seller -> record-gaps [seller-open-items]: what the seller
still owes, and what the new owner now holds
deviations:
mark-binding -> record-promises [promise-not-in-contract]: a promise
the agreement does not carry is marked said and not binding, so
the promise list goes back for a person to decide on it
check-package -> collect-the-sale [package-incomplete]: the package
is missing what the checklist says it must carry, so the sale is
collected again for the missing item
internal-brief -> name-new-owner [owner-refuses]: the new owner will
not take the account, so the gaps are filled or a different person
is named before the customer hears anything
introduce-owner -> map-people [sponsor-has-changed]: the person who
signed has left or handed the project on, so the people are mapped
again and the introduction goes to whoever holds it now
confirm-accepted -> introduce-owner [no-confirmation]: the customer
never confirms, so the introduction is made again through a
channel they use
bindings:
roster: <who holds each role - agents claiming the abstract agents
above, and named people for the account owner, the delivery
lead, the sales leader and the legal reviewer>
systems: the order system (read), the CRM (read), the CRM (write),
the contract repository (read), the handover record (write),
the delivery system (write), the support system (read),
product usage data (read), the calendar (write),
the customer communication channel (write)
data: <your handover checklist> <version> , the booked order,
the executed agreement <version> , <your account picture
template>, <your escalation list>
policy:
no customer hears about the handover before the internal handover has
happened
a promise made during the sale is recorded whether or not the contract
carries it, and the ones the contract does not carry are decided by
<who> before the customer is told anything
the new owner is a named person, never a queue or a shared mailbox
the seller stays reachable to the new owner for <days> after the
customer confirms, and stays out of the customer conversation unless
the new owner asks them into it
a handover the customer has not confirmed is not counted as complete,
however many internal steps are done
an account with something open in dispute or in support is handed over
with that item named, and <who> is told before the introduction
the package is scored against the checklist at a version, and a
missing item is carried forward with a date rather than waived
silently
measures:
cycle time: <target> from booking to the customer's confirmation
repeat rate: <target> for questions the new owner had to ask the
customer again in the first <weeks>
volume: <handovers per period>
quality gate: no handover closes without the customer's dated
confirmation and the promise list marked binding or not
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
315 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: hand over to delivery id: <team>/hand-over-to-delivery v1
from: ref/sls/hand-over-to-delivery v1
owner: <who> effective: <date>
trigger: an order is booked in <your order system>
watch: record=<order> system=<your order system>
change=<an order is recorded as booked>
concurrency: runs may overlap - <how many> handovers open at once, and
one account is handed over by one run at a time
goal: the customer deals with a named person other than the seller
within <days> of booking, that person holds everything the sale
learned, and the first working session is in diaries
phases:
take-in-order - runs collect-and-report: what was sold, on what
terms, at what price, starting when, and who signed
owner: handover-coordinator after: trigger
by: <hours> automation: <level>
name-new-owner - convenes decide-and-announce: the person who owns
the relationship from now on, named in writing,
with the date they take it
owner: <your delivery leadership role>
after: take-in-order
by: <days> automation: never
collect-the-sale - runs collect-and-report: the notes, the mail, the
call records, the proposal, the answers to the
buyer's questions, gathered into one place
owner: handover-coordinator after: take-in-order
by: <days> automation: <level>
picture - runs build-by-talent: who the customer is, what
they are trying to do, what they bought and why
they bought it
owner: handover-coordinator after: collect-the-sale
automation: <level>
record-promises - human: every commitment made during the sale,
written down one per line with who made it, when,
and to whom
owner: <your sales role> after: collect-the-sale
automation: <level>
mark-binding - runs assessment: each recorded promise marked as
carried by the agreement, carried by a side letter,
or said and not binding
owner: signature-manager after: record-promises
by: <days> automation: <level>
map-people - runs collect-and-report: who decides, who pays, who
uses it every day, who blocked the deal, and how
each one prefers to be reached
owner: handover-coordinator after: collect-the-sale
automation: <level>
standing - runs roll-call: product usage, support history,
open tickets, anything in dispute, and where the
account sits in its renewal cycle
owner: account-monitor after: take-in-order
by: <days> automation: <level>
check-package - runs assessment: the handover package scored
against <your handover checklist> at a version,
naming what is missing rather than what is present
owner: order-check
after: picture + mark-binding + map-people + standing
automation: <level>
internal-brief - convenes briefing: the seller walks the new owner
through the account, and the new owner asks the
questions the package did not answer
owner: handover-coordinator
after: name-new-owner + check-package
by: <days> automation: <level>
agree-message - convenes decide-and-announce: what the customer is
told, by whom, on what date, and through which
channel
owner: handover-coordinator after: internal-brief
automation: <level>
introduce-owner - human: the seller introduces the new owner to the
customer, and stays in the conversation until the
customer answers the new owner directly
owner: <your sales role> after: agree-message
by: <days> automation: <level>
schedule-start - human: the first working session is agreed with the
customer and put in diaries on both sides
owner: <your delivery role> after: introduce-owner
by: <days> automation: <level>
confirm-accepted - human: the customer confirms they know who they now
deal with and how to reach them, and the confirmation
is recorded with its date
owner: handover-coordinator after: schedule-start
by: <days> automation: <level>
close-seller - human: what the seller still owes is listed with a
date against each item, and everything else moves
to the new owner
owner: handover-coordinator after: confirm-accepted
automation: <level>
record-gaps - convenes debrief: what the new owner had to ask the
customer again, and what the sale should have
captured the first time
owner: handover-coordinator after: close-seller
automation: <level>
run-scoped:
open-promises - runs allocate-and-reconcile owner: handover-coordinator
from: record-promises until: run close
status - runs roll-call owner: handover-coordinator
every: <cadence>
from: take-in-order until: confirm-accepted
handoffs:
take-in-order -> name-new-owner [what-was-sold]: what was sold and
when it starts, so the person named can actually deliver it
take-in-order -> collect-the-sale [order-and-opportunity]: the
order, its identifier, and the opportunity every note hangs off
take-in-order -> standing [account-and-entity]: the account and the
entity, so standing is read for the party that bought
collect-the-sale -> picture [sale-material]: everything the sale
produced, in one place, with the date on each item
collect-the-sale -> record-promises [notes-and-calls]: the notes and
the call records the promises are read out of
collect-the-sale -> map-people [names-from-the-sale]: the names that
appeared during the sale, and what each one did
record-promises -> mark-binding [promise-list]: the promises as the
seller remembers them, one per line
mark-binding -> check-package [marked-promises]: each promise marked
binding or not binding, with the clause behind every binding one
picture -> check-package [account-picture]: the picture as written,
with the source behind every claim in it
map-people -> check-package [people-map]: the people, their roles,
and how each one is reached
standing -> check-package [account-standing]: the account's
standing, dated, with the system every line came from
check-package -> internal-brief [package-score]: the scored package,
with what is missing named and the checklist version it was scored
against
name-new-owner -> internal-brief [new-owner]: the new owner, and the
date they take the relationship
internal-brief -> agree-message [open-questions]: the questions the
package did not answer, and the answers the seller gave in the
room
agree-message -> introduce-owner [the-message-plan]: who says what,
on what date, through which channel
introduce-owner -> schedule-start [customer-reply]: the customer's
answer, and whoever at the customer replied
schedule-start -> confirm-accepted [session-in-diaries]: the session
in diaries on both sides, with the people invited to it
confirm-accepted -> close-seller [customer-confirmation]: the
customer's confirmation, dated, with what they were told
close-seller -> record-gaps [seller-open-items]: what the seller
still owes, and what the new owner now holds
deviations:
mark-binding -> record-promises [promise-not-in-contract]: a promise
the agreement does not carry is marked said and not binding, so
the promise list goes back for a person to decide on it
check-package -> collect-the-sale [package-incomplete]: the package
is missing what the checklist says it must carry, so the sale is
collected again for the missing item
internal-brief -> name-new-owner [owner-refuses]: the new owner will
not take the account, so the gaps are filled or a different person
is named before the customer hears anything
introduce-owner -> map-people [sponsor-has-changed]: the person who
signed has left or handed the project on, so the people are mapped
again and the introduction goes to whoever holds it now
confirm-accepted -> introduce-owner [no-confirmation]: the customer
never confirms, so the introduction is made again through a
channel they use
bindings:
roster: <who holds each role - agents claiming the abstract agents
above, and named people for the account owner, the delivery
lead, the sales leader and the legal reviewer>
systems: the order system (read), the CRM (read), the CRM (write),
the contract repository (read), the handover record (write),
the delivery system (write), the support system (read),
product usage data (read), the calendar (write),
the customer communication channel (write)
data: <your handover checklist> <version>, the booked order,
the executed agreement <version>, <your account picture
template>, <your escalation list>
policy:
no customer hears about the handover before the internal handover has
happened
a promise made during the sale is recorded whether or not the contract
carries it, and the ones the contract does not carry are decided by
<who> before the customer is told anything
the new owner is a named person, never a queue or a shared mailbox
the seller stays reachable to the new owner for <days> after the
customer confirms, and stays out of the customer conversation unless
the new owner asks them into it
a handover the customer has not confirmed is not counted as complete,
however many internal steps are done
an account with something open in dispute or in support is handed over
with that item named, and <who> is told before the introduction
the package is scored against the checklist at a version, and a
missing item is carried forward with a date rather than waived
silently
measures:
cycle time: <target> from booking to the customer's confirmation
repeat rate: <target> for questions the new owner had to ask the
customer again in the first <weeks>
volume: <handovers per period>
quality gate: no handover closes without the customer's dated
confirmation and the promise list marked binding or not
```
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
370 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: hand over to delivery id: <team>/hand-over-to-delivery v1
from: ref/sls/hand-over-to-delivery v1
owner: <who> effective: <date>
trigger: an order is booked in <your order system>
watch: record=<order> system=<your order system>
change=<an order is recorded as booked>
concurrency: runs may overlap - <how many> handovers open at once, and
one account is handed over by one run at a time
goal: the customer deals with a named person other than the seller
within <days> of booking, that person holds everything the sale
learned, and the first working session is in diaries
phases:
take-in-order - runs collect-and-report: what was sold, on what
terms, at what price, starting when, and who signed
owner: handover-coordinator after: trigger
by: <hours> automation: <level>
name-new-owner - convenes decide-and-announce: the person who owns
the relationship from now on, named in writing,
with the date they take it
owner: <your delivery leadership role>
after: take-in-order
by: <days> automation: never
collect-the-sale - runs collect-and-report: the notes, the mail, the
call records, the proposal, the answers to the
buyer's questions, gathered into one place
owner: handover-coordinator after: take-in-order
by: <days> automation: <level>
picture - runs build-by-talent: who the customer is, what
they are trying to do, what they bought and why
they bought it
owner: handover-coordinator after: collect-the-sale
automation: <level>
record-promises - human: every commitment made during the sale,
written down one per line with who made it, when,
and to whom
owner: <your sales role> after: collect-the-sale
automation: <level>
mark-binding - runs assessment: each recorded promise marked as
carried by the agreement, carried by a side letter,
or said and not binding
owner: signature-manager after: record-promises
by: <days> automation: <level>
map-people - runs collect-and-report: who decides, who pays, who
uses it every day, who blocked the deal, and how
each one prefers to be reached
owner: handover-coordinator after: collect-the-sale
automation: <level>
standing - runs roll-call: product usage, support history,
open tickets, anything in dispute, and where the
account sits in its renewal cycle
owner: account-monitor after: take-in-order
by: <days> automation: <level>
check-package - runs assessment: the handover package scored
against <your handover checklist> at a version,
naming what is missing rather than what is present
owner: order-check
after: picture + mark-binding + map-people + standing
automation: <level>
internal-brief - convenes briefing: the seller walks the new owner
through the account, and the new owner asks the
questions the package did not answer
owner: handover-coordinator
after: name-new-owner + check-package
by: <days> automation: <level>
agree-message - convenes decide-and-announce: what the customer is
told, by whom, on what date, and through which
channel
owner: handover-coordinator after: internal-brief
automation: <level>
introduce-owner - human: the seller introduces the new owner to the
customer, and stays in the conversation until the
customer answers the new owner directly
owner: <your sales role> after: agree-message
by: <days> automation: <level>
schedule-start - human: the first working session is agreed with the
customer and put in diaries on both sides
owner: <your delivery role> after: introduce-owner
by: <days> automation: <level>
confirm-accepted - human: the customer confirms they know who they now
deal with and how to reach them, and the confirmation
is recorded with its date
owner: handover-coordinator after: schedule-start
by: <days> automation: <level>
close-seller - human: what the seller still owes is listed with a
date against each item, and everything else moves
to the new owner
owner: handover-coordinator after: confirm-accepted
automation: <level>
record-gaps - convenes debrief: what the new owner had to ask the
customer again, and what the sale should have
captured the first time
owner: handover-coordinator after: close-seller
automation: <level>
run-scoped:
open-promises - runs allocate-and-reconcile owner: handover-coordinator
from: record-promises until: run close
status - runs roll-call owner: handover-coordinator
every: <cadence>
from: take-in-order until: confirm-accepted
handoffs:
take-in-order -> name-new-owner [what-was-sold]: what was sold and
when it starts, so the person named can actually deliver it
take-in-order -> collect-the-sale [order-and-opportunity]: the
order, its identifier, and the opportunity every note hangs off
take-in-order -> standing [account-and-entity]: the account and the
entity, so standing is read for the party that bought
collect-the-sale -> picture [sale-material]: everything the sale
produced, in one place, with the date on each item
collect-the-sale -> record-promises [notes-and-calls]: the notes and
the call records the promises are read out of
collect-the-sale -> map-people [names-from-the-sale]: the names that
appeared during the sale, and what each one did
record-promises -> mark-binding [promise-list]: the promises as the
seller remembers them, one per line
mark-binding -> check-package [marked-promises]: each promise marked
binding or not binding, with the clause behind every binding one
picture -> check-package [account-picture]: the picture as written,
with the source behind every claim in it
map-people -> check-package [people-map]: the people, their roles,
and how each one is reached
standing -> check-package [account-standing]: the account's
standing, dated, with the system every line came from
check-package -> internal-brief [package-score]: the scored package,
with what is missing named and the checklist version it was scored
against
name-new-owner -> internal-brief [new-owner]: the new owner, and the
date they take the relationship
internal-brief -> agree-message [open-questions]: the questions the
package did not answer, and the answers the seller gave in the
room
agree-message -> introduce-owner [the-message-plan]: who says what,
on what date, through which channel
introduce-owner -> schedule-start [customer-reply]: the customer's
answer, and whoever at the customer replied
schedule-start -> confirm-accepted [session-in-diaries]: the session
in diaries on both sides, with the people invited to it
confirm-accepted -> close-seller [customer-confirmation]: the
customer's confirmation, dated, with what they were told
close-seller -> record-gaps [seller-open-items]: what the seller
still owes, and what the new owner now holds
deviations:
mark-binding -> record-promises [promise-not-in-contract]: a promise
the agreement does not carry is marked said and not binding, so
the promise list goes back for a person to decide on it
check-package -> collect-the-sale [package-incomplete]: the package
is missing what the checklist says it must carry, so the sale is
collected again for the missing item
internal-brief -> name-new-owner [owner-refuses]: the new owner will
not take the account, so the gaps are filled or a different person
is named before the customer hears anything
introduce-owner -> map-people [sponsor-has-changed]: the person who
signed has left or handed the project on, so the people are mapped
again and the introduction goes to whoever holds it now
confirm-accepted -> introduce-owner [no-confirmation]: the customer
never confirms, so the introduction is made again through a
channel they use
bindings:
roster: <who holds each role - agents claiming the abstract agents
above, and named people for the account owner, the delivery
lead, the sales leader and the legal reviewer>
systems: the order system (read), the CRM (read), the CRM (write),
the contract repository (read), the handover record (write),
the delivery system (write), the support system (read),
product usage data (read), the calendar (write),
the customer communication channel (write)
data: <your handover checklist> <version>, the booked order,
the executed agreement <version>, <your account picture
template>, <your escalation list>
policy:
no customer hears about the handover before the internal handover has
happened
a promise made during the sale is recorded whether or not the contract
carries it, and the ones the contract does not carry are decided by
<who> before the customer is told anything
the new owner is a named person, never a queue or a shared mailbox
the seller stays reachable to the new owner for <days> after the
customer confirms, and stays out of the customer conversation unless
the new owner asks them into it
a handover the customer has not confirmed is not counted as complete,
however many internal steps are done
an account with something open in dispute or in support is handed over
with that item named, and <who> is told before the introduction
the package is scored against the checklist at a version, and a
missing item is carried forward with a date rather than waived
silently
measures:
cycle time: <target> from booking to the customer's confirmation
repeat rate: <target> for questions the new owner had to ask the
customer again in the first <weeks>
volume: <handovers per period>
quality gate: no handover closes without the customer's dated
confirmation and the promise list marked binding or not
```
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
375 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: hand over to delivery id: <team>/hand-over-to-delivery v1
from: ref/sls/hand-over-to-delivery v1
owner: <who> effective: <date>
trigger: an order is booked in <your order system>
watch: record=<order> system=<your order system>
change=<an order is recorded as booked>
concurrency: runs may overlap - <how many> handovers open at once, and
one account is handed over by one run at a time
goal: the customer deals with a named person other than the seller
within <days> of booking, that person holds everything the sale
learned, and the first working session is in diaries
phases:
take-in-order - runs collect-and-report: what was sold, on what
terms, at what price, starting when, and who signed
owner: handover-coordinator after: trigger
by: <hours> automation: <level>
name-new-owner - convenes decide-and-announce: the person who owns
the relationship from now on, named in writing,
with the date they take it
owner: <your delivery leadership role>
after: take-in-order
by: <days> automation: never
collect-the-sale - runs collect-and-report: the notes, the mail, the
call records, the proposal, the answers to the
buyer's questions, gathered into one place
owner: handover-coordinator after: take-in-order
by: <days> automation: <level>
picture - runs build-by-talent: who the customer is, what
they are trying to do, what they bought and why
they bought it
owner: handover-coordinator after: collect-the-sale
automation: <level>
record-promises - human: every commitment made during the sale,
written down one per line with who made it, when,
and to whom
owner: <your sales role> after: collect-the-sale
automation: <level>
mark-binding - runs assessment: each recorded promise marked as
carried by the agreement, carried by a side letter,
or said and not binding
owner: signature-manager after: record-promises
by: <days> automation: <level>
map-people - runs collect-and-report: who decides, who pays, who
uses it every day, who blocked the deal, and how
each one prefers to be reached
owner: handover-coordinator after: collect-the-sale
automation: <level>
standing - runs roll-call: product usage, support history,
open tickets, anything in dispute, and where the
account sits in its renewal cycle
owner: account-monitor after: take-in-order
by: <days> automation: <level>
check-package - runs assessment: the handover package scored
against <your handover checklist> at a version,
naming what is missing rather than what is present
owner: order-check
after: picture + mark-binding + map-people + standing
automation: <level>
internal-brief - convenes briefing: the seller walks the new owner
through the account, and the new owner asks the
questions the package did not answer
owner: handover-coordinator
after: name-new-owner + check-package
by: <days> automation: <level>
agree-message - convenes decide-and-announce: what the customer is
told, by whom, on what date, and through which
channel
owner: handover-coordinator after: internal-brief
automation: <level>
introduce-owner - human: the seller introduces the new owner to the
customer, and stays in the conversation until the
customer answers the new owner directly
owner: <your sales role> after: agree-message
by: <days> automation: <level>
schedule-start - human: the first working session is agreed with the
customer and put in diaries on both sides
owner: <your delivery role> after: introduce-owner
by: <days> automation: <level>
confirm-accepted - human: the customer confirms they know who they now
deal with and how to reach them, and the confirmation
is recorded with its date
owner: handover-coordinator after: schedule-start
by: <days> automation: <level>
close-seller - human: what the seller still owes is listed with a
date against each item, and everything else moves
to the new owner
owner: handover-coordinator after: confirm-accepted
automation: <level>
record-gaps - convenes debrief: what the new owner had to ask the
customer again, and what the sale should have
captured the first time
owner: handover-coordinator after: close-seller
automation: <level>
run-scoped:
open-promises - runs allocate-and-reconcile owner: handover-coordinator
from: record-promises until: run close
status - runs roll-call owner: handover-coordinator
every: <cadence>
from: take-in-order until: confirm-accepted
handoffs:
take-in-order -> name-new-owner [what-was-sold]: what was sold and
when it starts, so the person named can actually deliver it
take-in-order -> collect-the-sale [order-and-opportunity]: the
order, its identifier, and the opportunity every note hangs off
take-in-order -> standing [account-and-entity]: the account and the
entity, so standing is read for the party that bought
collect-the-sale -> picture [sale-material]: everything the sale
produced, in one place, with the date on each item
collect-the-sale -> record-promises [notes-and-calls]: the notes and
the call records the promises are read out of
collect-the-sale -> map-people [names-from-the-sale]: the names that
appeared during the sale, and what each one did
record-promises -> mark-binding [promise-list]: the promises as the
seller remembers them, one per line
mark-binding -> check-package [marked-promises]: each promise marked
binding or not binding, with the clause behind every binding one
picture -> check-package [account-picture]: the picture as written,
with the source behind every claim in it
map-people -> check-package [people-map]: the people, their roles,
and how each one is reached
standing -> check-package [account-standing]: the account's
standing, dated, with the system every line came from
check-package -> internal-brief [package-score]: the scored package,
with what is missing named and the checklist version it was scored
against
name-new-owner -> internal-brief [new-owner]: the new owner, and the
date they take the relationship
internal-brief -> agree-message [open-questions]: the questions the
package did not answer, and the answers the seller gave in the
room
agree-message -> introduce-owner [the-message-plan]: who says what,
on what date, through which channel
introduce-owner -> schedule-start [customer-reply]: the customer's
answer, and whoever at the customer replied
schedule-start -> confirm-accepted [session-in-diaries]: the session
in diaries on both sides, with the people invited to it
confirm-accepted -> close-seller [customer-confirmation]: the
customer's confirmation, dated, with what they were told
close-seller -> record-gaps [seller-open-items]: what the seller
still owes, and what the new owner now holds
deviations:
mark-binding -> record-promises [promise-not-in-contract]: a promise
the agreement does not carry is marked said and not binding, so
the promise list goes back for a person to decide on it
check-package -> collect-the-sale [package-incomplete]: the package
is missing what the checklist says it must carry, so the sale is
collected again for the missing item
internal-brief -> name-new-owner [owner-refuses]: the new owner will
not take the account, so the gaps are filled or a different person
is named before the customer hears anything
introduce-owner -> map-people [sponsor-has-changed]: the person who
signed has left or handed the project on, so the people are mapped
again and the introduction goes to whoever holds it now
confirm-accepted -> introduce-owner [no-confirmation]: the customer
never confirms, so the introduction is made again through a
channel they use
bindings:
roster: <who holds each role - agents claiming the abstract agents
above, and named people for the account owner, the delivery
lead, the sales leader and the legal reviewer>
systems: the order system (read), the CRM (read), the CRM (write),
the contract repository (read), the handover record (write),
the delivery system (write), the support system (read),
product usage data (read), the calendar (write),
the customer communication channel (write)
data: <your handover checklist> <version>, the booked order,
the executed agreement <version>, <your account picture
template>, <your escalation list>
policy:
no customer hears about the handover before the internal handover has
happened
a promise made during the sale is recorded whether or not the contract
carries it, and the ones the contract does not carry are decided by
<who> before the customer is told anything
the new owner is a named person, never a queue or a shared mailbox
the seller stays reachable to the new owner for <days> after the
customer confirms, and stays out of the customer conversation unless
the new owner asks them into it
a handover the customer has not confirmed is not counted as complete,
however many internal steps are done
an account with something open in dispute or in support is handed over
with that item named, and <who> is told before the introduction
the package is scored against the checklist at a version, and a
missing item is carried forward with a date rather than waived
silently
measures:
cycle time: <target> from booking to the customer's confirmation
repeat rate: <target> for questions the new owner had to ask the
customer again in the first <weeks>
volume: <handovers per period>
quality gate: no handover closes without the customer's dated
confirmation and the promise list marked binding or not
```
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
366 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: hand over to delivery id: <team>/hand-over-to-delivery v1
from: ref/sls/hand-over-to-delivery v1
owner: <who> effective: <date>
trigger: an order is booked in <your order system>
watch: record=<order> system=<your order system>
change=<an order is recorded as booked>
concurrency: runs may overlap - <how many> handovers open at once, and
one account is handed over by one run at a time
goal: the customer deals with a named person other than the seller
within <days> of booking, that person holds everything the sale
learned, and the first working session is in diaries
phases:
take-in-order - runs collect-and-report: what was sold, on what
terms, at what price, starting when, and who signed
owner: handover-coordinator after: trigger
by: <hours> automation: <level>
name-new-owner - convenes decide-and-announce: the person who owns
the relationship from now on, named in writing,
with the date they take it
owner: <your delivery leadership role>
after: take-in-order
by: <days> automation: never
collect-the-sale - runs collect-and-report: the notes, the mail, the
call records, the proposal, the answers to the
buyer's questions, gathered into one place
owner: handover-coordinator after: take-in-order
by: <days> automation: <level>
picture - runs build-by-talent: who the customer is, what
they are trying to do, what they bought and why
they bought it
owner: handover-coordinator after: collect-the-sale
automation: <level>
record-promises - human: every commitment made during the sale,
written down one per line with who made it, when,
and to whom
owner: <your sales role> after: collect-the-sale
automation: <level>
mark-binding - runs assessment: each recorded promise marked as
carried by the agreement, carried by a side letter,
or said and not binding
owner: signature-manager after: record-promises
by: <days> automation: <level>
map-people - runs collect-and-report: who decides, who pays, who
uses it every day, who blocked the deal, and how
each one prefers to be reached
owner: handover-coordinator after: collect-the-sale
automation: <level>
standing - runs roll-call: product usage, support history,
open tickets, anything in dispute, and where the
account sits in its renewal cycle
owner: account-monitor after: take-in-order
by: <days> automation: <level>
check-package - runs assessment: the handover package scored
against <your handover checklist> at a version,
naming what is missing rather than what is present
owner: order-check
after: picture + mark-binding + map-people + standing
automation: <level>
internal-brief - convenes briefing: the seller walks the new owner
through the account, and the new owner asks the
questions the package did not answer
owner: handover-coordinator
after: name-new-owner + check-package
by: <days> automation: <level>
agree-message - convenes decide-and-announce: what the customer is
told, by whom, on what date, and through which
channel
owner: handover-coordinator after: internal-brief
automation: <level>
introduce-owner - human: the seller introduces the new owner to the
customer, and stays in the conversation until the
customer answers the new owner directly
owner: <your sales role> after: agree-message
by: <days> automation: <level>
schedule-start - human: the first working session is agreed with the
customer and put in diaries on both sides
owner: <your delivery role> after: introduce-owner
by: <days> automation: <level>
confirm-accepted - human: the customer confirms they know who they now
deal with and how to reach them, and the confirmation
is recorded with its date
owner: handover-coordinator after: schedule-start
by: <days> automation: <level>
close-seller - human: what the seller still owes is listed with a
date against each item, and everything else moves
to the new owner
owner: handover-coordinator after: confirm-accepted
automation: <level>
record-gaps - convenes debrief: what the new owner had to ask the
customer again, and what the sale should have
captured the first time
owner: handover-coordinator after: close-seller
automation: <level>
run-scoped:
open-promises - runs allocate-and-reconcile owner: handover-coordinator
from: record-promises until: run close
status - runs roll-call owner: handover-coordinator
every: <cadence>
from: take-in-order until: confirm-accepted
handoffs:
take-in-order -> name-new-owner [what-was-sold]: what was sold and
when it starts, so the person named can actually deliver it
take-in-order -> collect-the-sale [order-and-opportunity]: the
order, its identifier, and the opportunity every note hangs off
take-in-order -> standing [account-and-entity]: the account and the
entity, so standing is read for the party that bought
collect-the-sale -> picture [sale-material]: everything the sale
produced, in one place, with the date on each item
collect-the-sale -> record-promises [notes-and-calls]: the notes and
the call records the promises are read out of
collect-the-sale -> map-people [names-from-the-sale]: the names that
appeared during the sale, and what each one did
record-promises -> mark-binding [promise-list]: the promises as the
seller remembers them, one per line
mark-binding -> check-package [marked-promises]: each promise marked
binding or not binding, with the clause behind every binding one
picture -> check-package [account-picture]: the picture as written,
with the source behind every claim in it
map-people -> check-package [people-map]: the people, their roles,
and how each one is reached
standing -> check-package [account-standing]: the account's
standing, dated, with the system every line came from
check-package -> internal-brief [package-score]: the scored package,
with what is missing named and the checklist version it was scored
against
name-new-owner -> internal-brief [new-owner]: the new owner, and the
date they take the relationship
internal-brief -> agree-message [open-questions]: the questions the
package did not answer, and the answers the seller gave in the
room
agree-message -> introduce-owner [the-message-plan]: who says what,
on what date, through which channel
introduce-owner -> schedule-start [customer-reply]: the customer's
answer, and whoever at the customer replied
schedule-start -> confirm-accepted [session-in-diaries]: the session
in diaries on both sides, with the people invited to it
confirm-accepted -> close-seller [customer-confirmation]: the
customer's confirmation, dated, with what they were told
close-seller -> record-gaps [seller-open-items]: what the seller
still owes, and what the new owner now holds
deviations:
mark-binding -> record-promises [promise-not-in-contract]: a promise
the agreement does not carry is marked said and not binding, so
the promise list goes back for a person to decide on it
check-package -> collect-the-sale [package-incomplete]: the package
is missing what the checklist says it must carry, so the sale is
collected again for the missing item
internal-brief -> name-new-owner [owner-refuses]: the new owner will
not take the account, so the gaps are filled or a different person
is named before the customer hears anything
introduce-owner -> map-people [sponsor-has-changed]: the person who
signed has left or handed the project on, so the people are mapped
again and the introduction goes to whoever holds it now
confirm-accepted -> introduce-owner [no-confirmation]: the customer
never confirms, so the introduction is made again through a
channel they use
bindings:
roster: <who holds each role - agents claiming the abstract agents
above, and named people for the account owner, the delivery
lead, the sales leader and the legal reviewer>
systems: the order system (read), the CRM (read), the CRM (write),
the contract repository (read), the handover record (write),
the delivery system (write), the support system (read),
product usage data (read), the calendar (write),
the customer communication channel (write)
data: <your handover checklist> <version>, the booked order,
the executed agreement <version>, <your account picture
template>, <your escalation list>
policy:
no customer hears about the handover before the internal handover has
happened
a promise made during the sale is recorded whether or not the contract
carries it, and the ones the contract does not carry are decided by
<who> before the customer is told anything
the new owner is a named person, never a queue or a shared mailbox
the seller stays reachable to the new owner for <days> after the
customer confirms, and stays out of the customer conversation unless
the new owner asks them into it
a handover the customer has not confirmed is not counted as complete,
however many internal steps are done
an account with something open in dispute or in support is handed over
with that item named, and <who> is told before the introduction
the package is scored against the checklist at a version, and a
missing item is carried forward with a date rather than waived
silently
measures:
cycle time: <target> from booking to the customer's confirmation
repeat rate: <target> for questions the new owner had to ask the
customer again in the first <weeks>
volume: <handovers per period>
quality gate: no handover closes without the customer's dated
confirmation and the promise list marked binding or not
```
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/sls/hand-over-to-delivery 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.