Catalog / Business processes / Revenue operations / Deal-to-Approval / Approve a Discount
reference process · revenue-operations · 15 activities · 7 on the rosterApprove a Discount
A discount past the threshold cannot be given by the seller who asked for it. This process takes the ask, checks it carries its lines and its evidence, and starts a clock the seller can see. The published table says who may sign at that size. The price is checked against the rate card in force, the margin against the floor, and the ask against what this customer and this segment already got. A named signer approves, cuts it back, or refuses, and the reason is recorded against the deal. An ask that passes its promised time escalates rather than waiting.
The walk
The document
One run
Adoption
The activities
What happens in a run
15 activities from a discount past the threshold is asked for to the discount is approved or refused, with the reason recorded, 2 of them gates a person has to sign. Drag the diagram to move along it.
Approve a Discount a discount past the threshold is asked for → the discount is approved or refused, with the reason recorded
the ask carries no evidence the quote was priced at an old card the signer is away and has no delegate the promised time has run out the promised time has run out a smaller ask is worth testing signed above the level the seller comes back with a new ask a discount past the threshold is asked for 1 Take in the Discount Ask the ask, the deal, the evidence and the date wanted 2 Check the Ask Is Complete no ask moves without its lines, its reason and a date 3 Start the Clock the response time promised, in writing, to the seller 4 Find the Level That Appli… the published table read against the size of the ask 5 Check the Price as Asked every line re-priced at the card version in force 6 Check the Margin Against … the discounted deal set against the floor 7 Read the Evidence the competitor, the volume, the term, the reason 8 Test the Ask Against the … what this customer and this segment already got 9 Say What the Discount Cos… the renewal price, the expansion, the precedent set 10 Route to the Signer the ask goes to whoever the table says may sign it 11 Decide, and Say Why approved, cut back or refused, with the reason a person signs · never an agent 12 Escalate a Clock That Ran… an ask past its promised time goes up the line a person signs · never an agent 13 Record the Decision the decision, the reason and the signer, at a version 14 Tell the Seller and the Q… the answer goes back, and the quote is built on it 15 Report What the Discounts… approvals and refusals set against what deals did the discount is approved or refused, with the reason recorded 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: approve a discount id: <team> /approve-a-discount v1
from: ref/rev/approve-a-discount v1
owner: <who> effective: <date>
trigger: a quote in <your quoting process> asks for a discount past
<threshold> , or past the level the seller may give
watch: record=<quote> system=<your quoting system>
change=<a discount is asked for past the threshold or
past the level the seller may give>
concurrency: runs may overlap freely - <how many> asks are live at the
desk at once, and one quote has one open ask at a time
goal: every discount past the threshold approved, cut back or refused
by somebody the table says may sign it, with the reason recorded
against the deal, inside the time that level promised
phases:
take-in-ask - human: read the ask. Which lines, how much off
each one, on which deal, and the date the seller
needs an answer
owner: discount-approver after: trigger
automation: assisted
check-complete - runs assessment: the ask tested for the lines it
covers, the reason behind it, the evidence, and
the date it is needed
owner: discount-approver after: take-in-ask
by: <hours> automation: <level>
start-clock - system: the band is read off the published table,
the time that band promises is stamped on the ask,
and the seller is told both
owner: discount-approver after: check-complete
automation: autonomous
find-level - system: the size of the ask matched to a band on
the approval table at the version in force, and to
the signer and the delegate that band names
owner: standards-keeper after: start-clock
automation: autonomous
check-price - runs assessment: every discounted line re-priced
against the rate card at the version in force, so
the discount is measured off a real list price
owner: discount-approver after: find-level
by: <hours> automation: <level>
check-margin - runs assessment: the deal at the asked price set
against the cost floor and the margin threshold
<threshold>
owner: discount-approver after: check-price
automation: <level>
read-evidence - human: what is behind the ask. A competing bid, a
volume, a longer term, a payment change, or a
reason that is none of those
owner: discount-approver after: check-margin
automation: assisted
test-precedent - runs collect-and-report: what this customer, this
segment and this product already got, and what
the last <n> asks of this size were given
owner: analytics after: read-evidence
automation: <level>
cost-it-later - runs assessment: what the discount does to the
renewal price, to the next expansion, and to the
next deal that cites it
owner: analytics after: test-precedent
automation: <level>
route-to-signer - system: the ask goes to the signer the band names,
or to their delegate, with everything above it
attached
owner: discount-approver after: cost-it-later
automation: autonomous
decide - convenes approval: a named signer approves, cuts
the ask back, or refuses. The reason is written by
the signer, not by the desk
owner: <your approver role>
after: route-to-signer
by: <hours> automation: never
escalate-clock - human: an ask that has passed the time its band
promised goes to <who> with the ask, what it is
waiting on, and what the desk recommends
owner: <your deal desk role>
after: route-to-signer or decide, whichever ran out
by: <hours> automation: never
record-decision - system: the decision, the reason, the signer, the
band, and the version of the quote it was decided
against
owner: discount-approver after: decide
automation: autonomous
tell-the-seller - human: the seller is told what was decided and
why, and the quote is rebuilt on the approved
number rather than on the asked one
owner: discount-approver after: record-decision
automation: assisted
report-discounts - runs collect-and-report: what was approved, what
was refused, what it cost, and what the deals went
on to do
owner: reporting-manager after: tell-the-seller
by: <days> automation: <level>
run-scoped:
clock - runs roll-call owner: discount-approver
every: <cadence>
from: start-clock until: tell-the-seller
giveaway - runs allocate-and-reconcile owner: analytics
from: record-decision until: run close
handoffs:
take-in-ask -> check-complete [discount-ask]: the ask as the seller
wrote it, with the quote version it is asked against
check-complete -> start-clock [complete-ask]: the complete ask, with
anything that was missing and has since arrived
start-clock -> find-level [ask-size-and-clock]: the ask, its size on
each line and in total, and the hour the clock started
find-level -> check-price [band-and-signer]: the band, the signer it
names, the delegate, and the time that band promises
check-price -> check-margin [list-prices]: every line at its list
price, the card version it was read from, and the discount as a
number
check-margin -> read-evidence [margin-position]: the margin at the
asked price, and every line that sits below the floor
read-evidence -> test-precedent [ask-evidence]: the reason behind the
ask, and the evidence the seller supplied for it
test-precedent -> cost-it-later [precedent]: what was already given
to this customer and this segment, dated, with the deals it was
given on
cost-it-later -> route-to-signer [later-cost]: what the discount
costs at renewal and on the next deal, as a number where there is
one
route-to-signer -> decide [signer-packet]: the ask, the price, the
margin, the evidence, the precedent and the later cost, in one
packet
decide -> record-decision [signed-decision]: the decision, the number
approved, the reason in the signer's words, and the signer
escalate-clock -> decide [escalation-outcome]: the ask as it stood
when the clock ran out, and what was decided above the band
record-decision -> tell-the-seller [approved-number]: the approved
number at a version, with the approval attached to the quote
tell-the-seller -> report-discounts [ask-outcome]: what was asked,
what was given, and how long the answer took
deviations:
check-complete -> take-in-ask [ask-carries-no-evidence]: the ask
arrives with a number and nothing else, so it goes back to the
seller with what is missing listed
check-price -> take-in-ask [priced-at-old-card]: the quote was priced
against an old rate card, so the seller gets the current list price
and says whether the ask still stands
route-to-signer -> find-level [signer-away-no-delegate]: the signer
is away and the band names no delegate, so the table is read again
at the version in force
decide -> read-evidence [smaller-ask-worth-testing]: the signer would
approve a smaller number, and a different shape of ask is worth
testing against the evidence
escalate-clock -> decide [signed-above-the-level]: the escalation is
settled above the band, and the decision comes back to be recorded
as the decision on the ask
tell-the-seller -> take-in-ask [new-ask-from-seller]: the seller
comes back with a new ask, which is taken in as its own ask rather
than edited into this one
bindings:
roster: <who holds each role - agents claiming the abstract agents
above, and named people for the seller, the finance
approver, and the sales leader who hears an escalation>
systems: the quoting system (read), the CRM (read),
the approval record (write), the rate card store (read),
the cost model (read), the discount log (write),
the notification channel (write)
data: the approval table <version> , the rate card <version> ,
the discount schedule <version> , the cost floor <version> ,
the delegation of authority <version>
policy:
a seller never approves their own ask, and no ask is signed by
somebody the table does not name for that band
every ask is answered inside the time its band promises, and an ask
that passes <hours> escalates to <who> without the seller having to
chase it
a refusal names the number the signer would approve, or what would
have to change for the asked number to be given
approval is a human gate and is never delegated to an agent
the discount is measured against the rate card at a named version,
never against a previous quote
a quote changed after approval goes back through approval, and the
old approval is voided rather than carried across
a deal below the cost floor is not approved unless <who> accepts it
in writing and the acceptance is recorded against the deal
an ask with no evidence behind it is sent back inside <hours> rather
than being decided on the size of the number alone
measures:
response time: <target> from a complete ask to a decision, reported
every <cadence> and broken out by band
first answer: <hours> from the ask landing to the seller being told
the clock or told what is missing
breach rate: <target> share of asks that pass their promised time,
with the band and the signer named for each breach
discount given: <target> average discount, and the share of deals
that needed an approval at all
volume: <asks per period>
quality gate: no discount reaches a customer without a signer, a
reason and a band recorded against 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
312 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: approve a discount id: <team>/approve-a-discount v1
from: ref/rev/approve-a-discount v1
owner: <who> effective: <date>
trigger: a quote in <your quoting process> asks for a discount past
<threshold>, or past the level the seller may give
watch: record=<quote> system=<your quoting system>
change=<a discount is asked for past the threshold or
past the level the seller may give>
concurrency: runs may overlap freely - <how many> asks are live at the
desk at once, and one quote has one open ask at a time
goal: every discount past the threshold approved, cut back or refused
by somebody the table says may sign it, with the reason recorded
against the deal, inside the time that level promised
phases:
take-in-ask - human: read the ask. Which lines, how much off
each one, on which deal, and the date the seller
needs an answer
owner: discount-approver after: trigger
automation: assisted
check-complete - runs assessment: the ask tested for the lines it
covers, the reason behind it, the evidence, and
the date it is needed
owner: discount-approver after: take-in-ask
by: <hours> automation: <level>
start-clock - system: the band is read off the published table,
the time that band promises is stamped on the ask,
and the seller is told both
owner: discount-approver after: check-complete
automation: autonomous
find-level - system: the size of the ask matched to a band on
the approval table at the version in force, and to
the signer and the delegate that band names
owner: standards-keeper after: start-clock
automation: autonomous
check-price - runs assessment: every discounted line re-priced
against the rate card at the version in force, so
the discount is measured off a real list price
owner: discount-approver after: find-level
by: <hours> automation: <level>
check-margin - runs assessment: the deal at the asked price set
against the cost floor and the margin threshold
<threshold>
owner: discount-approver after: check-price
automation: <level>
read-evidence - human: what is behind the ask. A competing bid, a
volume, a longer term, a payment change, or a
reason that is none of those
owner: discount-approver after: check-margin
automation: assisted
test-precedent - runs collect-and-report: what this customer, this
segment and this product already got, and what
the last <n> asks of this size were given
owner: analytics after: read-evidence
automation: <level>
cost-it-later - runs assessment: what the discount does to the
renewal price, to the next expansion, and to the
next deal that cites it
owner: analytics after: test-precedent
automation: <level>
route-to-signer - system: the ask goes to the signer the band names,
or to their delegate, with everything above it
attached
owner: discount-approver after: cost-it-later
automation: autonomous
decide - convenes approval: a named signer approves, cuts
the ask back, or refuses. The reason is written by
the signer, not by the desk
owner: <your approver role>
after: route-to-signer
by: <hours> automation: never
escalate-clock - human: an ask that has passed the time its band
promised goes to <who> with the ask, what it is
waiting on, and what the desk recommends
owner: <your deal desk role>
after: route-to-signer or decide, whichever ran out
by: <hours> automation: never
record-decision - system: the decision, the reason, the signer, the
band, and the version of the quote it was decided
against
owner: discount-approver after: decide
automation: autonomous
tell-the-seller - human: the seller is told what was decided and
why, and the quote is rebuilt on the approved
number rather than on the asked one
owner: discount-approver after: record-decision
automation: assisted
report-discounts - runs collect-and-report: what was approved, what
was refused, what it cost, and what the deals went
on to do
owner: reporting-manager after: tell-the-seller
by: <days> automation: <level>
run-scoped:
clock - runs roll-call owner: discount-approver
every: <cadence>
from: start-clock until: tell-the-seller
giveaway - runs allocate-and-reconcile owner: analytics
from: record-decision until: run close
handoffs:
take-in-ask -> check-complete [discount-ask]: the ask as the seller
wrote it, with the quote version it is asked against
check-complete -> start-clock [complete-ask]: the complete ask, with
anything that was missing and has since arrived
start-clock -> find-level [ask-size-and-clock]: the ask, its size on
each line and in total, and the hour the clock started
find-level -> check-price [band-and-signer]: the band, the signer it
names, the delegate, and the time that band promises
check-price -> check-margin [list-prices]: every line at its list
price, the card version it was read from, and the discount as a
number
check-margin -> read-evidence [margin-position]: the margin at the
asked price, and every line that sits below the floor
read-evidence -> test-precedent [ask-evidence]: the reason behind the
ask, and the evidence the seller supplied for it
test-precedent -> cost-it-later [precedent]: what was already given
to this customer and this segment, dated, with the deals it was
given on
cost-it-later -> route-to-signer [later-cost]: what the discount
costs at renewal and on the next deal, as a number where there is
one
route-to-signer -> decide [signer-packet]: the ask, the price, the
margin, the evidence, the precedent and the later cost, in one
packet
decide -> record-decision [signed-decision]: the decision, the number
approved, the reason in the signer's words, and the signer
escalate-clock -> decide [escalation-outcome]: the ask as it stood
when the clock ran out, and what was decided above the band
record-decision -> tell-the-seller [approved-number]: the approved
number at a version, with the approval attached to the quote
tell-the-seller -> report-discounts [ask-outcome]: what was asked,
what was given, and how long the answer took
deviations:
check-complete -> take-in-ask [ask-carries-no-evidence]: the ask
arrives with a number and nothing else, so it goes back to the
seller with what is missing listed
check-price -> take-in-ask [priced-at-old-card]: the quote was priced
against an old rate card, so the seller gets the current list price
and says whether the ask still stands
route-to-signer -> find-level [signer-away-no-delegate]: the signer
is away and the band names no delegate, so the table is read again
at the version in force
decide -> read-evidence [smaller-ask-worth-testing]: the signer would
approve a smaller number, and a different shape of ask is worth
testing against the evidence
escalate-clock -> decide [signed-above-the-level]: the escalation is
settled above the band, and the decision comes back to be recorded
as the decision on the ask
tell-the-seller -> take-in-ask [new-ask-from-seller]: the seller
comes back with a new ask, which is taken in as its own ask rather
than edited into this one
bindings:
roster: <who holds each role - agents claiming the abstract agents
above, and named people for the seller, the finance
approver, and the sales leader who hears an escalation>
systems: the quoting system (read), the CRM (read),
the approval record (write), the rate card store (read),
the cost model (read), the discount log (write),
the notification channel (write)
data: the approval table <version>, the rate card <version>,
the discount schedule <version>, the cost floor <version>,
the delegation of authority <version>
policy:
a seller never approves their own ask, and no ask is signed by
somebody the table does not name for that band
every ask is answered inside the time its band promises, and an ask
that passes <hours> escalates to <who> without the seller having to
chase it
a refusal names the number the signer would approve, or what would
have to change for the asked number to be given
approval is a human gate and is never delegated to an agent
the discount is measured against the rate card at a named version,
never against a previous quote
a quote changed after approval goes back through approval, and the
old approval is voided rather than carried across
a deal below the cost floor is not approved unless <who> accepts it
in writing and the acceptance is recorded against the deal
an ask with no evidence behind it is sent back inside <hours> rather
than being decided on the size of the number alone
measures:
response time: <target> from a complete ask to a decision, reported
every <cadence> and broken out by band
first answer: <hours> from the ask landing to the seller being told
the clock or told what is missing
breach rate: <target> share of asks that pass their promised time,
with the band and the signer named for each breach
discount given: <target> average discount, and the share of deals
that needed an approval at all
volume: <asks per period>
quality gate: no discount reaches a customer without a signer, a
reason and a band recorded against 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
367 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: approve a discount id: <team>/approve-a-discount v1
from: ref/rev/approve-a-discount v1
owner: <who> effective: <date>
trigger: a quote in <your quoting process> asks for a discount past
<threshold>, or past the level the seller may give
watch: record=<quote> system=<your quoting system>
change=<a discount is asked for past the threshold or
past the level the seller may give>
concurrency: runs may overlap freely - <how many> asks are live at the
desk at once, and one quote has one open ask at a time
goal: every discount past the threshold approved, cut back or refused
by somebody the table says may sign it, with the reason recorded
against the deal, inside the time that level promised
phases:
take-in-ask - human: read the ask. Which lines, how much off
each one, on which deal, and the date the seller
needs an answer
owner: discount-approver after: trigger
automation: assisted
check-complete - runs assessment: the ask tested for the lines it
covers, the reason behind it, the evidence, and
the date it is needed
owner: discount-approver after: take-in-ask
by: <hours> automation: <level>
start-clock - system: the band is read off the published table,
the time that band promises is stamped on the ask,
and the seller is told both
owner: discount-approver after: check-complete
automation: autonomous
find-level - system: the size of the ask matched to a band on
the approval table at the version in force, and to
the signer and the delegate that band names
owner: standards-keeper after: start-clock
automation: autonomous
check-price - runs assessment: every discounted line re-priced
against the rate card at the version in force, so
the discount is measured off a real list price
owner: discount-approver after: find-level
by: <hours> automation: <level>
check-margin - runs assessment: the deal at the asked price set
against the cost floor and the margin threshold
<threshold>
owner: discount-approver after: check-price
automation: <level>
read-evidence - human: what is behind the ask. A competing bid, a
volume, a longer term, a payment change, or a
reason that is none of those
owner: discount-approver after: check-margin
automation: assisted
test-precedent - runs collect-and-report: what this customer, this
segment and this product already got, and what
the last <n> asks of this size were given
owner: analytics after: read-evidence
automation: <level>
cost-it-later - runs assessment: what the discount does to the
renewal price, to the next expansion, and to the
next deal that cites it
owner: analytics after: test-precedent
automation: <level>
route-to-signer - system: the ask goes to the signer the band names,
or to their delegate, with everything above it
attached
owner: discount-approver after: cost-it-later
automation: autonomous
decide - convenes approval: a named signer approves, cuts
the ask back, or refuses. The reason is written by
the signer, not by the desk
owner: <your approver role>
after: route-to-signer
by: <hours> automation: never
escalate-clock - human: an ask that has passed the time its band
promised goes to <who> with the ask, what it is
waiting on, and what the desk recommends
owner: <your deal desk role>
after: route-to-signer or decide, whichever ran out
by: <hours> automation: never
record-decision - system: the decision, the reason, the signer, the
band, and the version of the quote it was decided
against
owner: discount-approver after: decide
automation: autonomous
tell-the-seller - human: the seller is told what was decided and
why, and the quote is rebuilt on the approved
number rather than on the asked one
owner: discount-approver after: record-decision
automation: assisted
report-discounts - runs collect-and-report: what was approved, what
was refused, what it cost, and what the deals went
on to do
owner: reporting-manager after: tell-the-seller
by: <days> automation: <level>
run-scoped:
clock - runs roll-call owner: discount-approver
every: <cadence>
from: start-clock until: tell-the-seller
giveaway - runs allocate-and-reconcile owner: analytics
from: record-decision until: run close
handoffs:
take-in-ask -> check-complete [discount-ask]: the ask as the seller
wrote it, with the quote version it is asked against
check-complete -> start-clock [complete-ask]: the complete ask, with
anything that was missing and has since arrived
start-clock -> find-level [ask-size-and-clock]: the ask, its size on
each line and in total, and the hour the clock started
find-level -> check-price [band-and-signer]: the band, the signer it
names, the delegate, and the time that band promises
check-price -> check-margin [list-prices]: every line at its list
price, the card version it was read from, and the discount as a
number
check-margin -> read-evidence [margin-position]: the margin at the
asked price, and every line that sits below the floor
read-evidence -> test-precedent [ask-evidence]: the reason behind the
ask, and the evidence the seller supplied for it
test-precedent -> cost-it-later [precedent]: what was already given
to this customer and this segment, dated, with the deals it was
given on
cost-it-later -> route-to-signer [later-cost]: what the discount
costs at renewal and on the next deal, as a number where there is
one
route-to-signer -> decide [signer-packet]: the ask, the price, the
margin, the evidence, the precedent and the later cost, in one
packet
decide -> record-decision [signed-decision]: the decision, the number
approved, the reason in the signer's words, and the signer
escalate-clock -> decide [escalation-outcome]: the ask as it stood
when the clock ran out, and what was decided above the band
record-decision -> tell-the-seller [approved-number]: the approved
number at a version, with the approval attached to the quote
tell-the-seller -> report-discounts [ask-outcome]: what was asked,
what was given, and how long the answer took
deviations:
check-complete -> take-in-ask [ask-carries-no-evidence]: the ask
arrives with a number and nothing else, so it goes back to the
seller with what is missing listed
check-price -> take-in-ask [priced-at-old-card]: the quote was priced
against an old rate card, so the seller gets the current list price
and says whether the ask still stands
route-to-signer -> find-level [signer-away-no-delegate]: the signer
is away and the band names no delegate, so the table is read again
at the version in force
decide -> read-evidence [smaller-ask-worth-testing]: the signer would
approve a smaller number, and a different shape of ask is worth
testing against the evidence
escalate-clock -> decide [signed-above-the-level]: the escalation is
settled above the band, and the decision comes back to be recorded
as the decision on the ask
tell-the-seller -> take-in-ask [new-ask-from-seller]: the seller
comes back with a new ask, which is taken in as its own ask rather
than edited into this one
bindings:
roster: <who holds each role - agents claiming the abstract agents
above, and named people for the seller, the finance
approver, and the sales leader who hears an escalation>
systems: the quoting system (read), the CRM (read),
the approval record (write), the rate card store (read),
the cost model (read), the discount log (write),
the notification channel (write)
data: the approval table <version>, the rate card <version>,
the discount schedule <version>, the cost floor <version>,
the delegation of authority <version>
policy:
a seller never approves their own ask, and no ask is signed by
somebody the table does not name for that band
every ask is answered inside the time its band promises, and an ask
that passes <hours> escalates to <who> without the seller having to
chase it
a refusal names the number the signer would approve, or what would
have to change for the asked number to be given
approval is a human gate and is never delegated to an agent
the discount is measured against the rate card at a named version,
never against a previous quote
a quote changed after approval goes back through approval, and the
old approval is voided rather than carried across
a deal below the cost floor is not approved unless <who> accepts it
in writing and the acceptance is recorded against the deal
an ask with no evidence behind it is sent back inside <hours> rather
than being decided on the size of the number alone
measures:
response time: <target> from a complete ask to a decision, reported
every <cadence> and broken out by band
first answer: <hours> from the ask landing to the seller being told
the clock or told what is missing
breach rate: <target> share of asks that pass their promised time,
with the band and the signer named for each breach
discount given: <target> average discount, and the share of deals
that needed an approval at all
volume: <asks per period>
quality gate: no discount reaches a customer without a signer, a
reason and a band recorded against 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
372 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: approve a discount id: <team>/approve-a-discount v1
from: ref/rev/approve-a-discount v1
owner: <who> effective: <date>
trigger: a quote in <your quoting process> asks for a discount past
<threshold>, or past the level the seller may give
watch: record=<quote> system=<your quoting system>
change=<a discount is asked for past the threshold or
past the level the seller may give>
concurrency: runs may overlap freely - <how many> asks are live at the
desk at once, and one quote has one open ask at a time
goal: every discount past the threshold approved, cut back or refused
by somebody the table says may sign it, with the reason recorded
against the deal, inside the time that level promised
phases:
take-in-ask - human: read the ask. Which lines, how much off
each one, on which deal, and the date the seller
needs an answer
owner: discount-approver after: trigger
automation: assisted
check-complete - runs assessment: the ask tested for the lines it
covers, the reason behind it, the evidence, and
the date it is needed
owner: discount-approver after: take-in-ask
by: <hours> automation: <level>
start-clock - system: the band is read off the published table,
the time that band promises is stamped on the ask,
and the seller is told both
owner: discount-approver after: check-complete
automation: autonomous
find-level - system: the size of the ask matched to a band on
the approval table at the version in force, and to
the signer and the delegate that band names
owner: standards-keeper after: start-clock
automation: autonomous
check-price - runs assessment: every discounted line re-priced
against the rate card at the version in force, so
the discount is measured off a real list price
owner: discount-approver after: find-level
by: <hours> automation: <level>
check-margin - runs assessment: the deal at the asked price set
against the cost floor and the margin threshold
<threshold>
owner: discount-approver after: check-price
automation: <level>
read-evidence - human: what is behind the ask. A competing bid, a
volume, a longer term, a payment change, or a
reason that is none of those
owner: discount-approver after: check-margin
automation: assisted
test-precedent - runs collect-and-report: what this customer, this
segment and this product already got, and what
the last <n> asks of this size were given
owner: analytics after: read-evidence
automation: <level>
cost-it-later - runs assessment: what the discount does to the
renewal price, to the next expansion, and to the
next deal that cites it
owner: analytics after: test-precedent
automation: <level>
route-to-signer - system: the ask goes to the signer the band names,
or to their delegate, with everything above it
attached
owner: discount-approver after: cost-it-later
automation: autonomous
decide - convenes approval: a named signer approves, cuts
the ask back, or refuses. The reason is written by
the signer, not by the desk
owner: <your approver role>
after: route-to-signer
by: <hours> automation: never
escalate-clock - human: an ask that has passed the time its band
promised goes to <who> with the ask, what it is
waiting on, and what the desk recommends
owner: <your deal desk role>
after: route-to-signer or decide, whichever ran out
by: <hours> automation: never
record-decision - system: the decision, the reason, the signer, the
band, and the version of the quote it was decided
against
owner: discount-approver after: decide
automation: autonomous
tell-the-seller - human: the seller is told what was decided and
why, and the quote is rebuilt on the approved
number rather than on the asked one
owner: discount-approver after: record-decision
automation: assisted
report-discounts - runs collect-and-report: what was approved, what
was refused, what it cost, and what the deals went
on to do
owner: reporting-manager after: tell-the-seller
by: <days> automation: <level>
run-scoped:
clock - runs roll-call owner: discount-approver
every: <cadence>
from: start-clock until: tell-the-seller
giveaway - runs allocate-and-reconcile owner: analytics
from: record-decision until: run close
handoffs:
take-in-ask -> check-complete [discount-ask]: the ask as the seller
wrote it, with the quote version it is asked against
check-complete -> start-clock [complete-ask]: the complete ask, with
anything that was missing and has since arrived
start-clock -> find-level [ask-size-and-clock]: the ask, its size on
each line and in total, and the hour the clock started
find-level -> check-price [band-and-signer]: the band, the signer it
names, the delegate, and the time that band promises
check-price -> check-margin [list-prices]: every line at its list
price, the card version it was read from, and the discount as a
number
check-margin -> read-evidence [margin-position]: the margin at the
asked price, and every line that sits below the floor
read-evidence -> test-precedent [ask-evidence]: the reason behind the
ask, and the evidence the seller supplied for it
test-precedent -> cost-it-later [precedent]: what was already given
to this customer and this segment, dated, with the deals it was
given on
cost-it-later -> route-to-signer [later-cost]: what the discount
costs at renewal and on the next deal, as a number where there is
one
route-to-signer -> decide [signer-packet]: the ask, the price, the
margin, the evidence, the precedent and the later cost, in one
packet
decide -> record-decision [signed-decision]: the decision, the number
approved, the reason in the signer's words, and the signer
escalate-clock -> decide [escalation-outcome]: the ask as it stood
when the clock ran out, and what was decided above the band
record-decision -> tell-the-seller [approved-number]: the approved
number at a version, with the approval attached to the quote
tell-the-seller -> report-discounts [ask-outcome]: what was asked,
what was given, and how long the answer took
deviations:
check-complete -> take-in-ask [ask-carries-no-evidence]: the ask
arrives with a number and nothing else, so it goes back to the
seller with what is missing listed
check-price -> take-in-ask [priced-at-old-card]: the quote was priced
against an old rate card, so the seller gets the current list price
and says whether the ask still stands
route-to-signer -> find-level [signer-away-no-delegate]: the signer
is away and the band names no delegate, so the table is read again
at the version in force
decide -> read-evidence [smaller-ask-worth-testing]: the signer would
approve a smaller number, and a different shape of ask is worth
testing against the evidence
escalate-clock -> decide [signed-above-the-level]: the escalation is
settled above the band, and the decision comes back to be recorded
as the decision on the ask
tell-the-seller -> take-in-ask [new-ask-from-seller]: the seller
comes back with a new ask, which is taken in as its own ask rather
than edited into this one
bindings:
roster: <who holds each role - agents claiming the abstract agents
above, and named people for the seller, the finance
approver, and the sales leader who hears an escalation>
systems: the quoting system (read), the CRM (read),
the approval record (write), the rate card store (read),
the cost model (read), the discount log (write),
the notification channel (write)
data: the approval table <version>, the rate card <version>,
the discount schedule <version>, the cost floor <version>,
the delegation of authority <version>
policy:
a seller never approves their own ask, and no ask is signed by
somebody the table does not name for that band
every ask is answered inside the time its band promises, and an ask
that passes <hours> escalates to <who> without the seller having to
chase it
a refusal names the number the signer would approve, or what would
have to change for the asked number to be given
approval is a human gate and is never delegated to an agent
the discount is measured against the rate card at a named version,
never against a previous quote
a quote changed after approval goes back through approval, and the
old approval is voided rather than carried across
a deal below the cost floor is not approved unless <who> accepts it
in writing and the acceptance is recorded against the deal
an ask with no evidence behind it is sent back inside <hours> rather
than being decided on the size of the number alone
measures:
response time: <target> from a complete ask to a decision, reported
every <cadence> and broken out by band
first answer: <hours> from the ask landing to the seller being told
the clock or told what is missing
breach rate: <target> share of asks that pass their promised time,
with the band and the signer named for each breach
discount given: <target> average discount, and the share of deals
that needed an approval at all
volume: <asks per period>
quality gate: no discount reaches a customer without a signer, a
reason and a band recorded against 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
363 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: approve a discount id: <team>/approve-a-discount v1
from: ref/rev/approve-a-discount v1
owner: <who> effective: <date>
trigger: a quote in <your quoting process> asks for a discount past
<threshold>, or past the level the seller may give
watch: record=<quote> system=<your quoting system>
change=<a discount is asked for past the threshold or
past the level the seller may give>
concurrency: runs may overlap freely - <how many> asks are live at the
desk at once, and one quote has one open ask at a time
goal: every discount past the threshold approved, cut back or refused
by somebody the table says may sign it, with the reason recorded
against the deal, inside the time that level promised
phases:
take-in-ask - human: read the ask. Which lines, how much off
each one, on which deal, and the date the seller
needs an answer
owner: discount-approver after: trigger
automation: assisted
check-complete - runs assessment: the ask tested for the lines it
covers, the reason behind it, the evidence, and
the date it is needed
owner: discount-approver after: take-in-ask
by: <hours> automation: <level>
start-clock - system: the band is read off the published table,
the time that band promises is stamped on the ask,
and the seller is told both
owner: discount-approver after: check-complete
automation: autonomous
find-level - system: the size of the ask matched to a band on
the approval table at the version in force, and to
the signer and the delegate that band names
owner: standards-keeper after: start-clock
automation: autonomous
check-price - runs assessment: every discounted line re-priced
against the rate card at the version in force, so
the discount is measured off a real list price
owner: discount-approver after: find-level
by: <hours> automation: <level>
check-margin - runs assessment: the deal at the asked price set
against the cost floor and the margin threshold
<threshold>
owner: discount-approver after: check-price
automation: <level>
read-evidence - human: what is behind the ask. A competing bid, a
volume, a longer term, a payment change, or a
reason that is none of those
owner: discount-approver after: check-margin
automation: assisted
test-precedent - runs collect-and-report: what this customer, this
segment and this product already got, and what
the last <n> asks of this size were given
owner: analytics after: read-evidence
automation: <level>
cost-it-later - runs assessment: what the discount does to the
renewal price, to the next expansion, and to the
next deal that cites it
owner: analytics after: test-precedent
automation: <level>
route-to-signer - system: the ask goes to the signer the band names,
or to their delegate, with everything above it
attached
owner: discount-approver after: cost-it-later
automation: autonomous
decide - convenes approval: a named signer approves, cuts
the ask back, or refuses. The reason is written by
the signer, not by the desk
owner: <your approver role>
after: route-to-signer
by: <hours> automation: never
escalate-clock - human: an ask that has passed the time its band
promised goes to <who> with the ask, what it is
waiting on, and what the desk recommends
owner: <your deal desk role>
after: route-to-signer or decide, whichever ran out
by: <hours> automation: never
record-decision - system: the decision, the reason, the signer, the
band, and the version of the quote it was decided
against
owner: discount-approver after: decide
automation: autonomous
tell-the-seller - human: the seller is told what was decided and
why, and the quote is rebuilt on the approved
number rather than on the asked one
owner: discount-approver after: record-decision
automation: assisted
report-discounts - runs collect-and-report: what was approved, what
was refused, what it cost, and what the deals went
on to do
owner: reporting-manager after: tell-the-seller
by: <days> automation: <level>
run-scoped:
clock - runs roll-call owner: discount-approver
every: <cadence>
from: start-clock until: tell-the-seller
giveaway - runs allocate-and-reconcile owner: analytics
from: record-decision until: run close
handoffs:
take-in-ask -> check-complete [discount-ask]: the ask as the seller
wrote it, with the quote version it is asked against
check-complete -> start-clock [complete-ask]: the complete ask, with
anything that was missing and has since arrived
start-clock -> find-level [ask-size-and-clock]: the ask, its size on
each line and in total, and the hour the clock started
find-level -> check-price [band-and-signer]: the band, the signer it
names, the delegate, and the time that band promises
check-price -> check-margin [list-prices]: every line at its list
price, the card version it was read from, and the discount as a
number
check-margin -> read-evidence [margin-position]: the margin at the
asked price, and every line that sits below the floor
read-evidence -> test-precedent [ask-evidence]: the reason behind the
ask, and the evidence the seller supplied for it
test-precedent -> cost-it-later [precedent]: what was already given
to this customer and this segment, dated, with the deals it was
given on
cost-it-later -> route-to-signer [later-cost]: what the discount
costs at renewal and on the next deal, as a number where there is
one
route-to-signer -> decide [signer-packet]: the ask, the price, the
margin, the evidence, the precedent and the later cost, in one
packet
decide -> record-decision [signed-decision]: the decision, the number
approved, the reason in the signer's words, and the signer
escalate-clock -> decide [escalation-outcome]: the ask as it stood
when the clock ran out, and what was decided above the band
record-decision -> tell-the-seller [approved-number]: the approved
number at a version, with the approval attached to the quote
tell-the-seller -> report-discounts [ask-outcome]: what was asked,
what was given, and how long the answer took
deviations:
check-complete -> take-in-ask [ask-carries-no-evidence]: the ask
arrives with a number and nothing else, so it goes back to the
seller with what is missing listed
check-price -> take-in-ask [priced-at-old-card]: the quote was priced
against an old rate card, so the seller gets the current list price
and says whether the ask still stands
route-to-signer -> find-level [signer-away-no-delegate]: the signer
is away and the band names no delegate, so the table is read again
at the version in force
decide -> read-evidence [smaller-ask-worth-testing]: the signer would
approve a smaller number, and a different shape of ask is worth
testing against the evidence
escalate-clock -> decide [signed-above-the-level]: the escalation is
settled above the band, and the decision comes back to be recorded
as the decision on the ask
tell-the-seller -> take-in-ask [new-ask-from-seller]: the seller
comes back with a new ask, which is taken in as its own ask rather
than edited into this one
bindings:
roster: <who holds each role - agents claiming the abstract agents
above, and named people for the seller, the finance
approver, and the sales leader who hears an escalation>
systems: the quoting system (read), the CRM (read),
the approval record (write), the rate card store (read),
the cost model (read), the discount log (write),
the notification channel (write)
data: the approval table <version>, the rate card <version>,
the discount schedule <version>, the cost floor <version>,
the delegation of authority <version>
policy:
a seller never approves their own ask, and no ask is signed by
somebody the table does not name for that band
every ask is answered inside the time its band promises, and an ask
that passes <hours> escalates to <who> without the seller having to
chase it
a refusal names the number the signer would approve, or what would
have to change for the asked number to be given
approval is a human gate and is never delegated to an agent
the discount is measured against the rate card at a named version,
never against a previous quote
a quote changed after approval goes back through approval, and the
old approval is voided rather than carried across
a deal below the cost floor is not approved unless <who> accepts it
in writing and the acceptance is recorded against the deal
an ask with no evidence behind it is sent back inside <hours> rather
than being decided on the size of the number alone
measures:
response time: <target> from a complete ask to a decision, reported
every <cadence> and broken out by band
first answer: <hours> from the ask landing to the seller being told
the clock or told what is missing
breach rate: <target> share of asks that pass their promised time,
with the band and the signer named for each breach
discount given: <target> average discount, and the share of deals
that needed an approval at all
volume: <asks per period>
quality gate: no discount reaches a customer without a signer, a
reason and a band recorded against 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
40 blanks to fill. Everything else is the process.
this process
from: ref/rev/approve-a-discount 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.