Catalog / Business processes / Marketing / Objective-to-Commitment / Brief Executive Leadership
reference process · marketing · 20 activities · 17 on the rosterBrief Executive Leadership
A board meeting or an executive review is coming, and marketing has to arrive with something the people in the room can decide from. The decision coordinator works out what marketing is asking them to settle, commissions the results, the money, the book of work and the outside picture from the agents that hold each one, has the position written into a paper for each decision, gets the pack signed and sent ahead, and runs the meeting where the decisions are put. The run stays open after the meeting ends, because every decision still has to be written down with its reasons, every question the room left open still has to be answered in writing, and every agent that acts on a decision still has to hear it. This process is a different job from the department's quarterly review. In that review marketing examines its own quarter and resets what each area is held to. This process goes outside the department, to a board or an executive team, and it asks those people to take the decisions marketing cannot take on its own.
The walk
The document
One run
Adoption
The activities
What happens in a run
20 activities from a board or executive cycle opens to the position is understood and every decision is recorded, 4 of them gates a person has to sign. Drag the diagram to move along it.
Brief Executive Leadership a board or executive cycle opens → the position is understood and every decision is recorded
the data will not carry the figure a rate nobody can source the evidence will not support the ask changes requested changes requested a member asks before the room the answer is not in the pack the answer changes what was decided a board or executive cycle opens 1 Take in the Cycle what the board asked for, and when it meets 2 Read the Last Meeting's R… the standing questions and the commitments made 3 Work out What Has to Be D… the decisions marketing is asking the board for a person signs · never an agent 4 Pull the Results for the … what the department did, with a source on every line 5 Say What the Numbers Carry which figures hold and how far they can be read 6 Account for the Money what was allocated, what was drawn, what is left 7 Account for the Book of W… what is committed and what room is left 8 Gather the Outside Picture the market, the competitors, and what buyers say 9 Put Numbers on the Choices cost and return for each option, and what they rest on 10 Settle Marketing's Positi… what marketing will say and what it will ask for a person signs · never an agent 11 Write the Decision Papers one paper per decision, with its options 12 Build the Pack the pages the board reads, in one document 13 Get Sign-Offs brand, legal and leadership approve the pack a person signs · never an agent 14 Send the Pack Ahead the board gets time to read it before the room 15 Rehearse the Briefing the hard questions get asked before the board asks 16 Deliver the Briefing marketing presents and the board decides a person signs · never an agent 17 Record the Decisions each decision, its reasons, and who disagreed 18 Answer What Was Left Open the questions the room could not settle 19 Hand the Decisions On every agent that has to act hears what was decided 20 Record What Was Learned what to repeat, what to avoid the position is understood and every decision is 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: brief executive leadership id: <team> /brief-executive-leadership v1
from: ref/mkt/brief-executive-leadership v1
owner: <who> effective: <date>
trigger: a board or executive cycle opens on <your board calendar>
watch: record=<the meeting> system=<your board calendar>
change=<a cycle opens with a meeting date and what
marketing is asked to bring>
concurrency: one run per meeting - a board cycle and an executive
review are separate runs and may overlap
goal: a board or an executive team that understands where marketing
stands, and every decision marketing asked for either taken and
recorded or declined with a reason
phases:
take-in-cycle - human: read what the board asked marketing to
bring, and write down the date it meets and the
date the pack is due
owner: decision-coordinator after: trigger
automation: <level>
read-last-record - human: the questions the board left open last
time, and the commitments marketing made in front
of it
owner: decision-coordinator
after: take-in-cycle automation: <level>
set-decisions - convenes briefing: what marketing is asking the
board to settle, heard at once by every agent that
owes evidence toward it
owner: decision-coordinator
after: read-last-record automation: never
pull-results - runs collect-and-report: what the department did
in the period, each line carrying its source and
the date it was pulled
owner: reporting-manager after: set-decisions
by: <days> automation: <level>
qualify-numbers - runs assessment: which figures hold, the range
around each one, and which cannot be computed
from the data there is
owner: statistician after: pull-results
by: <days> automation: <level>
account-money - human: what each function was allocated, what has
been drawn against it, and what is left
owner: budget-keeper after: set-decisions
by: <days> automation: <level>
account-work - human: what the department has already committed
for the period ahead, and what room is left in it
owner: capacity-manager after: set-decisions
by: <days> automation: <level>
outside-picture - runs build-by-talent: the market, the competitors
and what buyers have been saying, every fact
carrying the source under it
owner: researcher after: set-decisions
by: <weeks> automation: <level>
size-choices - runs build-by-talent: what each option would cost
and return at each level of spend, with the
assumptions written beside every number
owner: forecaster
after: qualify-numbers + account-money +
account-work + outside-picture
by: <days> automation: <level>
settle-position - convenes decide-and-announce: what marketing will
say to the board, and what it will ask for
owner: decision-coordinator after: size-choices
automation: never
write-papers - human: one paper for each decision, saying what
is being asked, the options, and what each option
would rule out
owner: copywriter
after: settle-position
by: <days> automation: <level>
build-pack - runs build-by-talent: the papers, the figures and
the charts assembled into the one document the
board reads
owner: designer after: write-papers
by: <days> automation: <level>
get-sign-offs - convenes approval: brand, legal and <who> sign, as
named signers, against a version of the pack
owner: <your legal role> after: build-pack
by: <days> automation: never
send-ahead - human: the signed pack reaches every member with
enough days in front of the meeting to be read
owner: decision-coordinator after: get-sign-offs
by: <days> automation: <level>
rehearse - runs layered-passes: the hard questions asked
against the pack, and the answer to each one
written down
owner: editor after: send-ahead
by: <days> automation: <level>
deliver-briefing - convenes decide-and-announce: the position is
presented, each decision is put to the room, and
the answer is said out loud there
owner: decision-coordinator after: rehearse
automation: never
record-decisions - human: each decision at a version, naming who
decided it, on what reasons, and anyone who
disagreed and what they said
owner: decision-coordinator
after: deliver-briefing
by: <days> automation: <level>
answer-open - runs collect-and-report: the questions the room
could not settle, each answered in writing with
the source under the answer
owner: decision-coordinator
after: deliver-briefing
by: <days> automation: <level>
hand-on - convenes decide-and-announce: every agent that has
to act hears the decision and the date it applies
from
owner: decision-coordinator
after: record-decisions + answer-open
automation: <level>
record-learnings - convenes debrief: what to repeat, what to avoid
owner: decision-coordinator after: hand-on
automation: <level>
run-scoped:
status - runs roll-call owner: decision-coordinator
every: <cadence>
from: set-decisions until: get-sign-offs
handoffs:
take-in-cycle -> read-last-record [dates-and-ask]: the date the
board meets, the date the pack is due, and what the board asked
marketing to bring
read-last-record -> set-decisions [last-meeting-record]: the
questions the board left open last time, and the commitments
marketing made in front of it
set-decisions -> pull-results / account-money / account-work /
outside-picture [decisions-asked-for]: the decisions being asked
for and the date the evidence is due. Four branches read one
record
pull-results -> qualify-numbers [period-results]: the results, each
line naming its source and the date it was pulled
qualify-numbers -> size-choices [qualified-figures]: the figures
that hold, the range around each one, every exclusion and the rule
behind it, and every figure marked uncomputed
account-money -> size-choices [money-account]: what each function
was allocated, what has been drawn against it, and what is left
account-work -> size-choices [work-account]: what the department has
committed for the period ahead, and what a new commitment would
displace
outside-picture -> size-choices [market-picture]: the market and the
competitors, each fact carrying its source and the date it was
read
size-choices -> settle-position [costed-options]: what each option
would cost and return, with the assumptions beside the numbers and
every rate that could not be sourced marked unsourced
settle-position -> write-papers [marketing-position]: what marketing
will say, and the decision it wants against each option
write-papers -> build-pack [decision-papers]: the papers at a
version, one for each decision
build-pack -> get-sign-offs [the-pack]: the pack at a version, as
the board will read it
get-sign-offs -> send-ahead [signed-pack]: the pack at the signed
version. A later change voids the approval and the signers see it
again
send-ahead -> rehearse [pack-as-sent]: the pack as the board
received it, and the date each member received it
rehearse -> deliver-briefing [rehearsal-answers]: the questions the
rehearsal asked, and the answer given to each one
deliver-briefing -> record-decisions [what-the-room-decided]: what
the room decided, on what reasons, and what it declined to decide
deliver-briefing -> answer-open [open-questions]: the questions the
room could not settle, each with the date its answer is due
record-decisions -> hand-on [recorded-decisions]: each decision at a
version, naming the agents that have to act on it
answer-open -> hand-on [written-answers]: the written answer to each
open question, with the source under it
hand-on -> record-learnings [what-agents-took-away]: what each agent
took away, and anything an agent said it could not do
deviations:
qualify-numbers -> pull-results [figure-will-not-carry]: the data
will not carry a figure the pack wants to claim, so the results
are pulled again for what will carry it
size-choices -> outside-picture [rate-with-no-source]: a choice
rests on a rate nobody can source, so the outside picture is
gathered again for it
settle-position -> size-choices [evidence-will-not-support-the-ask]:
the evidence will not support the ask, so the choices are sized
again
get-sign-offs -> write-papers [paper-changes]: a signer comes back
with changes to a decision paper
get-sign-offs -> build-pack [pack-changes]: a signer comes back with
changes to the pack
send-ahead -> write-papers [question-before-the-room]: a board
member asks a question before the meeting, and the answer goes
into the papers so every member gets it
rehearse -> write-papers [pack-cannot-answer]: the rehearsal finds a
question the pack cannot answer, so the papers either answer it or
say when they will
answer-open -> record-decisions [answer-changes-the-decision]: an
answer given after the meeting changes what was decided, so the
decision is recorded again at a new version
bindings:
roster: <who holds each role - agents claiming the abstract agents
above, and named people for the board, leadership, legal
and finance>
systems: the decision record (write), the report store (read),
the budget record (read), the book of work (read),
the model store (write), the calculation record (write),
the source record (write), the asset store (write),
analytics platforms (read), the notification channel
(write), the meeting calendar (write)
data: the record of the last meeting, the closed periods'
reports, what the department committed to for the period,
the marketing standards at their versions, <your measure
definitions> at a version, the board calendar
policy:
every figure in the pack names the source or the model version it
came from
a figure that cannot be computed from the data there is appears in
the pack as uncomputed, and nobody fills it in
a rate the model cannot source appears in the pack as unsourced
a difference inside the noise of the measurement is never presented
as a result
the decisions belong to the people in the room and are never
delegated to an agent
every decision is recorded with its reasons and with anyone who
disagreed, and a recorded decision changes only as a new version
the pack goes to the board only at the version the signers signed
a question the room could not settle gets a written answer by
<when> , rather than waiting for the next cycle
measures:
cycle time: <weeks> from the cycle opening to the briefing
coverage: <share> of the decisions asked for that came back decided
quality gate: every figure in the pack carries its source, and every
decision leaves a record
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
346 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: brief executive leadership id: <team>/brief-executive-leadership v1
from: ref/mkt/brief-executive-leadership v1
owner: <who> effective: <date>
trigger: a board or executive cycle opens on <your board calendar>
watch: record=<the meeting> system=<your board calendar>
change=<a cycle opens with a meeting date and what
marketing is asked to bring>
concurrency: one run per meeting - a board cycle and an executive
review are separate runs and may overlap
goal: a board or an executive team that understands where marketing
stands, and every decision marketing asked for either taken and
recorded or declined with a reason
phases:
take-in-cycle - human: read what the board asked marketing to
bring, and write down the date it meets and the
date the pack is due
owner: decision-coordinator after: trigger
automation: <level>
read-last-record - human: the questions the board left open last
time, and the commitments marketing made in front
of it
owner: decision-coordinator
after: take-in-cycle automation: <level>
set-decisions - convenes briefing: what marketing is asking the
board to settle, heard at once by every agent that
owes evidence toward it
owner: decision-coordinator
after: read-last-record automation: never
pull-results - runs collect-and-report: what the department did
in the period, each line carrying its source and
the date it was pulled
owner: reporting-manager after: set-decisions
by: <days> automation: <level>
qualify-numbers - runs assessment: which figures hold, the range
around each one, and which cannot be computed
from the data there is
owner: statistician after: pull-results
by: <days> automation: <level>
account-money - human: what each function was allocated, what has
been drawn against it, and what is left
owner: budget-keeper after: set-decisions
by: <days> automation: <level>
account-work - human: what the department has already committed
for the period ahead, and what room is left in it
owner: capacity-manager after: set-decisions
by: <days> automation: <level>
outside-picture - runs build-by-talent: the market, the competitors
and what buyers have been saying, every fact
carrying the source under it
owner: researcher after: set-decisions
by: <weeks> automation: <level>
size-choices - runs build-by-talent: what each option would cost
and return at each level of spend, with the
assumptions written beside every number
owner: forecaster
after: qualify-numbers + account-money +
account-work + outside-picture
by: <days> automation: <level>
settle-position - convenes decide-and-announce: what marketing will
say to the board, and what it will ask for
owner: decision-coordinator after: size-choices
automation: never
write-papers - human: one paper for each decision, saying what
is being asked, the options, and what each option
would rule out
owner: copywriter
after: settle-position
by: <days> automation: <level>
build-pack - runs build-by-talent: the papers, the figures and
the charts assembled into the one document the
board reads
owner: designer after: write-papers
by: <days> automation: <level>
get-sign-offs - convenes approval: brand, legal and <who> sign, as
named signers, against a version of the pack
owner: <your legal role> after: build-pack
by: <days> automation: never
send-ahead - human: the signed pack reaches every member with
enough days in front of the meeting to be read
owner: decision-coordinator after: get-sign-offs
by: <days> automation: <level>
rehearse - runs layered-passes: the hard questions asked
against the pack, and the answer to each one
written down
owner: editor after: send-ahead
by: <days> automation: <level>
deliver-briefing - convenes decide-and-announce: the position is
presented, each decision is put to the room, and
the answer is said out loud there
owner: decision-coordinator after: rehearse
automation: never
record-decisions - human: each decision at a version, naming who
decided it, on what reasons, and anyone who
disagreed and what they said
owner: decision-coordinator
after: deliver-briefing
by: <days> automation: <level>
answer-open - runs collect-and-report: the questions the room
could not settle, each answered in writing with
the source under the answer
owner: decision-coordinator
after: deliver-briefing
by: <days> automation: <level>
hand-on - convenes decide-and-announce: every agent that has
to act hears the decision and the date it applies
from
owner: decision-coordinator
after: record-decisions + answer-open
automation: <level>
record-learnings - convenes debrief: what to repeat, what to avoid
owner: decision-coordinator after: hand-on
automation: <level>
run-scoped:
status - runs roll-call owner: decision-coordinator
every: <cadence>
from: set-decisions until: get-sign-offs
handoffs:
take-in-cycle -> read-last-record [dates-and-ask]: the date the
board meets, the date the pack is due, and what the board asked
marketing to bring
read-last-record -> set-decisions [last-meeting-record]: the
questions the board left open last time, and the commitments
marketing made in front of it
set-decisions -> pull-results / account-money / account-work /
outside-picture [decisions-asked-for]: the decisions being asked
for and the date the evidence is due. Four branches read one
record
pull-results -> qualify-numbers [period-results]: the results, each
line naming its source and the date it was pulled
qualify-numbers -> size-choices [qualified-figures]: the figures
that hold, the range around each one, every exclusion and the rule
behind it, and every figure marked uncomputed
account-money -> size-choices [money-account]: what each function
was allocated, what has been drawn against it, and what is left
account-work -> size-choices [work-account]: what the department has
committed for the period ahead, and what a new commitment would
displace
outside-picture -> size-choices [market-picture]: the market and the
competitors, each fact carrying its source and the date it was
read
size-choices -> settle-position [costed-options]: what each option
would cost and return, with the assumptions beside the numbers and
every rate that could not be sourced marked unsourced
settle-position -> write-papers [marketing-position]: what marketing
will say, and the decision it wants against each option
write-papers -> build-pack [decision-papers]: the papers at a
version, one for each decision
build-pack -> get-sign-offs [the-pack]: the pack at a version, as
the board will read it
get-sign-offs -> send-ahead [signed-pack]: the pack at the signed
version. A later change voids the approval and the signers see it
again
send-ahead -> rehearse [pack-as-sent]: the pack as the board
received it, and the date each member received it
rehearse -> deliver-briefing [rehearsal-answers]: the questions the
rehearsal asked, and the answer given to each one
deliver-briefing -> record-decisions [what-the-room-decided]: what
the room decided, on what reasons, and what it declined to decide
deliver-briefing -> answer-open [open-questions]: the questions the
room could not settle, each with the date its answer is due
record-decisions -> hand-on [recorded-decisions]: each decision at a
version, naming the agents that have to act on it
answer-open -> hand-on [written-answers]: the written answer to each
open question, with the source under it
hand-on -> record-learnings [what-agents-took-away]: what each agent
took away, and anything an agent said it could not do
deviations:
qualify-numbers -> pull-results [figure-will-not-carry]: the data
will not carry a figure the pack wants to claim, so the results
are pulled again for what will carry it
size-choices -> outside-picture [rate-with-no-source]: a choice
rests on a rate nobody can source, so the outside picture is
gathered again for it
settle-position -> size-choices [evidence-will-not-support-the-ask]:
the evidence will not support the ask, so the choices are sized
again
get-sign-offs -> write-papers [paper-changes]: a signer comes back
with changes to a decision paper
get-sign-offs -> build-pack [pack-changes]: a signer comes back with
changes to the pack
send-ahead -> write-papers [question-before-the-room]: a board
member asks a question before the meeting, and the answer goes
into the papers so every member gets it
rehearse -> write-papers [pack-cannot-answer]: the rehearsal finds a
question the pack cannot answer, so the papers either answer it or
say when they will
answer-open -> record-decisions [answer-changes-the-decision]: an
answer given after the meeting changes what was decided, so the
decision is recorded again at a new version
bindings:
roster: <who holds each role - agents claiming the abstract agents
above, and named people for the board, leadership, legal
and finance>
systems: the decision record (write), the report store (read),
the budget record (read), the book of work (read),
the model store (write), the calculation record (write),
the source record (write), the asset store (write),
analytics platforms (read), the notification channel
(write), the meeting calendar (write)
data: the record of the last meeting, the closed periods'
reports, what the department committed to for the period,
the marketing standards at their versions, <your measure
definitions> at a version, the board calendar
policy:
every figure in the pack names the source or the model version it
came from
a figure that cannot be computed from the data there is appears in
the pack as uncomputed, and nobody fills it in
a rate the model cannot source appears in the pack as unsourced
a difference inside the noise of the measurement is never presented
as a result
the decisions belong to the people in the room and are never
delegated to an agent
every decision is recorded with its reasons and with anyone who
disagreed, and a recorded decision changes only as a new version
the pack goes to the board only at the version the signers signed
a question the room could not settle gets a written answer by
<when>, rather than waiting for the next cycle
measures:
cycle time: <weeks> from the cycle opening to the briefing
coverage: <share> of the decisions asked for that came back decided
quality gate: every figure in the pack carries its source, and every
decision leaves a record
```
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
401 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: brief executive leadership id: <team>/brief-executive-leadership v1
from: ref/mkt/brief-executive-leadership v1
owner: <who> effective: <date>
trigger: a board or executive cycle opens on <your board calendar>
watch: record=<the meeting> system=<your board calendar>
change=<a cycle opens with a meeting date and what
marketing is asked to bring>
concurrency: one run per meeting - a board cycle and an executive
review are separate runs and may overlap
goal: a board or an executive team that understands where marketing
stands, and every decision marketing asked for either taken and
recorded or declined with a reason
phases:
take-in-cycle - human: read what the board asked marketing to
bring, and write down the date it meets and the
date the pack is due
owner: decision-coordinator after: trigger
automation: <level>
read-last-record - human: the questions the board left open last
time, and the commitments marketing made in front
of it
owner: decision-coordinator
after: take-in-cycle automation: <level>
set-decisions - convenes briefing: what marketing is asking the
board to settle, heard at once by every agent that
owes evidence toward it
owner: decision-coordinator
after: read-last-record automation: never
pull-results - runs collect-and-report: what the department did
in the period, each line carrying its source and
the date it was pulled
owner: reporting-manager after: set-decisions
by: <days> automation: <level>
qualify-numbers - runs assessment: which figures hold, the range
around each one, and which cannot be computed
from the data there is
owner: statistician after: pull-results
by: <days> automation: <level>
account-money - human: what each function was allocated, what has
been drawn against it, and what is left
owner: budget-keeper after: set-decisions
by: <days> automation: <level>
account-work - human: what the department has already committed
for the period ahead, and what room is left in it
owner: capacity-manager after: set-decisions
by: <days> automation: <level>
outside-picture - runs build-by-talent: the market, the competitors
and what buyers have been saying, every fact
carrying the source under it
owner: researcher after: set-decisions
by: <weeks> automation: <level>
size-choices - runs build-by-talent: what each option would cost
and return at each level of spend, with the
assumptions written beside every number
owner: forecaster
after: qualify-numbers + account-money +
account-work + outside-picture
by: <days> automation: <level>
settle-position - convenes decide-and-announce: what marketing will
say to the board, and what it will ask for
owner: decision-coordinator after: size-choices
automation: never
write-papers - human: one paper for each decision, saying what
is being asked, the options, and what each option
would rule out
owner: copywriter
after: settle-position
by: <days> automation: <level>
build-pack - runs build-by-talent: the papers, the figures and
the charts assembled into the one document the
board reads
owner: designer after: write-papers
by: <days> automation: <level>
get-sign-offs - convenes approval: brand, legal and <who> sign, as
named signers, against a version of the pack
owner: <your legal role> after: build-pack
by: <days> automation: never
send-ahead - human: the signed pack reaches every member with
enough days in front of the meeting to be read
owner: decision-coordinator after: get-sign-offs
by: <days> automation: <level>
rehearse - runs layered-passes: the hard questions asked
against the pack, and the answer to each one
written down
owner: editor after: send-ahead
by: <days> automation: <level>
deliver-briefing - convenes decide-and-announce: the position is
presented, each decision is put to the room, and
the answer is said out loud there
owner: decision-coordinator after: rehearse
automation: never
record-decisions - human: each decision at a version, naming who
decided it, on what reasons, and anyone who
disagreed and what they said
owner: decision-coordinator
after: deliver-briefing
by: <days> automation: <level>
answer-open - runs collect-and-report: the questions the room
could not settle, each answered in writing with
the source under the answer
owner: decision-coordinator
after: deliver-briefing
by: <days> automation: <level>
hand-on - convenes decide-and-announce: every agent that has
to act hears the decision and the date it applies
from
owner: decision-coordinator
after: record-decisions + answer-open
automation: <level>
record-learnings - convenes debrief: what to repeat, what to avoid
owner: decision-coordinator after: hand-on
automation: <level>
run-scoped:
status - runs roll-call owner: decision-coordinator
every: <cadence>
from: set-decisions until: get-sign-offs
handoffs:
take-in-cycle -> read-last-record [dates-and-ask]: the date the
board meets, the date the pack is due, and what the board asked
marketing to bring
read-last-record -> set-decisions [last-meeting-record]: the
questions the board left open last time, and the commitments
marketing made in front of it
set-decisions -> pull-results / account-money / account-work /
outside-picture [decisions-asked-for]: the decisions being asked
for and the date the evidence is due. Four branches read one
record
pull-results -> qualify-numbers [period-results]: the results, each
line naming its source and the date it was pulled
qualify-numbers -> size-choices [qualified-figures]: the figures
that hold, the range around each one, every exclusion and the rule
behind it, and every figure marked uncomputed
account-money -> size-choices [money-account]: what each function
was allocated, what has been drawn against it, and what is left
account-work -> size-choices [work-account]: what the department has
committed for the period ahead, and what a new commitment would
displace
outside-picture -> size-choices [market-picture]: the market and the
competitors, each fact carrying its source and the date it was
read
size-choices -> settle-position [costed-options]: what each option
would cost and return, with the assumptions beside the numbers and
every rate that could not be sourced marked unsourced
settle-position -> write-papers [marketing-position]: what marketing
will say, and the decision it wants against each option
write-papers -> build-pack [decision-papers]: the papers at a
version, one for each decision
build-pack -> get-sign-offs [the-pack]: the pack at a version, as
the board will read it
get-sign-offs -> send-ahead [signed-pack]: the pack at the signed
version. A later change voids the approval and the signers see it
again
send-ahead -> rehearse [pack-as-sent]: the pack as the board
received it, and the date each member received it
rehearse -> deliver-briefing [rehearsal-answers]: the questions the
rehearsal asked, and the answer given to each one
deliver-briefing -> record-decisions [what-the-room-decided]: what
the room decided, on what reasons, and what it declined to decide
deliver-briefing -> answer-open [open-questions]: the questions the
room could not settle, each with the date its answer is due
record-decisions -> hand-on [recorded-decisions]: each decision at a
version, naming the agents that have to act on it
answer-open -> hand-on [written-answers]: the written answer to each
open question, with the source under it
hand-on -> record-learnings [what-agents-took-away]: what each agent
took away, and anything an agent said it could not do
deviations:
qualify-numbers -> pull-results [figure-will-not-carry]: the data
will not carry a figure the pack wants to claim, so the results
are pulled again for what will carry it
size-choices -> outside-picture [rate-with-no-source]: a choice
rests on a rate nobody can source, so the outside picture is
gathered again for it
settle-position -> size-choices [evidence-will-not-support-the-ask]:
the evidence will not support the ask, so the choices are sized
again
get-sign-offs -> write-papers [paper-changes]: a signer comes back
with changes to a decision paper
get-sign-offs -> build-pack [pack-changes]: a signer comes back with
changes to the pack
send-ahead -> write-papers [question-before-the-room]: a board
member asks a question before the meeting, and the answer goes
into the papers so every member gets it
rehearse -> write-papers [pack-cannot-answer]: the rehearsal finds a
question the pack cannot answer, so the papers either answer it or
say when they will
answer-open -> record-decisions [answer-changes-the-decision]: an
answer given after the meeting changes what was decided, so the
decision is recorded again at a new version
bindings:
roster: <who holds each role - agents claiming the abstract agents
above, and named people for the board, leadership, legal
and finance>
systems: the decision record (write), the report store (read),
the budget record (read), the book of work (read),
the model store (write), the calculation record (write),
the source record (write), the asset store (write),
analytics platforms (read), the notification channel
(write), the meeting calendar (write)
data: the record of the last meeting, the closed periods'
reports, what the department committed to for the period,
the marketing standards at their versions, <your measure
definitions> at a version, the board calendar
policy:
every figure in the pack names the source or the model version it
came from
a figure that cannot be computed from the data there is appears in
the pack as uncomputed, and nobody fills it in
a rate the model cannot source appears in the pack as unsourced
a difference inside the noise of the measurement is never presented
as a result
the decisions belong to the people in the room and are never
delegated to an agent
every decision is recorded with its reasons and with anyone who
disagreed, and a recorded decision changes only as a new version
the pack goes to the board only at the version the signers signed
a question the room could not settle gets a written answer by
<when>, rather than waiting for the next cycle
measures:
cycle time: <weeks> from the cycle opening to the briefing
coverage: <share> of the decisions asked for that came back decided
quality gate: every figure in the pack carries its source, and every
decision leaves a record
```
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
406 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: brief executive leadership id: <team>/brief-executive-leadership v1
from: ref/mkt/brief-executive-leadership v1
owner: <who> effective: <date>
trigger: a board or executive cycle opens on <your board calendar>
watch: record=<the meeting> system=<your board calendar>
change=<a cycle opens with a meeting date and what
marketing is asked to bring>
concurrency: one run per meeting - a board cycle and an executive
review are separate runs and may overlap
goal: a board or an executive team that understands where marketing
stands, and every decision marketing asked for either taken and
recorded or declined with a reason
phases:
take-in-cycle - human: read what the board asked marketing to
bring, and write down the date it meets and the
date the pack is due
owner: decision-coordinator after: trigger
automation: <level>
read-last-record - human: the questions the board left open last
time, and the commitments marketing made in front
of it
owner: decision-coordinator
after: take-in-cycle automation: <level>
set-decisions - convenes briefing: what marketing is asking the
board to settle, heard at once by every agent that
owes evidence toward it
owner: decision-coordinator
after: read-last-record automation: never
pull-results - runs collect-and-report: what the department did
in the period, each line carrying its source and
the date it was pulled
owner: reporting-manager after: set-decisions
by: <days> automation: <level>
qualify-numbers - runs assessment: which figures hold, the range
around each one, and which cannot be computed
from the data there is
owner: statistician after: pull-results
by: <days> automation: <level>
account-money - human: what each function was allocated, what has
been drawn against it, and what is left
owner: budget-keeper after: set-decisions
by: <days> automation: <level>
account-work - human: what the department has already committed
for the period ahead, and what room is left in it
owner: capacity-manager after: set-decisions
by: <days> automation: <level>
outside-picture - runs build-by-talent: the market, the competitors
and what buyers have been saying, every fact
carrying the source under it
owner: researcher after: set-decisions
by: <weeks> automation: <level>
size-choices - runs build-by-talent: what each option would cost
and return at each level of spend, with the
assumptions written beside every number
owner: forecaster
after: qualify-numbers + account-money +
account-work + outside-picture
by: <days> automation: <level>
settle-position - convenes decide-and-announce: what marketing will
say to the board, and what it will ask for
owner: decision-coordinator after: size-choices
automation: never
write-papers - human: one paper for each decision, saying what
is being asked, the options, and what each option
would rule out
owner: copywriter
after: settle-position
by: <days> automation: <level>
build-pack - runs build-by-talent: the papers, the figures and
the charts assembled into the one document the
board reads
owner: designer after: write-papers
by: <days> automation: <level>
get-sign-offs - convenes approval: brand, legal and <who> sign, as
named signers, against a version of the pack
owner: <your legal role> after: build-pack
by: <days> automation: never
send-ahead - human: the signed pack reaches every member with
enough days in front of the meeting to be read
owner: decision-coordinator after: get-sign-offs
by: <days> automation: <level>
rehearse - runs layered-passes: the hard questions asked
against the pack, and the answer to each one
written down
owner: editor after: send-ahead
by: <days> automation: <level>
deliver-briefing - convenes decide-and-announce: the position is
presented, each decision is put to the room, and
the answer is said out loud there
owner: decision-coordinator after: rehearse
automation: never
record-decisions - human: each decision at a version, naming who
decided it, on what reasons, and anyone who
disagreed and what they said
owner: decision-coordinator
after: deliver-briefing
by: <days> automation: <level>
answer-open - runs collect-and-report: the questions the room
could not settle, each answered in writing with
the source under the answer
owner: decision-coordinator
after: deliver-briefing
by: <days> automation: <level>
hand-on - convenes decide-and-announce: every agent that has
to act hears the decision and the date it applies
from
owner: decision-coordinator
after: record-decisions + answer-open
automation: <level>
record-learnings - convenes debrief: what to repeat, what to avoid
owner: decision-coordinator after: hand-on
automation: <level>
run-scoped:
status - runs roll-call owner: decision-coordinator
every: <cadence>
from: set-decisions until: get-sign-offs
handoffs:
take-in-cycle -> read-last-record [dates-and-ask]: the date the
board meets, the date the pack is due, and what the board asked
marketing to bring
read-last-record -> set-decisions [last-meeting-record]: the
questions the board left open last time, and the commitments
marketing made in front of it
set-decisions -> pull-results / account-money / account-work /
outside-picture [decisions-asked-for]: the decisions being asked
for and the date the evidence is due. Four branches read one
record
pull-results -> qualify-numbers [period-results]: the results, each
line naming its source and the date it was pulled
qualify-numbers -> size-choices [qualified-figures]: the figures
that hold, the range around each one, every exclusion and the rule
behind it, and every figure marked uncomputed
account-money -> size-choices [money-account]: what each function
was allocated, what has been drawn against it, and what is left
account-work -> size-choices [work-account]: what the department has
committed for the period ahead, and what a new commitment would
displace
outside-picture -> size-choices [market-picture]: the market and the
competitors, each fact carrying its source and the date it was
read
size-choices -> settle-position [costed-options]: what each option
would cost and return, with the assumptions beside the numbers and
every rate that could not be sourced marked unsourced
settle-position -> write-papers [marketing-position]: what marketing
will say, and the decision it wants against each option
write-papers -> build-pack [decision-papers]: the papers at a
version, one for each decision
build-pack -> get-sign-offs [the-pack]: the pack at a version, as
the board will read it
get-sign-offs -> send-ahead [signed-pack]: the pack at the signed
version. A later change voids the approval and the signers see it
again
send-ahead -> rehearse [pack-as-sent]: the pack as the board
received it, and the date each member received it
rehearse -> deliver-briefing [rehearsal-answers]: the questions the
rehearsal asked, and the answer given to each one
deliver-briefing -> record-decisions [what-the-room-decided]: what
the room decided, on what reasons, and what it declined to decide
deliver-briefing -> answer-open [open-questions]: the questions the
room could not settle, each with the date its answer is due
record-decisions -> hand-on [recorded-decisions]: each decision at a
version, naming the agents that have to act on it
answer-open -> hand-on [written-answers]: the written answer to each
open question, with the source under it
hand-on -> record-learnings [what-agents-took-away]: what each agent
took away, and anything an agent said it could not do
deviations:
qualify-numbers -> pull-results [figure-will-not-carry]: the data
will not carry a figure the pack wants to claim, so the results
are pulled again for what will carry it
size-choices -> outside-picture [rate-with-no-source]: a choice
rests on a rate nobody can source, so the outside picture is
gathered again for it
settle-position -> size-choices [evidence-will-not-support-the-ask]:
the evidence will not support the ask, so the choices are sized
again
get-sign-offs -> write-papers [paper-changes]: a signer comes back
with changes to a decision paper
get-sign-offs -> build-pack [pack-changes]: a signer comes back with
changes to the pack
send-ahead -> write-papers [question-before-the-room]: a board
member asks a question before the meeting, and the answer goes
into the papers so every member gets it
rehearse -> write-papers [pack-cannot-answer]: the rehearsal finds a
question the pack cannot answer, so the papers either answer it or
say when they will
answer-open -> record-decisions [answer-changes-the-decision]: an
answer given after the meeting changes what was decided, so the
decision is recorded again at a new version
bindings:
roster: <who holds each role - agents claiming the abstract agents
above, and named people for the board, leadership, legal
and finance>
systems: the decision record (write), the report store (read),
the budget record (read), the book of work (read),
the model store (write), the calculation record (write),
the source record (write), the asset store (write),
analytics platforms (read), the notification channel
(write), the meeting calendar (write)
data: the record of the last meeting, the closed periods'
reports, what the department committed to for the period,
the marketing standards at their versions, <your measure
definitions> at a version, the board calendar
policy:
every figure in the pack names the source or the model version it
came from
a figure that cannot be computed from the data there is appears in
the pack as uncomputed, and nobody fills it in
a rate the model cannot source appears in the pack as unsourced
a difference inside the noise of the measurement is never presented
as a result
the decisions belong to the people in the room and are never
delegated to an agent
every decision is recorded with its reasons and with anyone who
disagreed, and a recorded decision changes only as a new version
the pack goes to the board only at the version the signers signed
a question the room could not settle gets a written answer by
<when>, rather than waiting for the next cycle
measures:
cycle time: <weeks> from the cycle opening to the briefing
coverage: <share> of the decisions asked for that came back decided
quality gate: every figure in the pack carries its source, and every
decision leaves a record
```
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
397 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: brief executive leadership id: <team>/brief-executive-leadership v1
from: ref/mkt/brief-executive-leadership v1
owner: <who> effective: <date>
trigger: a board or executive cycle opens on <your board calendar>
watch: record=<the meeting> system=<your board calendar>
change=<a cycle opens with a meeting date and what
marketing is asked to bring>
concurrency: one run per meeting - a board cycle and an executive
review are separate runs and may overlap
goal: a board or an executive team that understands where marketing
stands, and every decision marketing asked for either taken and
recorded or declined with a reason
phases:
take-in-cycle - human: read what the board asked marketing to
bring, and write down the date it meets and the
date the pack is due
owner: decision-coordinator after: trigger
automation: <level>
read-last-record - human: the questions the board left open last
time, and the commitments marketing made in front
of it
owner: decision-coordinator
after: take-in-cycle automation: <level>
set-decisions - convenes briefing: what marketing is asking the
board to settle, heard at once by every agent that
owes evidence toward it
owner: decision-coordinator
after: read-last-record automation: never
pull-results - runs collect-and-report: what the department did
in the period, each line carrying its source and
the date it was pulled
owner: reporting-manager after: set-decisions
by: <days> automation: <level>
qualify-numbers - runs assessment: which figures hold, the range
around each one, and which cannot be computed
from the data there is
owner: statistician after: pull-results
by: <days> automation: <level>
account-money - human: what each function was allocated, what has
been drawn against it, and what is left
owner: budget-keeper after: set-decisions
by: <days> automation: <level>
account-work - human: what the department has already committed
for the period ahead, and what room is left in it
owner: capacity-manager after: set-decisions
by: <days> automation: <level>
outside-picture - runs build-by-talent: the market, the competitors
and what buyers have been saying, every fact
carrying the source under it
owner: researcher after: set-decisions
by: <weeks> automation: <level>
size-choices - runs build-by-talent: what each option would cost
and return at each level of spend, with the
assumptions written beside every number
owner: forecaster
after: qualify-numbers + account-money +
account-work + outside-picture
by: <days> automation: <level>
settle-position - convenes decide-and-announce: what marketing will
say to the board, and what it will ask for
owner: decision-coordinator after: size-choices
automation: never
write-papers - human: one paper for each decision, saying what
is being asked, the options, and what each option
would rule out
owner: copywriter
after: settle-position
by: <days> automation: <level>
build-pack - runs build-by-talent: the papers, the figures and
the charts assembled into the one document the
board reads
owner: designer after: write-papers
by: <days> automation: <level>
get-sign-offs - convenes approval: brand, legal and <who> sign, as
named signers, against a version of the pack
owner: <your legal role> after: build-pack
by: <days> automation: never
send-ahead - human: the signed pack reaches every member with
enough days in front of the meeting to be read
owner: decision-coordinator after: get-sign-offs
by: <days> automation: <level>
rehearse - runs layered-passes: the hard questions asked
against the pack, and the answer to each one
written down
owner: editor after: send-ahead
by: <days> automation: <level>
deliver-briefing - convenes decide-and-announce: the position is
presented, each decision is put to the room, and
the answer is said out loud there
owner: decision-coordinator after: rehearse
automation: never
record-decisions - human: each decision at a version, naming who
decided it, on what reasons, and anyone who
disagreed and what they said
owner: decision-coordinator
after: deliver-briefing
by: <days> automation: <level>
answer-open - runs collect-and-report: the questions the room
could not settle, each answered in writing with
the source under the answer
owner: decision-coordinator
after: deliver-briefing
by: <days> automation: <level>
hand-on - convenes decide-and-announce: every agent that has
to act hears the decision and the date it applies
from
owner: decision-coordinator
after: record-decisions + answer-open
automation: <level>
record-learnings - convenes debrief: what to repeat, what to avoid
owner: decision-coordinator after: hand-on
automation: <level>
run-scoped:
status - runs roll-call owner: decision-coordinator
every: <cadence>
from: set-decisions until: get-sign-offs
handoffs:
take-in-cycle -> read-last-record [dates-and-ask]: the date the
board meets, the date the pack is due, and what the board asked
marketing to bring
read-last-record -> set-decisions [last-meeting-record]: the
questions the board left open last time, and the commitments
marketing made in front of it
set-decisions -> pull-results / account-money / account-work /
outside-picture [decisions-asked-for]: the decisions being asked
for and the date the evidence is due. Four branches read one
record
pull-results -> qualify-numbers [period-results]: the results, each
line naming its source and the date it was pulled
qualify-numbers -> size-choices [qualified-figures]: the figures
that hold, the range around each one, every exclusion and the rule
behind it, and every figure marked uncomputed
account-money -> size-choices [money-account]: what each function
was allocated, what has been drawn against it, and what is left
account-work -> size-choices [work-account]: what the department has
committed for the period ahead, and what a new commitment would
displace
outside-picture -> size-choices [market-picture]: the market and the
competitors, each fact carrying its source and the date it was
read
size-choices -> settle-position [costed-options]: what each option
would cost and return, with the assumptions beside the numbers and
every rate that could not be sourced marked unsourced
settle-position -> write-papers [marketing-position]: what marketing
will say, and the decision it wants against each option
write-papers -> build-pack [decision-papers]: the papers at a
version, one for each decision
build-pack -> get-sign-offs [the-pack]: the pack at a version, as
the board will read it
get-sign-offs -> send-ahead [signed-pack]: the pack at the signed
version. A later change voids the approval and the signers see it
again
send-ahead -> rehearse [pack-as-sent]: the pack as the board
received it, and the date each member received it
rehearse -> deliver-briefing [rehearsal-answers]: the questions the
rehearsal asked, and the answer given to each one
deliver-briefing -> record-decisions [what-the-room-decided]: what
the room decided, on what reasons, and what it declined to decide
deliver-briefing -> answer-open [open-questions]: the questions the
room could not settle, each with the date its answer is due
record-decisions -> hand-on [recorded-decisions]: each decision at a
version, naming the agents that have to act on it
answer-open -> hand-on [written-answers]: the written answer to each
open question, with the source under it
hand-on -> record-learnings [what-agents-took-away]: what each agent
took away, and anything an agent said it could not do
deviations:
qualify-numbers -> pull-results [figure-will-not-carry]: the data
will not carry a figure the pack wants to claim, so the results
are pulled again for what will carry it
size-choices -> outside-picture [rate-with-no-source]: a choice
rests on a rate nobody can source, so the outside picture is
gathered again for it
settle-position -> size-choices [evidence-will-not-support-the-ask]:
the evidence will not support the ask, so the choices are sized
again
get-sign-offs -> write-papers [paper-changes]: a signer comes back
with changes to a decision paper
get-sign-offs -> build-pack [pack-changes]: a signer comes back with
changes to the pack
send-ahead -> write-papers [question-before-the-room]: a board
member asks a question before the meeting, and the answer goes
into the papers so every member gets it
rehearse -> write-papers [pack-cannot-answer]: the rehearsal finds a
question the pack cannot answer, so the papers either answer it or
say when they will
answer-open -> record-decisions [answer-changes-the-decision]: an
answer given after the meeting changes what was decided, so the
decision is recorded again at a new version
bindings:
roster: <who holds each role - agents claiming the abstract agents
above, and named people for the board, leadership, legal
and finance>
systems: the decision record (write), the report store (read),
the budget record (read), the book of work (read),
the model store (write), the calculation record (write),
the source record (write), the asset store (write),
analytics platforms (read), the notification channel
(write), the meeting calendar (write)
data: the record of the last meeting, the closed periods'
reports, what the department committed to for the period,
the marketing standards at their versions, <your measure
definitions> at a version, the board calendar
policy:
every figure in the pack names the source or the model version it
came from
a figure that cannot be computed from the data there is appears in
the pack as uncomputed, and nobody fills it in
a rate the model cannot source appears in the pack as unsourced
a difference inside the noise of the measurement is never presented
as a result
the decisions belong to the people in the room and are never
delegated to an agent
every decision is recorded with its reasons and with anyone who
disagreed, and a recorded decision changes only as a new version
the pack goes to the board only at the version the signers signed
a question the room could not settle gets a written answer by
<when>, rather than waiting for the next cycle
measures:
cycle time: <weeks> from the cycle opening to the briefing
coverage: <share> of the decisions asked for that came back decided
quality gate: every figure in the pack carries its source, and every
decision leaves a record
```
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
41 blanks to fill. Everything else is the process.
this process
from: ref/mkt/brief-executive-leadership 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.