Catalog / Business processes / Marketing / Brief-to-Results / Run Influencer Campaign
reference process · marketing · 16 activities · 15 on the rosterRun Influencer Campaign
A campaign manager takes a target audience, has outside creators found and checked, gets the shortlist cleared by the people who decide who the organization is willing to be seen with, agrees terms with each creator, briefs them, reads what they made before it goes out, and confirms that every agreed post is live and carries the disclosure its market requires. The run stays open until the disclosure check has passed on every post. A post that runs without its disclosure breaks advertising law in most markets, and the organization that paid for it is the party held responsible.
The walk
The document
One run
Adoption
The activities
What happens in a run
16 activities from a target audience is handed to the campaign to every agreed post is live and disclosed, 3 of them gates a person has to sign. Drag the diagram to move along it.
Run Influencer Campaign a target audience is handed to the campaign → every agreed post is live and disclosed
too few creators cleared too few accepted changes requested an agreed post never ran a post missing its disclosure a target audience is handed to the campaign 1 Take in the Audience work out who to reach and what the run must do 2 Set the Parameters markets, platforms, dates, budget and deliverables 3 Read the Disclosure Rules what each market requires a paid post to say 4 Draw up the Candidate List creators whose following matches the audience 5 Vet the Candidates check the audience is real and the history is clean 6 Clear the Shortlist brand and legal accept who the organization pays a person signs · never an agent 7 Approach the Creators make the offer and find out who is interested 8 Settle the Terms deliverables, dates, usage rights, disclosure, fee a person signs · never an agent 9 Set up the Tracking links and codes so each creator can be counted 10 Brief the Creators what the campaign is for and what must be said 11 Collect the Drafts each creator sends what the deal said they owe 12 Review the Drafts each draft read against the rules before it runs a person signs · never an agent 13 Publish the Posts the creators post on the dates that were agreed 14 Record the Live Posts every agreed post is found and kept as it ran 15 Check the Disclosure every live post carries the disclosure required 16 Correct What Failed the creator corrects or takes down what failed every agreed post is live and disclosed 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: influencer campaign id: <team> /influencer-campaign v1
from: ref/mkt/influencer-campaign v1
owner: <who> effective: <date>
trigger: an audience is handed to a campaign in <your planning process>
watch: record=<campaign brief>
system=<your planning process>
change=<an audience is handed to a campaign>
concurrency: runs may overlap - <how many> live at once
goal: every creator the campaign agreed terms with has published what
the deal named, on the date it named, carrying the disclosure the
market it ran in requires
phases:
take-in-audience - human: read the audience the run was given and
write down what the campaign has to do with it
owner: campaign-manager after: trigger
automation: <level>
set-parameters - human: the markets, the platforms, the dates, the
deliverables and the money. <who> confirms the
budget
owner: campaign-manager after: take-in-audience
automation: <level>
disclosure-rules - human: pull what each market and each platform
requires a paid post to say. <your legal
reviewer> confirms which version is in force
owner: researcher after: set-parameters
by: <days> automation: <level>
candidate-list - human: the creators whose following matches the
audience, each with the figures behind it
owner: creator-relations after: set-parameters
by: <days> automation: <level>
vet-candidates - runs assessment: each candidate scored on whether
the audience is real and the history is clean
owner: creator-relations after: candidate-list
by: <days> automation: <level>
clear-shortlist - convenes approval: brand and legal accept, as
named signers, who the organization will pay
owner: <your legal role> after: vet-candidates
by: <days> automation: never
approach - human: the offer goes to each cleared creator and
the answer lands against their name
owner: creator-relations after: clear-shortlist
by: <days> automation: <level>
settle-terms - convenes approval: the deliverables, the dates,
the usage rights, the disclosure and the fee, each
signed by the person who answers for it
owner: creator-relations after: approach
by: <days> automation: never
set-up-tracking - human: the link, the code and the parameters that
make each creator countable on their own
owner: conversion-tracker after: set-parameters
by: brief-creators automation: <level>
brief-creators - convenes briefing: what the campaign is for, what
the deal requires, and what has to be disclosed
owner: campaign-manager
after: settle-terms + disclosure-rules +
set-up-tracking
automation: <level>
collect-drafts - human: each creator sends what the deal said they
owe, on the date it was due
owner: creator-relations after: brief-creators
by: <days> automation: <level>
review-drafts - convenes approval: brand, disclosure and legal
read each draft against the rules, as named
signers, before it goes out
owner: <your legal role> after: collect-drafts
by: <days> automation: never
publish-posts - human: the creators post on the agreed dates, on
their own accounts
owner: creator-relations after: review-drafts
automation: <level>
record-posts - human: every agreed post is found and kept as it
ran, with its address and the date it appeared
owner: coverage-monitor after: publish-posts
by: <days> automation: <level>
check-disclosure - runs assessment: every live post scored against
the disclosure rules of the market it ran in
owner: disclosure-check after: record-posts
by: <days> automation: <level>
correct-failed - human: the agent holding the deal goes back to the
creator, and <who> decides what is asked for
owner: creator-relations after: check-disclosure
by: <hours> automation: <level>
run-scoped:
status - runs roll-call owner: campaign-manager
every: <cadence>
from: brief-creators until: check-disclosure
replies - runs collect-and-report owner: community-manager
every: <cadence>
from: publish-posts until: run close
what people asked on the organization's own channels once
the creator posts went out
fees - runs allocate-and-reconcile owner: spend-reconciler
from: settle-terms until: run close
handoffs:
take-in-audience -> set-parameters [audience-in-one-line]: who the
campaign is for, in one line that every later decision can be tested
against
set-parameters -> disclosure-rules [markets-and-platforms]: the
markets and the platforms the work will run in
set-parameters -> candidate-list [campaign-parameters]: the audience,
the markets, the deliverables and what there is to spend
set-parameters -> set-up-tracking [parameters-for-tracking]: the same
parameters. Both branches read one record
disclosure-rules -> brief-creators [disclosure-requirements]: what
each market requires a paid post to say, quoted, at the version in
force, with the date it was read
candidate-list -> vet-candidates [candidates-and-figures]: each
candidate with the audience figures, the source they came from and
the date they were read
vet-candidates -> clear-shortlist [vetting-scores]: the scored list,
with the criterion behind every verdict
clear-shortlist -> approach [cleared-creators]: the creators the
signers accepted, and the ones they refused with the reason
approach -> settle-terms [acceptances-and-asks]: who accepted, and the
terms each of them asked for
settle-terms -> brief-creators [signed-deals]: the deal at the version
it was agreed, naming every deliverable, the date each one is due,
the channels the work may run on, how long the organization may use
it, what the disclosure has to say, and the fee
set-up-tracking -> brief-creators [creator-links]: the link and the
code each creator puts in their post, one set per creator
brief-creators -> collect-drafts [creator-brief]: the request as every
creator heard it, the date each deliverable is due, and the
disclosure wording that has to appear
collect-drafts -> review-drafts [creator-drafts]: each draft at the
version the creator sent it
review-drafts -> publish-posts [approved-drafts]: the approved drafts
at the signed version. A later change voids the approval and the
review runs again
publish-posts -> record-posts [posting-claims]: what each creator says
they posted, where they posted it, and on what date
record-posts -> check-disclosure [live-posts]: every live post as it
ran, with its address, the date it appeared and the market it ran in
check-disclosure -> correct-failed [disclosure-failures]: the
failures, each with the rule and the market named
correct-failed -> check-disclosure [corrected-posts]: the corrected
post, scored again before the run closes
deviations:
clear-shortlist -> candidate-list [too-few-cleared]: the signers clear
too few creators, so more candidates are drawn up against the same
audience
approach -> candidate-list [too-few-accepted]: too few creators accept
the offer, so more candidates are drawn up
review-drafts -> collect-drafts [review-changes]: the review asks for
changes, so the creator sends a new draft and only what the signers
named reopens
record-posts -> publish-posts [post-never-ran]: an agreed post never
appeared, so the creator is gone back to for a new date
check-disclosure -> correct-failed [disclosure-missing]: a live post
carries no disclosure, or one a reader has to expand to see, so the
creator is asked to correct it or take it down
bindings:
roster: <who holds each role - agents claiming the abstract agents
above, and named people for legal, brand, rights and
finance>
systems: the creator record (write), the deal record (write),
the contact log (write),
the outreach channel (write, cap: <n> creators/run),
audience measurement sources (read),
the rights record (write), the review record (write),
the coverage record (write), analytics (write),
the CRM (write), tracking and URL tooling (write)
data: the disclosure rules for each market <version> ,
brand guidelines <version> , <your claims register> ,
the audience definition, the deals as agreed
policy:
the version of each market's disclosure rules is confirmed by a
person before any deal is agreed
no creator is offered money before the audience check and the history
check have both been read by a person
the disclosure the market requires is written into the deal, and a
creator who will not carry it is not paid to publish
sign-off is a human gate and is never delegated to an agent
a draft changed after sign-off goes back through the review
a live post that fails the disclosure check is corrected or taken
down, and the run stays open until the check passes on it
the fee is released only after the disclosure check has passed on
everything that creator published
measures:
cycle time: <target> from the audience to the first post live
volume: <creators per period>
quality gate: every agreed post live, and every live post carrying
the disclosure its market requires
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
306 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: influencer campaign id: <team>/influencer-campaign v1
from: ref/mkt/influencer-campaign v1
owner: <who> effective: <date>
trigger: an audience is handed to a campaign in <your planning process>
watch: record=<campaign brief>
system=<your planning process>
change=<an audience is handed to a campaign>
concurrency: runs may overlap - <how many> live at once
goal: every creator the campaign agreed terms with has published what
the deal named, on the date it named, carrying the disclosure the
market it ran in requires
phases:
take-in-audience - human: read the audience the run was given and
write down what the campaign has to do with it
owner: campaign-manager after: trigger
automation: <level>
set-parameters - human: the markets, the platforms, the dates, the
deliverables and the money. <who> confirms the
budget
owner: campaign-manager after: take-in-audience
automation: <level>
disclosure-rules - human: pull what each market and each platform
requires a paid post to say. <your legal
reviewer> confirms which version is in force
owner: researcher after: set-parameters
by: <days> automation: <level>
candidate-list - human: the creators whose following matches the
audience, each with the figures behind it
owner: creator-relations after: set-parameters
by: <days> automation: <level>
vet-candidates - runs assessment: each candidate scored on whether
the audience is real and the history is clean
owner: creator-relations after: candidate-list
by: <days> automation: <level>
clear-shortlist - convenes approval: brand and legal accept, as
named signers, who the organization will pay
owner: <your legal role> after: vet-candidates
by: <days> automation: never
approach - human: the offer goes to each cleared creator and
the answer lands against their name
owner: creator-relations after: clear-shortlist
by: <days> automation: <level>
settle-terms - convenes approval: the deliverables, the dates,
the usage rights, the disclosure and the fee, each
signed by the person who answers for it
owner: creator-relations after: approach
by: <days> automation: never
set-up-tracking - human: the link, the code and the parameters that
make each creator countable on their own
owner: conversion-tracker after: set-parameters
by: brief-creators automation: <level>
brief-creators - convenes briefing: what the campaign is for, what
the deal requires, and what has to be disclosed
owner: campaign-manager
after: settle-terms + disclosure-rules +
set-up-tracking
automation: <level>
collect-drafts - human: each creator sends what the deal said they
owe, on the date it was due
owner: creator-relations after: brief-creators
by: <days> automation: <level>
review-drafts - convenes approval: brand, disclosure and legal
read each draft against the rules, as named
signers, before it goes out
owner: <your legal role> after: collect-drafts
by: <days> automation: never
publish-posts - human: the creators post on the agreed dates, on
their own accounts
owner: creator-relations after: review-drafts
automation: <level>
record-posts - human: every agreed post is found and kept as it
ran, with its address and the date it appeared
owner: coverage-monitor after: publish-posts
by: <days> automation: <level>
check-disclosure - runs assessment: every live post scored against
the disclosure rules of the market it ran in
owner: disclosure-check after: record-posts
by: <days> automation: <level>
correct-failed - human: the agent holding the deal goes back to the
creator, and <who> decides what is asked for
owner: creator-relations after: check-disclosure
by: <hours> automation: <level>
run-scoped:
status - runs roll-call owner: campaign-manager
every: <cadence>
from: brief-creators until: check-disclosure
replies - runs collect-and-report owner: community-manager
every: <cadence>
from: publish-posts until: run close
what people asked on the organization's own channels once
the creator posts went out
fees - runs allocate-and-reconcile owner: spend-reconciler
from: settle-terms until: run close
handoffs:
take-in-audience -> set-parameters [audience-in-one-line]: who the
campaign is for, in one line that every later decision can be tested
against
set-parameters -> disclosure-rules [markets-and-platforms]: the
markets and the platforms the work will run in
set-parameters -> candidate-list [campaign-parameters]: the audience,
the markets, the deliverables and what there is to spend
set-parameters -> set-up-tracking [parameters-for-tracking]: the same
parameters. Both branches read one record
disclosure-rules -> brief-creators [disclosure-requirements]: what
each market requires a paid post to say, quoted, at the version in
force, with the date it was read
candidate-list -> vet-candidates [candidates-and-figures]: each
candidate with the audience figures, the source they came from and
the date they were read
vet-candidates -> clear-shortlist [vetting-scores]: the scored list,
with the criterion behind every verdict
clear-shortlist -> approach [cleared-creators]: the creators the
signers accepted, and the ones they refused with the reason
approach -> settle-terms [acceptances-and-asks]: who accepted, and the
terms each of them asked for
settle-terms -> brief-creators [signed-deals]: the deal at the version
it was agreed, naming every deliverable, the date each one is due,
the channels the work may run on, how long the organization may use
it, what the disclosure has to say, and the fee
set-up-tracking -> brief-creators [creator-links]: the link and the
code each creator puts in their post, one set per creator
brief-creators -> collect-drafts [creator-brief]: the request as every
creator heard it, the date each deliverable is due, and the
disclosure wording that has to appear
collect-drafts -> review-drafts [creator-drafts]: each draft at the
version the creator sent it
review-drafts -> publish-posts [approved-drafts]: the approved drafts
at the signed version. A later change voids the approval and the
review runs again
publish-posts -> record-posts [posting-claims]: what each creator says
they posted, where they posted it, and on what date
record-posts -> check-disclosure [live-posts]: every live post as it
ran, with its address, the date it appeared and the market it ran in
check-disclosure -> correct-failed [disclosure-failures]: the
failures, each with the rule and the market named
correct-failed -> check-disclosure [corrected-posts]: the corrected
post, scored again before the run closes
deviations:
clear-shortlist -> candidate-list [too-few-cleared]: the signers clear
too few creators, so more candidates are drawn up against the same
audience
approach -> candidate-list [too-few-accepted]: too few creators accept
the offer, so more candidates are drawn up
review-drafts -> collect-drafts [review-changes]: the review asks for
changes, so the creator sends a new draft and only what the signers
named reopens
record-posts -> publish-posts [post-never-ran]: an agreed post never
appeared, so the creator is gone back to for a new date
check-disclosure -> correct-failed [disclosure-missing]: a live post
carries no disclosure, or one a reader has to expand to see, so the
creator is asked to correct it or take it down
bindings:
roster: <who holds each role - agents claiming the abstract agents
above, and named people for legal, brand, rights and
finance>
systems: the creator record (write), the deal record (write),
the contact log (write),
the outreach channel (write, cap: <n> creators/run),
audience measurement sources (read),
the rights record (write), the review record (write),
the coverage record (write), analytics (write),
the CRM (write), tracking and URL tooling (write)
data: the disclosure rules for each market <version>,
brand guidelines <version>, <your claims register>,
the audience definition, the deals as agreed
policy:
the version of each market's disclosure rules is confirmed by a
person before any deal is agreed
no creator is offered money before the audience check and the history
check have both been read by a person
the disclosure the market requires is written into the deal, and a
creator who will not carry it is not paid to publish
sign-off is a human gate and is never delegated to an agent
a draft changed after sign-off goes back through the review
a live post that fails the disclosure check is corrected or taken
down, and the run stays open until the check passes on it
the fee is released only after the disclosure check has passed on
everything that creator published
measures:
cycle time: <target> from the audience to the first post live
volume: <creators per period>
quality gate: every agreed post live, and every live post carrying
the disclosure its market requires
```
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
361 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: influencer campaign id: <team>/influencer-campaign v1
from: ref/mkt/influencer-campaign v1
owner: <who> effective: <date>
trigger: an audience is handed to a campaign in <your planning process>
watch: record=<campaign brief>
system=<your planning process>
change=<an audience is handed to a campaign>
concurrency: runs may overlap - <how many> live at once
goal: every creator the campaign agreed terms with has published what
the deal named, on the date it named, carrying the disclosure the
market it ran in requires
phases:
take-in-audience - human: read the audience the run was given and
write down what the campaign has to do with it
owner: campaign-manager after: trigger
automation: <level>
set-parameters - human: the markets, the platforms, the dates, the
deliverables and the money. <who> confirms the
budget
owner: campaign-manager after: take-in-audience
automation: <level>
disclosure-rules - human: pull what each market and each platform
requires a paid post to say. <your legal
reviewer> confirms which version is in force
owner: researcher after: set-parameters
by: <days> automation: <level>
candidate-list - human: the creators whose following matches the
audience, each with the figures behind it
owner: creator-relations after: set-parameters
by: <days> automation: <level>
vet-candidates - runs assessment: each candidate scored on whether
the audience is real and the history is clean
owner: creator-relations after: candidate-list
by: <days> automation: <level>
clear-shortlist - convenes approval: brand and legal accept, as
named signers, who the organization will pay
owner: <your legal role> after: vet-candidates
by: <days> automation: never
approach - human: the offer goes to each cleared creator and
the answer lands against their name
owner: creator-relations after: clear-shortlist
by: <days> automation: <level>
settle-terms - convenes approval: the deliverables, the dates,
the usage rights, the disclosure and the fee, each
signed by the person who answers for it
owner: creator-relations after: approach
by: <days> automation: never
set-up-tracking - human: the link, the code and the parameters that
make each creator countable on their own
owner: conversion-tracker after: set-parameters
by: brief-creators automation: <level>
brief-creators - convenes briefing: what the campaign is for, what
the deal requires, and what has to be disclosed
owner: campaign-manager
after: settle-terms + disclosure-rules +
set-up-tracking
automation: <level>
collect-drafts - human: each creator sends what the deal said they
owe, on the date it was due
owner: creator-relations after: brief-creators
by: <days> automation: <level>
review-drafts - convenes approval: brand, disclosure and legal
read each draft against the rules, as named
signers, before it goes out
owner: <your legal role> after: collect-drafts
by: <days> automation: never
publish-posts - human: the creators post on the agreed dates, on
their own accounts
owner: creator-relations after: review-drafts
automation: <level>
record-posts - human: every agreed post is found and kept as it
ran, with its address and the date it appeared
owner: coverage-monitor after: publish-posts
by: <days> automation: <level>
check-disclosure - runs assessment: every live post scored against
the disclosure rules of the market it ran in
owner: disclosure-check after: record-posts
by: <days> automation: <level>
correct-failed - human: the agent holding the deal goes back to the
creator, and <who> decides what is asked for
owner: creator-relations after: check-disclosure
by: <hours> automation: <level>
run-scoped:
status - runs roll-call owner: campaign-manager
every: <cadence>
from: brief-creators until: check-disclosure
replies - runs collect-and-report owner: community-manager
every: <cadence>
from: publish-posts until: run close
what people asked on the organization's own channels once
the creator posts went out
fees - runs allocate-and-reconcile owner: spend-reconciler
from: settle-terms until: run close
handoffs:
take-in-audience -> set-parameters [audience-in-one-line]: who the
campaign is for, in one line that every later decision can be tested
against
set-parameters -> disclosure-rules [markets-and-platforms]: the
markets and the platforms the work will run in
set-parameters -> candidate-list [campaign-parameters]: the audience,
the markets, the deliverables and what there is to spend
set-parameters -> set-up-tracking [parameters-for-tracking]: the same
parameters. Both branches read one record
disclosure-rules -> brief-creators [disclosure-requirements]: what
each market requires a paid post to say, quoted, at the version in
force, with the date it was read
candidate-list -> vet-candidates [candidates-and-figures]: each
candidate with the audience figures, the source they came from and
the date they were read
vet-candidates -> clear-shortlist [vetting-scores]: the scored list,
with the criterion behind every verdict
clear-shortlist -> approach [cleared-creators]: the creators the
signers accepted, and the ones they refused with the reason
approach -> settle-terms [acceptances-and-asks]: who accepted, and the
terms each of them asked for
settle-terms -> brief-creators [signed-deals]: the deal at the version
it was agreed, naming every deliverable, the date each one is due,
the channels the work may run on, how long the organization may use
it, what the disclosure has to say, and the fee
set-up-tracking -> brief-creators [creator-links]: the link and the
code each creator puts in their post, one set per creator
brief-creators -> collect-drafts [creator-brief]: the request as every
creator heard it, the date each deliverable is due, and the
disclosure wording that has to appear
collect-drafts -> review-drafts [creator-drafts]: each draft at the
version the creator sent it
review-drafts -> publish-posts [approved-drafts]: the approved drafts
at the signed version. A later change voids the approval and the
review runs again
publish-posts -> record-posts [posting-claims]: what each creator says
they posted, where they posted it, and on what date
record-posts -> check-disclosure [live-posts]: every live post as it
ran, with its address, the date it appeared and the market it ran in
check-disclosure -> correct-failed [disclosure-failures]: the
failures, each with the rule and the market named
correct-failed -> check-disclosure [corrected-posts]: the corrected
post, scored again before the run closes
deviations:
clear-shortlist -> candidate-list [too-few-cleared]: the signers clear
too few creators, so more candidates are drawn up against the same
audience
approach -> candidate-list [too-few-accepted]: too few creators accept
the offer, so more candidates are drawn up
review-drafts -> collect-drafts [review-changes]: the review asks for
changes, so the creator sends a new draft and only what the signers
named reopens
record-posts -> publish-posts [post-never-ran]: an agreed post never
appeared, so the creator is gone back to for a new date
check-disclosure -> correct-failed [disclosure-missing]: a live post
carries no disclosure, or one a reader has to expand to see, so the
creator is asked to correct it or take it down
bindings:
roster: <who holds each role - agents claiming the abstract agents
above, and named people for legal, brand, rights and
finance>
systems: the creator record (write), the deal record (write),
the contact log (write),
the outreach channel (write, cap: <n> creators/run),
audience measurement sources (read),
the rights record (write), the review record (write),
the coverage record (write), analytics (write),
the CRM (write), tracking and URL tooling (write)
data: the disclosure rules for each market <version>,
brand guidelines <version>, <your claims register>,
the audience definition, the deals as agreed
policy:
the version of each market's disclosure rules is confirmed by a
person before any deal is agreed
no creator is offered money before the audience check and the history
check have both been read by a person
the disclosure the market requires is written into the deal, and a
creator who will not carry it is not paid to publish
sign-off is a human gate and is never delegated to an agent
a draft changed after sign-off goes back through the review
a live post that fails the disclosure check is corrected or taken
down, and the run stays open until the check passes on it
the fee is released only after the disclosure check has passed on
everything that creator published
measures:
cycle time: <target> from the audience to the first post live
volume: <creators per period>
quality gate: every agreed post live, and every live post carrying
the disclosure its market requires
```
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
366 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: influencer campaign id: <team>/influencer-campaign v1
from: ref/mkt/influencer-campaign v1
owner: <who> effective: <date>
trigger: an audience is handed to a campaign in <your planning process>
watch: record=<campaign brief>
system=<your planning process>
change=<an audience is handed to a campaign>
concurrency: runs may overlap - <how many> live at once
goal: every creator the campaign agreed terms with has published what
the deal named, on the date it named, carrying the disclosure the
market it ran in requires
phases:
take-in-audience - human: read the audience the run was given and
write down what the campaign has to do with it
owner: campaign-manager after: trigger
automation: <level>
set-parameters - human: the markets, the platforms, the dates, the
deliverables and the money. <who> confirms the
budget
owner: campaign-manager after: take-in-audience
automation: <level>
disclosure-rules - human: pull what each market and each platform
requires a paid post to say. <your legal
reviewer> confirms which version is in force
owner: researcher after: set-parameters
by: <days> automation: <level>
candidate-list - human: the creators whose following matches the
audience, each with the figures behind it
owner: creator-relations after: set-parameters
by: <days> automation: <level>
vet-candidates - runs assessment: each candidate scored on whether
the audience is real and the history is clean
owner: creator-relations after: candidate-list
by: <days> automation: <level>
clear-shortlist - convenes approval: brand and legal accept, as
named signers, who the organization will pay
owner: <your legal role> after: vet-candidates
by: <days> automation: never
approach - human: the offer goes to each cleared creator and
the answer lands against their name
owner: creator-relations after: clear-shortlist
by: <days> automation: <level>
settle-terms - convenes approval: the deliverables, the dates,
the usage rights, the disclosure and the fee, each
signed by the person who answers for it
owner: creator-relations after: approach
by: <days> automation: never
set-up-tracking - human: the link, the code and the parameters that
make each creator countable on their own
owner: conversion-tracker after: set-parameters
by: brief-creators automation: <level>
brief-creators - convenes briefing: what the campaign is for, what
the deal requires, and what has to be disclosed
owner: campaign-manager
after: settle-terms + disclosure-rules +
set-up-tracking
automation: <level>
collect-drafts - human: each creator sends what the deal said they
owe, on the date it was due
owner: creator-relations after: brief-creators
by: <days> automation: <level>
review-drafts - convenes approval: brand, disclosure and legal
read each draft against the rules, as named
signers, before it goes out
owner: <your legal role> after: collect-drafts
by: <days> automation: never
publish-posts - human: the creators post on the agreed dates, on
their own accounts
owner: creator-relations after: review-drafts
automation: <level>
record-posts - human: every agreed post is found and kept as it
ran, with its address and the date it appeared
owner: coverage-monitor after: publish-posts
by: <days> automation: <level>
check-disclosure - runs assessment: every live post scored against
the disclosure rules of the market it ran in
owner: disclosure-check after: record-posts
by: <days> automation: <level>
correct-failed - human: the agent holding the deal goes back to the
creator, and <who> decides what is asked for
owner: creator-relations after: check-disclosure
by: <hours> automation: <level>
run-scoped:
status - runs roll-call owner: campaign-manager
every: <cadence>
from: brief-creators until: check-disclosure
replies - runs collect-and-report owner: community-manager
every: <cadence>
from: publish-posts until: run close
what people asked on the organization's own channels once
the creator posts went out
fees - runs allocate-and-reconcile owner: spend-reconciler
from: settle-terms until: run close
handoffs:
take-in-audience -> set-parameters [audience-in-one-line]: who the
campaign is for, in one line that every later decision can be tested
against
set-parameters -> disclosure-rules [markets-and-platforms]: the
markets and the platforms the work will run in
set-parameters -> candidate-list [campaign-parameters]: the audience,
the markets, the deliverables and what there is to spend
set-parameters -> set-up-tracking [parameters-for-tracking]: the same
parameters. Both branches read one record
disclosure-rules -> brief-creators [disclosure-requirements]: what
each market requires a paid post to say, quoted, at the version in
force, with the date it was read
candidate-list -> vet-candidates [candidates-and-figures]: each
candidate with the audience figures, the source they came from and
the date they were read
vet-candidates -> clear-shortlist [vetting-scores]: the scored list,
with the criterion behind every verdict
clear-shortlist -> approach [cleared-creators]: the creators the
signers accepted, and the ones they refused with the reason
approach -> settle-terms [acceptances-and-asks]: who accepted, and the
terms each of them asked for
settle-terms -> brief-creators [signed-deals]: the deal at the version
it was agreed, naming every deliverable, the date each one is due,
the channels the work may run on, how long the organization may use
it, what the disclosure has to say, and the fee
set-up-tracking -> brief-creators [creator-links]: the link and the
code each creator puts in their post, one set per creator
brief-creators -> collect-drafts [creator-brief]: the request as every
creator heard it, the date each deliverable is due, and the
disclosure wording that has to appear
collect-drafts -> review-drafts [creator-drafts]: each draft at the
version the creator sent it
review-drafts -> publish-posts [approved-drafts]: the approved drafts
at the signed version. A later change voids the approval and the
review runs again
publish-posts -> record-posts [posting-claims]: what each creator says
they posted, where they posted it, and on what date
record-posts -> check-disclosure [live-posts]: every live post as it
ran, with its address, the date it appeared and the market it ran in
check-disclosure -> correct-failed [disclosure-failures]: the
failures, each with the rule and the market named
correct-failed -> check-disclosure [corrected-posts]: the corrected
post, scored again before the run closes
deviations:
clear-shortlist -> candidate-list [too-few-cleared]: the signers clear
too few creators, so more candidates are drawn up against the same
audience
approach -> candidate-list [too-few-accepted]: too few creators accept
the offer, so more candidates are drawn up
review-drafts -> collect-drafts [review-changes]: the review asks for
changes, so the creator sends a new draft and only what the signers
named reopens
record-posts -> publish-posts [post-never-ran]: an agreed post never
appeared, so the creator is gone back to for a new date
check-disclosure -> correct-failed [disclosure-missing]: a live post
carries no disclosure, or one a reader has to expand to see, so the
creator is asked to correct it or take it down
bindings:
roster: <who holds each role - agents claiming the abstract agents
above, and named people for legal, brand, rights and
finance>
systems: the creator record (write), the deal record (write),
the contact log (write),
the outreach channel (write, cap: <n> creators/run),
audience measurement sources (read),
the rights record (write), the review record (write),
the coverage record (write), analytics (write),
the CRM (write), tracking and URL tooling (write)
data: the disclosure rules for each market <version>,
brand guidelines <version>, <your claims register>,
the audience definition, the deals as agreed
policy:
the version of each market's disclosure rules is confirmed by a
person before any deal is agreed
no creator is offered money before the audience check and the history
check have both been read by a person
the disclosure the market requires is written into the deal, and a
creator who will not carry it is not paid to publish
sign-off is a human gate and is never delegated to an agent
a draft changed after sign-off goes back through the review
a live post that fails the disclosure check is corrected or taken
down, and the run stays open until the check passes on it
the fee is released only after the disclosure check has passed on
everything that creator published
measures:
cycle time: <target> from the audience to the first post live
volume: <creators per period>
quality gate: every agreed post live, and every live post carrying
the disclosure its market requires
```
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
357 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: influencer campaign id: <team>/influencer-campaign v1
from: ref/mkt/influencer-campaign v1
owner: <who> effective: <date>
trigger: an audience is handed to a campaign in <your planning process>
watch: record=<campaign brief>
system=<your planning process>
change=<an audience is handed to a campaign>
concurrency: runs may overlap - <how many> live at once
goal: every creator the campaign agreed terms with has published what
the deal named, on the date it named, carrying the disclosure the
market it ran in requires
phases:
take-in-audience - human: read the audience the run was given and
write down what the campaign has to do with it
owner: campaign-manager after: trigger
automation: <level>
set-parameters - human: the markets, the platforms, the dates, the
deliverables and the money. <who> confirms the
budget
owner: campaign-manager after: take-in-audience
automation: <level>
disclosure-rules - human: pull what each market and each platform
requires a paid post to say. <your legal
reviewer> confirms which version is in force
owner: researcher after: set-parameters
by: <days> automation: <level>
candidate-list - human: the creators whose following matches the
audience, each with the figures behind it
owner: creator-relations after: set-parameters
by: <days> automation: <level>
vet-candidates - runs assessment: each candidate scored on whether
the audience is real and the history is clean
owner: creator-relations after: candidate-list
by: <days> automation: <level>
clear-shortlist - convenes approval: brand and legal accept, as
named signers, who the organization will pay
owner: <your legal role> after: vet-candidates
by: <days> automation: never
approach - human: the offer goes to each cleared creator and
the answer lands against their name
owner: creator-relations after: clear-shortlist
by: <days> automation: <level>
settle-terms - convenes approval: the deliverables, the dates,
the usage rights, the disclosure and the fee, each
signed by the person who answers for it
owner: creator-relations after: approach
by: <days> automation: never
set-up-tracking - human: the link, the code and the parameters that
make each creator countable on their own
owner: conversion-tracker after: set-parameters
by: brief-creators automation: <level>
brief-creators - convenes briefing: what the campaign is for, what
the deal requires, and what has to be disclosed
owner: campaign-manager
after: settle-terms + disclosure-rules +
set-up-tracking
automation: <level>
collect-drafts - human: each creator sends what the deal said they
owe, on the date it was due
owner: creator-relations after: brief-creators
by: <days> automation: <level>
review-drafts - convenes approval: brand, disclosure and legal
read each draft against the rules, as named
signers, before it goes out
owner: <your legal role> after: collect-drafts
by: <days> automation: never
publish-posts - human: the creators post on the agreed dates, on
their own accounts
owner: creator-relations after: review-drafts
automation: <level>
record-posts - human: every agreed post is found and kept as it
ran, with its address and the date it appeared
owner: coverage-monitor after: publish-posts
by: <days> automation: <level>
check-disclosure - runs assessment: every live post scored against
the disclosure rules of the market it ran in
owner: disclosure-check after: record-posts
by: <days> automation: <level>
correct-failed - human: the agent holding the deal goes back to the
creator, and <who> decides what is asked for
owner: creator-relations after: check-disclosure
by: <hours> automation: <level>
run-scoped:
status - runs roll-call owner: campaign-manager
every: <cadence>
from: brief-creators until: check-disclosure
replies - runs collect-and-report owner: community-manager
every: <cadence>
from: publish-posts until: run close
what people asked on the organization's own channels once
the creator posts went out
fees - runs allocate-and-reconcile owner: spend-reconciler
from: settle-terms until: run close
handoffs:
take-in-audience -> set-parameters [audience-in-one-line]: who the
campaign is for, in one line that every later decision can be tested
against
set-parameters -> disclosure-rules [markets-and-platforms]: the
markets and the platforms the work will run in
set-parameters -> candidate-list [campaign-parameters]: the audience,
the markets, the deliverables and what there is to spend
set-parameters -> set-up-tracking [parameters-for-tracking]: the same
parameters. Both branches read one record
disclosure-rules -> brief-creators [disclosure-requirements]: what
each market requires a paid post to say, quoted, at the version in
force, with the date it was read
candidate-list -> vet-candidates [candidates-and-figures]: each
candidate with the audience figures, the source they came from and
the date they were read
vet-candidates -> clear-shortlist [vetting-scores]: the scored list,
with the criterion behind every verdict
clear-shortlist -> approach [cleared-creators]: the creators the
signers accepted, and the ones they refused with the reason
approach -> settle-terms [acceptances-and-asks]: who accepted, and the
terms each of them asked for
settle-terms -> brief-creators [signed-deals]: the deal at the version
it was agreed, naming every deliverable, the date each one is due,
the channels the work may run on, how long the organization may use
it, what the disclosure has to say, and the fee
set-up-tracking -> brief-creators [creator-links]: the link and the
code each creator puts in their post, one set per creator
brief-creators -> collect-drafts [creator-brief]: the request as every
creator heard it, the date each deliverable is due, and the
disclosure wording that has to appear
collect-drafts -> review-drafts [creator-drafts]: each draft at the
version the creator sent it
review-drafts -> publish-posts [approved-drafts]: the approved drafts
at the signed version. A later change voids the approval and the
review runs again
publish-posts -> record-posts [posting-claims]: what each creator says
they posted, where they posted it, and on what date
record-posts -> check-disclosure [live-posts]: every live post as it
ran, with its address, the date it appeared and the market it ran in
check-disclosure -> correct-failed [disclosure-failures]: the
failures, each with the rule and the market named
correct-failed -> check-disclosure [corrected-posts]: the corrected
post, scored again before the run closes
deviations:
clear-shortlist -> candidate-list [too-few-cleared]: the signers clear
too few creators, so more candidates are drawn up against the same
audience
approach -> candidate-list [too-few-accepted]: too few creators accept
the offer, so more candidates are drawn up
review-drafts -> collect-drafts [review-changes]: the review asks for
changes, so the creator sends a new draft and only what the signers
named reopens
record-posts -> publish-posts [post-never-ran]: an agreed post never
appeared, so the creator is gone back to for a new date
check-disclosure -> correct-failed [disclosure-missing]: a live post
carries no disclosure, or one a reader has to expand to see, so the
creator is asked to correct it or take it down
bindings:
roster: <who holds each role - agents claiming the abstract agents
above, and named people for legal, brand, rights and
finance>
systems: the creator record (write), the deal record (write),
the contact log (write),
the outreach channel (write, cap: <n> creators/run),
audience measurement sources (read),
the rights record (write), the review record (write),
the coverage record (write), analytics (write),
the CRM (write), tracking and URL tooling (write)
data: the disclosure rules for each market <version>,
brand guidelines <version>, <your claims register>,
the audience definition, the deals as agreed
policy:
the version of each market's disclosure rules is confirmed by a
person before any deal is agreed
no creator is offered money before the audience check and the history
check have both been read by a person
the disclosure the market requires is written into the deal, and a
creator who will not carry it is not paid to publish
sign-off is a human gate and is never delegated to an agent
a draft changed after sign-off goes back through the review
a live post that fails the disclosure check is corrected or taken
down, and the run stays open until the check passes on it
the fee is released only after the disclosure check has passed on
everything that creator published
measures:
cycle time: <target> from the audience to the first post live
volume: <creators per period>
quality gate: every agreed post live, and every live post carrying
the disclosure its market requires
```
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
44 blanks to fill. Everything else is the process.
this process
from: ref/mkt/influencer-campaign 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.