Catalog / Business processes / Marketing / Promise-to-Perception / Conduct Brand Audit
reference process · marketing · 17 activities · 14 on the rosterConduct Brand Audit
A study manager runs one audit of how the brand actually shows up. The manager settles which channels, which period and which markets the audit covers, and the standards keeper names the version of each standard everything will be judged against. The run works out every place somebody outside the organization meets the brand, and it pulls a sample of that material in the form it is really served. Brand check scores each item against the rule it has to meet, and a designer and an editor read the whole sample together, because items that each pass their own rules can still look like they came from more than one company. The coverage monitor reads what outsiders published, the study manager asks customers and prospects what they think the organization stands for, and analytics reports how often people come looking for the organization by name. The run sets all of that against the standard, names every gap with the rule and the evidence under it, and puts the list in front of the brand owner and leadership, who decide gap by gap whether it is fixed now, fixed later, or accepted in writing. The run ends when each gap has been handed to whoever can close it. Brand check scores a single piece before it is published. This process reads a sample of everything already published and reports where it has moved away from the standard.
The walk
The document
One run
Adoption
The activities
What happens in a run
17 activities from a cadence or a concern to the gaps are named and handed on, 2 of them gates a person has to sign. Drag the diagram to move along it.
Conduct Brand Audit a cadence or a concern → the gaps are named and handed on
a rule the text does not settle a channel nobody listed too few answers to read the sample will not carry it a finding is disputed a cadence or a concern 1 Take in the Request read the cadence or the concern that called it 2 Set What the Audit Covers the channels, the period and the markets covered a person signs · never an agent 3 Name the Standard Versions which version of each standard applies 4 Brief the Audit every agent hears the scope and the standard at once 5 List Where the Brand Appe… every place an outsider meets the brand, by channel 6 Draw the Sample what gets read, pulled as it is actually served 7 Score the Sample every item scored against the rule it must meet 8 Read the Set as a Whole whether it all looks and sounds like one company 9 Read What Outsiders Publi… what press, analysts and reviewers said, and when 10 Ask the Audience what customers say the organization stands for 11 Read the Numbers how often people come looking for the name itself 12 Work out the Figures which figures hold and what moved since last time 13 Name the Gaps where the material and the standard do not agree 14 Write the Findings each gap with the rule and the evidence under it 15 Decide What Happens to Ea… fixed now, fixed later, or accepted in writing a person signs · never an agent 16 Hand the Gaps to the Owne… each gap goes to the agent that can close it 17 Record What Was Learned what to repeat, what to avoid the gaps are named and handed on 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: brand audit id: <team> /brand-audit v1
from: ref/mkt/brand-audit v1
owner: <who> effective: <date>
trigger: the audit falls due on <your cadence> , or <who> raises a
concern about how the organization is coming across
watch: every=<your cadence>
or watch: record=<concern> system=<your brand concern record>
change=<a concern about how the organization is coming
across is raised>
concurrency: one run at a time over the same channels and the same
period. Audits of different markets may overlap -
<how many> at once
goal: a named gap for every place the published material and the
standard disagree, each carrying the rule it fails and the
evidence under it, and each handed to whoever can close it
phases:
take-in-request - human: read the cadence or the concern, and write
down what the audit has to settle and by when
owner: study-manager after: trigger
automation: <level>
set-the-scope - human: which channels, which period and which
markets. <who> confirms the scope before any
material is pulled
owner: study-manager after: take-in-request
automation: never
name-versions - human: the version of each standard the material
will be judged against, named before scoring
owner: standards-keeper after: set-the-scope
automation: <level>
brief-the-audit - convenes briefing: the scope, the standard and the
due date, heard by every agent at once
owner: study-manager after: name-versions
automation: <level>
list-the-places - runs collect-and-report: every place somebody
outside the organization meets the brand, channel
by channel, including material the department did
not make
owner: study-manager after: brief-the-audit
by: <days> automation: <level>
draw-the-sample - human: which items get read, how many from each
channel, and how they are drawn. Each item is
pulled in the form it is actually served
owner: study-manager after: list-the-places
by: <days> automation: <level>
score-the-sample - runs assessment: every item scored against the
rule it has to meet, at the named version
owner: brand-check after: draw-the-sample
by: <days> automation: <level>
read-the-set - runs layered-passes: the visual pass and the
language pass over the whole sample, looking for
what no single rule catches
owner: study-manager after: draw-the-sample
by: <days> automation: <level>
read-coverage - runs collect-and-report: what outsiders published
about the organization in the period, quoted
owner: coverage-monitor after: brief-the-audit
by: <days> automation: <level>
ask-the-audience - human: what customers and prospects say the
organization stands for, asked the same way it was
asked last time
owner: study-manager after: brief-the-audit
by: <weeks> automation: <level>
read-the-numbers - human: how often people come looking for the name
itself, and what they ask when they arrive
owner: analytics after: brief-the-audit
by: <days> automation: <level>
work-out-figures - human: which answers can be relied on, each figure
with its range, and what moved since the last
audit
owner: statistician
after: ask-the-audience + read-the-numbers
by: <days> automation: <level>
name-the-gaps - human: every place the material and the standard
do not agree, each one against the rule it fails
owner: study-manager
after: score-the-sample + read-the-set +
read-coverage + work-out-figures
by: <days> automation: <level>
write-findings - runs collect-and-report: the findings on their
date, each gap carrying the rule and the evidence
owner: study-manager after: name-the-gaps
by: <days> automation: <level>
decide-each-gap - convenes decide-and-announce: fixed now, fixed
later, or accepted in writing, gap by gap
owner: study-manager after: write-findings
by: <date> automation: never
hand-off-gaps - human: each gap goes to the agent that can close
it, with the decision and the date attached
owner: study-manager after: decide-each-gap
by: <days> automation: <level>
record-learnings - convenes debrief: what to repeat, what to avoid
owner: study-manager after: hand-off-gaps
automation: <level>
run-scoped:
status - runs roll-call owner: study-manager
every: <cadence>
from: brief-the-audit until: hand-off-gaps
spend - runs allocate-and-reconcile owner: study-manager
from: ask-the-audience until: run close
handoffs:
take-in-request -> set-the-scope [audit-question]: what the audit
has to settle, and the date the findings are owed
set-the-scope -> name-versions [audit-scope]: the channels, the
period and the markets the audit covers, and what it leaves out
name-versions -> brief-the-audit [standard-versions]: each standard
at the version the material will be judged against, and what
changed in it since the last audit
brief-the-audit -> list-the-places / read-coverage / ask-the-audience
/ read-the-numbers [audit-brief]: the scope and the standard as
every agent heard them, and the date each part is due
list-the-places -> draw-the-sample [appearance-list]: every place the
brand appears, by channel, with the agent that answers for each one
draw-the-sample -> score-the-sample [sampled-items]: the sampled
items at the version each was served at, with the date each was
pulled
draw-the-sample -> read-the-set [whole-sample]: the same items, read
together
score-the-sample -> name-the-gaps [item-verdicts]: a verdict per
item, each citing the standard, its version and the rule applied
read-the-set -> name-the-gaps [set-reading]: what the sample looks
and sounds like taken together, with the items that show it named
read-coverage -> name-the-gaps [outside-coverage]: what outsiders
said, attributed and dated, quoted where a summary would lose the
point
ask-the-audience -> work-out-figures [audience-answers]: the answers
as they were given, each marked with the version of the question
it answered
read-the-numbers -> work-out-figures [own-figures]: the
organization's own figures, each naming where it came from and
when it was pulled
work-out-figures -> name-the-gaps [perception-figures]: what people
say the organization stands for, with the range around every
figure and what moved since the last audit
name-the-gaps -> write-findings [named-gaps]: each gap with the rule
it fails, the version of that rule, and the items that show it
write-findings -> decide-each-gap [audit-findings]: the findings at
a version, with everything the audit could not read marked as
unread
decide-each-gap -> hand-off-gaps [gap-decisions]: a decision per
gap, the person who made it, and the date an accepted gap is read
again
hand-off-gaps -> record-learnings [gap-owners]: who took each gap
and what they said they would do about it
deviations:
score-the-sample -> name-versions [rule-does-not-settle]: a rule
does not settle the case in front of it, so the item is held
unscored and what the rule means is written down at its version
read-the-set -> list-the-places [unlisted-channel]: material turns
up from a channel nobody listed, so the places are listed again
and a sample is drawn from the new one
work-out-figures -> ask-the-audience [too-few-answers]: too few
answers came back to read, so the audience is asked again or a
different sample is drawn
name-the-gaps -> draw-the-sample [sample-too-thin]: the sample will
not carry a finding, so more is pulled from that channel before
the gap is named
decide-each-gap -> write-findings [finding-disputed]: a finding is
disputed, so it is restated, narrowed or withdrawn with the reason
recorded beside it
bindings:
roster: <who holds each role - agents claiming the abstract agents
above, and named people for the requester, the brand owner
and leadership>
systems: the audit record (write), the study record (write),
the response record (write), the survey and interview
system (trigger), the CMS (read), the asset store (read),
the content inventory (read), the standards store (read),
the claims register (read), the coverage record (read),
analytics platforms (read), the consent record (read),
the contact database (read), the notification channel
(write), the meeting calendar (write)
data: brand guidelines <version> , <your claims register> ,
<your consent rules> <version> , the last audit at the
version it ran under
policy:
nothing is scored until the version of every standard is named
material is judged against the version of the standard in force when
it was made, until <who> says otherwise
every gap carries the rule it fails, the version of that rule, and
the items that show it
a gap is accepted only in writing, by a named person, with the date
it is read again
a finding is never dropped because somebody asked. <who> decides,
and the decision is recorded with the findings
this run names gaps and hands them on, and no agent in it changes the
material or the standard
the questions put to the audience are reworded only when <who>
agrees, because the readings before and after stop being comparable
measures:
cycle time: <target> from the trigger to the delivered findings
coverage: <share> of the channels in scope with a sample drawn
closure: <share> of gaps with a decision recorded within <days>
quality gate: no gap is reported without the rule and the evidence
under it
Copy
Take it somewhere
Use this process in LangGraph
close
Paste this into an assistant that can read the web, such as Claude, ChatGPT or Cursor. It reads the specification and the current LangGraph documentation, then writes two files: the graph, and a note on what did not survive the translation. Read the note first. What a runtime cannot express is the part worth arguing about, and this process is a draft to argue with.
copy the prompt
317 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: brand audit id: <team>/brand-audit v1
from: ref/mkt/brand-audit v1
owner: <who> effective: <date>
trigger: the audit falls due on <your cadence>, or <who> raises a
concern about how the organization is coming across
watch: every=<your cadence>
or watch: record=<concern> system=<your brand concern record>
change=<a concern about how the organization is coming
across is raised>
concurrency: one run at a time over the same channels and the same
period. Audits of different markets may overlap -
<how many> at once
goal: a named gap for every place the published material and the
standard disagree, each carrying the rule it fails and the
evidence under it, and each handed to whoever can close it
phases:
take-in-request - human: read the cadence or the concern, and write
down what the audit has to settle and by when
owner: study-manager after: trigger
automation: <level>
set-the-scope - human: which channels, which period and which
markets. <who> confirms the scope before any
material is pulled
owner: study-manager after: take-in-request
automation: never
name-versions - human: the version of each standard the material
will be judged against, named before scoring
owner: standards-keeper after: set-the-scope
automation: <level>
brief-the-audit - convenes briefing: the scope, the standard and the
due date, heard by every agent at once
owner: study-manager after: name-versions
automation: <level>
list-the-places - runs collect-and-report: every place somebody
outside the organization meets the brand, channel
by channel, including material the department did
not make
owner: study-manager after: brief-the-audit
by: <days> automation: <level>
draw-the-sample - human: which items get read, how many from each
channel, and how they are drawn. Each item is
pulled in the form it is actually served
owner: study-manager after: list-the-places
by: <days> automation: <level>
score-the-sample - runs assessment: every item scored against the
rule it has to meet, at the named version
owner: brand-check after: draw-the-sample
by: <days> automation: <level>
read-the-set - runs layered-passes: the visual pass and the
language pass over the whole sample, looking for
what no single rule catches
owner: study-manager after: draw-the-sample
by: <days> automation: <level>
read-coverage - runs collect-and-report: what outsiders published
about the organization in the period, quoted
owner: coverage-monitor after: brief-the-audit
by: <days> automation: <level>
ask-the-audience - human: what customers and prospects say the
organization stands for, asked the same way it was
asked last time
owner: study-manager after: brief-the-audit
by: <weeks> automation: <level>
read-the-numbers - human: how often people come looking for the name
itself, and what they ask when they arrive
owner: analytics after: brief-the-audit
by: <days> automation: <level>
work-out-figures - human: which answers can be relied on, each figure
with its range, and what moved since the last
audit
owner: statistician
after: ask-the-audience + read-the-numbers
by: <days> automation: <level>
name-the-gaps - human: every place the material and the standard
do not agree, each one against the rule it fails
owner: study-manager
after: score-the-sample + read-the-set +
read-coverage + work-out-figures
by: <days> automation: <level>
write-findings - runs collect-and-report: the findings on their
date, each gap carrying the rule and the evidence
owner: study-manager after: name-the-gaps
by: <days> automation: <level>
decide-each-gap - convenes decide-and-announce: fixed now, fixed
later, or accepted in writing, gap by gap
owner: study-manager after: write-findings
by: <date> automation: never
hand-off-gaps - human: each gap goes to the agent that can close
it, with the decision and the date attached
owner: study-manager after: decide-each-gap
by: <days> automation: <level>
record-learnings - convenes debrief: what to repeat, what to avoid
owner: study-manager after: hand-off-gaps
automation: <level>
run-scoped:
status - runs roll-call owner: study-manager
every: <cadence>
from: brief-the-audit until: hand-off-gaps
spend - runs allocate-and-reconcile owner: study-manager
from: ask-the-audience until: run close
handoffs:
take-in-request -> set-the-scope [audit-question]: what the audit
has to settle, and the date the findings are owed
set-the-scope -> name-versions [audit-scope]: the channels, the
period and the markets the audit covers, and what it leaves out
name-versions -> brief-the-audit [standard-versions]: each standard
at the version the material will be judged against, and what
changed in it since the last audit
brief-the-audit -> list-the-places / read-coverage / ask-the-audience
/ read-the-numbers [audit-brief]: the scope and the standard as
every agent heard them, and the date each part is due
list-the-places -> draw-the-sample [appearance-list]: every place the
brand appears, by channel, with the agent that answers for each one
draw-the-sample -> score-the-sample [sampled-items]: the sampled
items at the version each was served at, with the date each was
pulled
draw-the-sample -> read-the-set [whole-sample]: the same items, read
together
score-the-sample -> name-the-gaps [item-verdicts]: a verdict per
item, each citing the standard, its version and the rule applied
read-the-set -> name-the-gaps [set-reading]: what the sample looks
and sounds like taken together, with the items that show it named
read-coverage -> name-the-gaps [outside-coverage]: what outsiders
said, attributed and dated, quoted where a summary would lose the
point
ask-the-audience -> work-out-figures [audience-answers]: the answers
as they were given, each marked with the version of the question
it answered
read-the-numbers -> work-out-figures [own-figures]: the
organization's own figures, each naming where it came from and
when it was pulled
work-out-figures -> name-the-gaps [perception-figures]: what people
say the organization stands for, with the range around every
figure and what moved since the last audit
name-the-gaps -> write-findings [named-gaps]: each gap with the rule
it fails, the version of that rule, and the items that show it
write-findings -> decide-each-gap [audit-findings]: the findings at
a version, with everything the audit could not read marked as
unread
decide-each-gap -> hand-off-gaps [gap-decisions]: a decision per
gap, the person who made it, and the date an accepted gap is read
again
hand-off-gaps -> record-learnings [gap-owners]: who took each gap
and what they said they would do about it
deviations:
score-the-sample -> name-versions [rule-does-not-settle]: a rule
does not settle the case in front of it, so the item is held
unscored and what the rule means is written down at its version
read-the-set -> list-the-places [unlisted-channel]: material turns
up from a channel nobody listed, so the places are listed again
and a sample is drawn from the new one
work-out-figures -> ask-the-audience [too-few-answers]: too few
answers came back to read, so the audience is asked again or a
different sample is drawn
name-the-gaps -> draw-the-sample [sample-too-thin]: the sample will
not carry a finding, so more is pulled from that channel before
the gap is named
decide-each-gap -> write-findings [finding-disputed]: a finding is
disputed, so it is restated, narrowed or withdrawn with the reason
recorded beside it
bindings:
roster: <who holds each role - agents claiming the abstract agents
above, and named people for the requester, the brand owner
and leadership>
systems: the audit record (write), the study record (write),
the response record (write), the survey and interview
system (trigger), the CMS (read), the asset store (read),
the content inventory (read), the standards store (read),
the claims register (read), the coverage record (read),
analytics platforms (read), the consent record (read),
the contact database (read), the notification channel
(write), the meeting calendar (write)
data: brand guidelines <version>, <your claims register>,
<your consent rules> <version>, the last audit at the
version it ran under
policy:
nothing is scored until the version of every standard is named
material is judged against the version of the standard in force when
it was made, until <who> says otherwise
every gap carries the rule it fails, the version of that rule, and
the items that show it
a gap is accepted only in writing, by a named person, with the date
it is read again
a finding is never dropped because somebody asked. <who> decides,
and the decision is recorded with the findings
this run names gaps and hands them on, and no agent in it changes the
material or the standard
the questions put to the audience are reworded only when <who>
agrees, because the readings before and after stop being comparable
measures:
cycle time: <target> from the trigger to the delivered findings
coverage: <share> of the channels in scope with a sample drawn
closure: <share> of gaps with a decision recorded within <days>
quality gate: no gap is reported without the rule and the evidence
under it
```
Take it somewhere
Use this process in Microsoft Agent Framework
close
Paste this into an assistant that can read the web, such as Claude, ChatGPT or Cursor. It reads the specification and the current Agent Framework documentation, then writes two files: the workflow, and a note on what did not survive the translation. Read the note first. What a runtime cannot express is the part worth arguing about, and this process is a draft to argue with.
copy the prompt
372 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: brand audit id: <team>/brand-audit v1
from: ref/mkt/brand-audit v1
owner: <who> effective: <date>
trigger: the audit falls due on <your cadence>, or <who> raises a
concern about how the organization is coming across
watch: every=<your cadence>
or watch: record=<concern> system=<your brand concern record>
change=<a concern about how the organization is coming
across is raised>
concurrency: one run at a time over the same channels and the same
period. Audits of different markets may overlap -
<how many> at once
goal: a named gap for every place the published material and the
standard disagree, each carrying the rule it fails and the
evidence under it, and each handed to whoever can close it
phases:
take-in-request - human: read the cadence or the concern, and write
down what the audit has to settle and by when
owner: study-manager after: trigger
automation: <level>
set-the-scope - human: which channels, which period and which
markets. <who> confirms the scope before any
material is pulled
owner: study-manager after: take-in-request
automation: never
name-versions - human: the version of each standard the material
will be judged against, named before scoring
owner: standards-keeper after: set-the-scope
automation: <level>
brief-the-audit - convenes briefing: the scope, the standard and the
due date, heard by every agent at once
owner: study-manager after: name-versions
automation: <level>
list-the-places - runs collect-and-report: every place somebody
outside the organization meets the brand, channel
by channel, including material the department did
not make
owner: study-manager after: brief-the-audit
by: <days> automation: <level>
draw-the-sample - human: which items get read, how many from each
channel, and how they are drawn. Each item is
pulled in the form it is actually served
owner: study-manager after: list-the-places
by: <days> automation: <level>
score-the-sample - runs assessment: every item scored against the
rule it has to meet, at the named version
owner: brand-check after: draw-the-sample
by: <days> automation: <level>
read-the-set - runs layered-passes: the visual pass and the
language pass over the whole sample, looking for
what no single rule catches
owner: study-manager after: draw-the-sample
by: <days> automation: <level>
read-coverage - runs collect-and-report: what outsiders published
about the organization in the period, quoted
owner: coverage-monitor after: brief-the-audit
by: <days> automation: <level>
ask-the-audience - human: what customers and prospects say the
organization stands for, asked the same way it was
asked last time
owner: study-manager after: brief-the-audit
by: <weeks> automation: <level>
read-the-numbers - human: how often people come looking for the name
itself, and what they ask when they arrive
owner: analytics after: brief-the-audit
by: <days> automation: <level>
work-out-figures - human: which answers can be relied on, each figure
with its range, and what moved since the last
audit
owner: statistician
after: ask-the-audience + read-the-numbers
by: <days> automation: <level>
name-the-gaps - human: every place the material and the standard
do not agree, each one against the rule it fails
owner: study-manager
after: score-the-sample + read-the-set +
read-coverage + work-out-figures
by: <days> automation: <level>
write-findings - runs collect-and-report: the findings on their
date, each gap carrying the rule and the evidence
owner: study-manager after: name-the-gaps
by: <days> automation: <level>
decide-each-gap - convenes decide-and-announce: fixed now, fixed
later, or accepted in writing, gap by gap
owner: study-manager after: write-findings
by: <date> automation: never
hand-off-gaps - human: each gap goes to the agent that can close
it, with the decision and the date attached
owner: study-manager after: decide-each-gap
by: <days> automation: <level>
record-learnings - convenes debrief: what to repeat, what to avoid
owner: study-manager after: hand-off-gaps
automation: <level>
run-scoped:
status - runs roll-call owner: study-manager
every: <cadence>
from: brief-the-audit until: hand-off-gaps
spend - runs allocate-and-reconcile owner: study-manager
from: ask-the-audience until: run close
handoffs:
take-in-request -> set-the-scope [audit-question]: what the audit
has to settle, and the date the findings are owed
set-the-scope -> name-versions [audit-scope]: the channels, the
period and the markets the audit covers, and what it leaves out
name-versions -> brief-the-audit [standard-versions]: each standard
at the version the material will be judged against, and what
changed in it since the last audit
brief-the-audit -> list-the-places / read-coverage / ask-the-audience
/ read-the-numbers [audit-brief]: the scope and the standard as
every agent heard them, and the date each part is due
list-the-places -> draw-the-sample [appearance-list]: every place the
brand appears, by channel, with the agent that answers for each one
draw-the-sample -> score-the-sample [sampled-items]: the sampled
items at the version each was served at, with the date each was
pulled
draw-the-sample -> read-the-set [whole-sample]: the same items, read
together
score-the-sample -> name-the-gaps [item-verdicts]: a verdict per
item, each citing the standard, its version and the rule applied
read-the-set -> name-the-gaps [set-reading]: what the sample looks
and sounds like taken together, with the items that show it named
read-coverage -> name-the-gaps [outside-coverage]: what outsiders
said, attributed and dated, quoted where a summary would lose the
point
ask-the-audience -> work-out-figures [audience-answers]: the answers
as they were given, each marked with the version of the question
it answered
read-the-numbers -> work-out-figures [own-figures]: the
organization's own figures, each naming where it came from and
when it was pulled
work-out-figures -> name-the-gaps [perception-figures]: what people
say the organization stands for, with the range around every
figure and what moved since the last audit
name-the-gaps -> write-findings [named-gaps]: each gap with the rule
it fails, the version of that rule, and the items that show it
write-findings -> decide-each-gap [audit-findings]: the findings at
a version, with everything the audit could not read marked as
unread
decide-each-gap -> hand-off-gaps [gap-decisions]: a decision per
gap, the person who made it, and the date an accepted gap is read
again
hand-off-gaps -> record-learnings [gap-owners]: who took each gap
and what they said they would do about it
deviations:
score-the-sample -> name-versions [rule-does-not-settle]: a rule
does not settle the case in front of it, so the item is held
unscored and what the rule means is written down at its version
read-the-set -> list-the-places [unlisted-channel]: material turns
up from a channel nobody listed, so the places are listed again
and a sample is drawn from the new one
work-out-figures -> ask-the-audience [too-few-answers]: too few
answers came back to read, so the audience is asked again or a
different sample is drawn
name-the-gaps -> draw-the-sample [sample-too-thin]: the sample will
not carry a finding, so more is pulled from that channel before
the gap is named
decide-each-gap -> write-findings [finding-disputed]: a finding is
disputed, so it is restated, narrowed or withdrawn with the reason
recorded beside it
bindings:
roster: <who holds each role - agents claiming the abstract agents
above, and named people for the requester, the brand owner
and leadership>
systems: the audit record (write), the study record (write),
the response record (write), the survey and interview
system (trigger), the CMS (read), the asset store (read),
the content inventory (read), the standards store (read),
the claims register (read), the coverage record (read),
analytics platforms (read), the consent record (read),
the contact database (read), the notification channel
(write), the meeting calendar (write)
data: brand guidelines <version>, <your claims register>,
<your consent rules> <version>, the last audit at the
version it ran under
policy:
nothing is scored until the version of every standard is named
material is judged against the version of the standard in force when
it was made, until <who> says otherwise
every gap carries the rule it fails, the version of that rule, and
the items that show it
a gap is accepted only in writing, by a named person, with the date
it is read again
a finding is never dropped because somebody asked. <who> decides,
and the decision is recorded with the findings
this run names gaps and hands them on, and no agent in it changes the
material or the standard
the questions put to the audience are reworded only when <who>
agrees, because the readings before and after stop being comparable
measures:
cycle time: <target> from the trigger to the delivered findings
coverage: <share> of the channels in scope with a sample drawn
closure: <share> of gaps with a decision recorded within <days>
quality gate: no gap is reported without the rule and the evidence
under it
```
Take it somewhere
Use this process in CrewAI Flows
close
Paste this into an assistant that can read the web, such as Claude, ChatGPT or Cursor. It reads the specification and the current CrewAI documentation, then writes two files: the flow, and a note on what did not survive the translation. Read the note first. What a runtime cannot express is the part worth arguing about, and this process is a draft to argue with.
copy the prompt
377 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: brand audit id: <team>/brand-audit v1
from: ref/mkt/brand-audit v1
owner: <who> effective: <date>
trigger: the audit falls due on <your cadence>, or <who> raises a
concern about how the organization is coming across
watch: every=<your cadence>
or watch: record=<concern> system=<your brand concern record>
change=<a concern about how the organization is coming
across is raised>
concurrency: one run at a time over the same channels and the same
period. Audits of different markets may overlap -
<how many> at once
goal: a named gap for every place the published material and the
standard disagree, each carrying the rule it fails and the
evidence under it, and each handed to whoever can close it
phases:
take-in-request - human: read the cadence or the concern, and write
down what the audit has to settle and by when
owner: study-manager after: trigger
automation: <level>
set-the-scope - human: which channels, which period and which
markets. <who> confirms the scope before any
material is pulled
owner: study-manager after: take-in-request
automation: never
name-versions - human: the version of each standard the material
will be judged against, named before scoring
owner: standards-keeper after: set-the-scope
automation: <level>
brief-the-audit - convenes briefing: the scope, the standard and the
due date, heard by every agent at once
owner: study-manager after: name-versions
automation: <level>
list-the-places - runs collect-and-report: every place somebody
outside the organization meets the brand, channel
by channel, including material the department did
not make
owner: study-manager after: brief-the-audit
by: <days> automation: <level>
draw-the-sample - human: which items get read, how many from each
channel, and how they are drawn. Each item is
pulled in the form it is actually served
owner: study-manager after: list-the-places
by: <days> automation: <level>
score-the-sample - runs assessment: every item scored against the
rule it has to meet, at the named version
owner: brand-check after: draw-the-sample
by: <days> automation: <level>
read-the-set - runs layered-passes: the visual pass and the
language pass over the whole sample, looking for
what no single rule catches
owner: study-manager after: draw-the-sample
by: <days> automation: <level>
read-coverage - runs collect-and-report: what outsiders published
about the organization in the period, quoted
owner: coverage-monitor after: brief-the-audit
by: <days> automation: <level>
ask-the-audience - human: what customers and prospects say the
organization stands for, asked the same way it was
asked last time
owner: study-manager after: brief-the-audit
by: <weeks> automation: <level>
read-the-numbers - human: how often people come looking for the name
itself, and what they ask when they arrive
owner: analytics after: brief-the-audit
by: <days> automation: <level>
work-out-figures - human: which answers can be relied on, each figure
with its range, and what moved since the last
audit
owner: statistician
after: ask-the-audience + read-the-numbers
by: <days> automation: <level>
name-the-gaps - human: every place the material and the standard
do not agree, each one against the rule it fails
owner: study-manager
after: score-the-sample + read-the-set +
read-coverage + work-out-figures
by: <days> automation: <level>
write-findings - runs collect-and-report: the findings on their
date, each gap carrying the rule and the evidence
owner: study-manager after: name-the-gaps
by: <days> automation: <level>
decide-each-gap - convenes decide-and-announce: fixed now, fixed
later, or accepted in writing, gap by gap
owner: study-manager after: write-findings
by: <date> automation: never
hand-off-gaps - human: each gap goes to the agent that can close
it, with the decision and the date attached
owner: study-manager after: decide-each-gap
by: <days> automation: <level>
record-learnings - convenes debrief: what to repeat, what to avoid
owner: study-manager after: hand-off-gaps
automation: <level>
run-scoped:
status - runs roll-call owner: study-manager
every: <cadence>
from: brief-the-audit until: hand-off-gaps
spend - runs allocate-and-reconcile owner: study-manager
from: ask-the-audience until: run close
handoffs:
take-in-request -> set-the-scope [audit-question]: what the audit
has to settle, and the date the findings are owed
set-the-scope -> name-versions [audit-scope]: the channels, the
period and the markets the audit covers, and what it leaves out
name-versions -> brief-the-audit [standard-versions]: each standard
at the version the material will be judged against, and what
changed in it since the last audit
brief-the-audit -> list-the-places / read-coverage / ask-the-audience
/ read-the-numbers [audit-brief]: the scope and the standard as
every agent heard them, and the date each part is due
list-the-places -> draw-the-sample [appearance-list]: every place the
brand appears, by channel, with the agent that answers for each one
draw-the-sample -> score-the-sample [sampled-items]: the sampled
items at the version each was served at, with the date each was
pulled
draw-the-sample -> read-the-set [whole-sample]: the same items, read
together
score-the-sample -> name-the-gaps [item-verdicts]: a verdict per
item, each citing the standard, its version and the rule applied
read-the-set -> name-the-gaps [set-reading]: what the sample looks
and sounds like taken together, with the items that show it named
read-coverage -> name-the-gaps [outside-coverage]: what outsiders
said, attributed and dated, quoted where a summary would lose the
point
ask-the-audience -> work-out-figures [audience-answers]: the answers
as they were given, each marked with the version of the question
it answered
read-the-numbers -> work-out-figures [own-figures]: the
organization's own figures, each naming where it came from and
when it was pulled
work-out-figures -> name-the-gaps [perception-figures]: what people
say the organization stands for, with the range around every
figure and what moved since the last audit
name-the-gaps -> write-findings [named-gaps]: each gap with the rule
it fails, the version of that rule, and the items that show it
write-findings -> decide-each-gap [audit-findings]: the findings at
a version, with everything the audit could not read marked as
unread
decide-each-gap -> hand-off-gaps [gap-decisions]: a decision per
gap, the person who made it, and the date an accepted gap is read
again
hand-off-gaps -> record-learnings [gap-owners]: who took each gap
and what they said they would do about it
deviations:
score-the-sample -> name-versions [rule-does-not-settle]: a rule
does not settle the case in front of it, so the item is held
unscored and what the rule means is written down at its version
read-the-set -> list-the-places [unlisted-channel]: material turns
up from a channel nobody listed, so the places are listed again
and a sample is drawn from the new one
work-out-figures -> ask-the-audience [too-few-answers]: too few
answers came back to read, so the audience is asked again or a
different sample is drawn
name-the-gaps -> draw-the-sample [sample-too-thin]: the sample will
not carry a finding, so more is pulled from that channel before
the gap is named
decide-each-gap -> write-findings [finding-disputed]: a finding is
disputed, so it is restated, narrowed or withdrawn with the reason
recorded beside it
bindings:
roster: <who holds each role - agents claiming the abstract agents
above, and named people for the requester, the brand owner
and leadership>
systems: the audit record (write), the study record (write),
the response record (write), the survey and interview
system (trigger), the CMS (read), the asset store (read),
the content inventory (read), the standards store (read),
the claims register (read), the coverage record (read),
analytics platforms (read), the consent record (read),
the contact database (read), the notification channel
(write), the meeting calendar (write)
data: brand guidelines <version>, <your claims register>,
<your consent rules> <version>, the last audit at the
version it ran under
policy:
nothing is scored until the version of every standard is named
material is judged against the version of the standard in force when
it was made, until <who> says otherwise
every gap carries the rule it fails, the version of that rule, and
the items that show it
a gap is accepted only in writing, by a named person, with the date
it is read again
a finding is never dropped because somebody asked. <who> decides,
and the decision is recorded with the findings
this run names gaps and hands them on, and no agent in it changes the
material or the standard
the questions put to the audience are reworded only when <who>
agrees, because the readings before and after stop being comparable
measures:
cycle time: <target> from the trigger to the delivered findings
coverage: <share> of the channels in scope with a sample drawn
closure: <share> of gaps with a decision recorded within <days>
quality gate: no gap is reported without the rule and the evidence
under it
```
Take it somewhere
Use this process in Google ADK
close
Paste this into an assistant that can read the web, such as Claude, ChatGPT or Cursor. It reads the specification and the current ADK documentation, then writes two files: the workflow, and a note on what did not survive the translation. Read the note first. What a runtime cannot express is the part worth arguing about, and this process is a draft to argue with.
copy the prompt
368 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: brand audit id: <team>/brand-audit v1
from: ref/mkt/brand-audit v1
owner: <who> effective: <date>
trigger: the audit falls due on <your cadence>, or <who> raises a
concern about how the organization is coming across
watch: every=<your cadence>
or watch: record=<concern> system=<your brand concern record>
change=<a concern about how the organization is coming
across is raised>
concurrency: one run at a time over the same channels and the same
period. Audits of different markets may overlap -
<how many> at once
goal: a named gap for every place the published material and the
standard disagree, each carrying the rule it fails and the
evidence under it, and each handed to whoever can close it
phases:
take-in-request - human: read the cadence or the concern, and write
down what the audit has to settle and by when
owner: study-manager after: trigger
automation: <level>
set-the-scope - human: which channels, which period and which
markets. <who> confirms the scope before any
material is pulled
owner: study-manager after: take-in-request
automation: never
name-versions - human: the version of each standard the material
will be judged against, named before scoring
owner: standards-keeper after: set-the-scope
automation: <level>
brief-the-audit - convenes briefing: the scope, the standard and the
due date, heard by every agent at once
owner: study-manager after: name-versions
automation: <level>
list-the-places - runs collect-and-report: every place somebody
outside the organization meets the brand, channel
by channel, including material the department did
not make
owner: study-manager after: brief-the-audit
by: <days> automation: <level>
draw-the-sample - human: which items get read, how many from each
channel, and how they are drawn. Each item is
pulled in the form it is actually served
owner: study-manager after: list-the-places
by: <days> automation: <level>
score-the-sample - runs assessment: every item scored against the
rule it has to meet, at the named version
owner: brand-check after: draw-the-sample
by: <days> automation: <level>
read-the-set - runs layered-passes: the visual pass and the
language pass over the whole sample, looking for
what no single rule catches
owner: study-manager after: draw-the-sample
by: <days> automation: <level>
read-coverage - runs collect-and-report: what outsiders published
about the organization in the period, quoted
owner: coverage-monitor after: brief-the-audit
by: <days> automation: <level>
ask-the-audience - human: what customers and prospects say the
organization stands for, asked the same way it was
asked last time
owner: study-manager after: brief-the-audit
by: <weeks> automation: <level>
read-the-numbers - human: how often people come looking for the name
itself, and what they ask when they arrive
owner: analytics after: brief-the-audit
by: <days> automation: <level>
work-out-figures - human: which answers can be relied on, each figure
with its range, and what moved since the last
audit
owner: statistician
after: ask-the-audience + read-the-numbers
by: <days> automation: <level>
name-the-gaps - human: every place the material and the standard
do not agree, each one against the rule it fails
owner: study-manager
after: score-the-sample + read-the-set +
read-coverage + work-out-figures
by: <days> automation: <level>
write-findings - runs collect-and-report: the findings on their
date, each gap carrying the rule and the evidence
owner: study-manager after: name-the-gaps
by: <days> automation: <level>
decide-each-gap - convenes decide-and-announce: fixed now, fixed
later, or accepted in writing, gap by gap
owner: study-manager after: write-findings
by: <date> automation: never
hand-off-gaps - human: each gap goes to the agent that can close
it, with the decision and the date attached
owner: study-manager after: decide-each-gap
by: <days> automation: <level>
record-learnings - convenes debrief: what to repeat, what to avoid
owner: study-manager after: hand-off-gaps
automation: <level>
run-scoped:
status - runs roll-call owner: study-manager
every: <cadence>
from: brief-the-audit until: hand-off-gaps
spend - runs allocate-and-reconcile owner: study-manager
from: ask-the-audience until: run close
handoffs:
take-in-request -> set-the-scope [audit-question]: what the audit
has to settle, and the date the findings are owed
set-the-scope -> name-versions [audit-scope]: the channels, the
period and the markets the audit covers, and what it leaves out
name-versions -> brief-the-audit [standard-versions]: each standard
at the version the material will be judged against, and what
changed in it since the last audit
brief-the-audit -> list-the-places / read-coverage / ask-the-audience
/ read-the-numbers [audit-brief]: the scope and the standard as
every agent heard them, and the date each part is due
list-the-places -> draw-the-sample [appearance-list]: every place the
brand appears, by channel, with the agent that answers for each one
draw-the-sample -> score-the-sample [sampled-items]: the sampled
items at the version each was served at, with the date each was
pulled
draw-the-sample -> read-the-set [whole-sample]: the same items, read
together
score-the-sample -> name-the-gaps [item-verdicts]: a verdict per
item, each citing the standard, its version and the rule applied
read-the-set -> name-the-gaps [set-reading]: what the sample looks
and sounds like taken together, with the items that show it named
read-coverage -> name-the-gaps [outside-coverage]: what outsiders
said, attributed and dated, quoted where a summary would lose the
point
ask-the-audience -> work-out-figures [audience-answers]: the answers
as they were given, each marked with the version of the question
it answered
read-the-numbers -> work-out-figures [own-figures]: the
organization's own figures, each naming where it came from and
when it was pulled
work-out-figures -> name-the-gaps [perception-figures]: what people
say the organization stands for, with the range around every
figure and what moved since the last audit
name-the-gaps -> write-findings [named-gaps]: each gap with the rule
it fails, the version of that rule, and the items that show it
write-findings -> decide-each-gap [audit-findings]: the findings at
a version, with everything the audit could not read marked as
unread
decide-each-gap -> hand-off-gaps [gap-decisions]: a decision per
gap, the person who made it, and the date an accepted gap is read
again
hand-off-gaps -> record-learnings [gap-owners]: who took each gap
and what they said they would do about it
deviations:
score-the-sample -> name-versions [rule-does-not-settle]: a rule
does not settle the case in front of it, so the item is held
unscored and what the rule means is written down at its version
read-the-set -> list-the-places [unlisted-channel]: material turns
up from a channel nobody listed, so the places are listed again
and a sample is drawn from the new one
work-out-figures -> ask-the-audience [too-few-answers]: too few
answers came back to read, so the audience is asked again or a
different sample is drawn
name-the-gaps -> draw-the-sample [sample-too-thin]: the sample will
not carry a finding, so more is pulled from that channel before
the gap is named
decide-each-gap -> write-findings [finding-disputed]: a finding is
disputed, so it is restated, narrowed or withdrawn with the reason
recorded beside it
bindings:
roster: <who holds each role - agents claiming the abstract agents
above, and named people for the requester, the brand owner
and leadership>
systems: the audit record (write), the study record (write),
the response record (write), the survey and interview
system (trigger), the CMS (read), the asset store (read),
the content inventory (read), the standards store (read),
the claims register (read), the coverage record (read),
analytics platforms (read), the consent record (read),
the contact database (read), the notification channel
(write), the meeting calendar (write)
data: brand guidelines <version>, <your claims register>,
<your consent rules> <version>, the last audit at the
version it ran under
policy:
nothing is scored until the version of every standard is named
material is judged against the version of the standard in force when
it was made, until <who> says otherwise
every gap carries the rule it fails, the version of that rule, and
the items that show it
a gap is accepted only in writing, by a named person, with the date
it is read again
a finding is never dropped because somebody asked. <who> decides,
and the decision is recorded with the findings
this run names gaps and hands them on, and no agent in it changes the
material or the standard
the questions put to the audience are reworded only when <who>
agrees, because the readings before and after stop being comparable
measures:
cycle time: <target> from the trigger to the delivered findings
coverage: <share> of the channels in scope with a sample drawn
closure: <share> of gaps with a decision recorded within <days>
quality gate: no gap is reported without the rule and the evidence
under it
```
One run
A simulation of one run
The activities are on the left, whoever is doing the active one is on the right, and the record of the run builds up as it goes.
This run is built from the same rows as the diagram above: the left column is the activity list, the captions are the activity lines, the cast is the roster, and the labels on the wires are what the handoffs say actually passes.
Adoption
What you fill in
49 blanks to fill. Everything else is the process.
this process
from: ref/mkt/brand-audit 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.