# Purpose, Participation, and Judgment

**An introduction to the three Chirality theses**

Work begins with something that matters. A person encounters a need, gives it a
first description, and tries to act. The description changes as the work reveals
what was overlooked. Other people contribute. Tools make some actions possible
and some consequences visible. What counts as a useful result depends on the
undertaking and on the world in which that result will be used.

Artificial agents enlarge this activity. They can investigate a question,
interpret sources, develop alternatives, operate software, and carry repairs
through sustained work. Their contribution can change what a person has time to
consider and what a small team can attempt. It also changes the demands on the
surrounding environment. More production can bring more useful inquiry, more
unexamined assumptions, or both. The important question is how that enlarged
capacity becomes purposeful work whose grounds and consequences remain open to
understanding and correction.

The three theses examine this question together. Root develops its normative
orientation and shared means. The App investigates its operative expression.
SWBPIPE examines its adequacy in a particular engineering practice. Iteration
connects the three: experience can change an operation, a method, a representation,
or the understanding of the purpose itself. The argument concerns how these
relationships can be sustained as both capability and circumstances change.

## One undertaking, three perspectives

The [Root thesis](README.md#reading-the-root-thesis) asks what should orient
human–agent work and why its means must remain revisable. Its concern is broader
than a collection of repository instructions. An arrangement for work embodies
choices about what participants can perceive, what they can do, what they must
examine, and who can make a consequential commitment. Roles, methods, tools, and
artifacts give those choices practical form. Their form can be changed when
experience shows that they no longer serve their purpose.

This is the **normative** emphasis. It identifies commitments and offers reasons
for them: useful work, inspectable grounds, intelligible authority, human
answerability, and attention to consequences. Applicable obligations constrain
the arrangement. Chosen mechanisms remain design hypotheses. A requirement to
preserve responsibility does not uniquely determine a hierarchy of agents, a
sequence of approvals, or a format for records.

The [App thesis](../../projects/chirality-app-v4/docs/thesis/THESIS.md) asks how
this orientation becomes actionable within software. A general agent needs a
meaningful relation to the application's objects and operations. A reference
must concern the right object; a proposed change must concern the version that
was examined; a reported outcome must distinguish what happened from what was
only intended. The person must be able to understand and direct that activity.

This is the **operative** emphasis. The workflow-authoring App is a useful first
exemplar because the method of work is itself its subject. A person and an agent
can develop a method through conversation, try it, examine the result, and make
it available for another undertaking. The application can help retain what was
learned while leaving room for circumstances that the method's author did not
anticipate. It must also justify the effort that its own machinery requires.

The [Piping thesis](../../projects/chirality-piping/docs/thesis/THESIS.md) asks
what this arrangement can establish when it enters an engineering practice.
SWBPIPE is an instance of software through which agents participate in domain
work. Its models concern proposed physical arrangements; its calculations depend
on analytical idealizations; its results affect choices with consequences beyond
the application. A successful operation, a verified numerical result, and an
adequate design are different achievements.

This is the **evaluative** emphasis. Engineering gives the common argument a
subject that can resist its assumptions. A model can be internally consistent and
miss a relevant condition. A calculated improvement can make construction or
maintenance more difficult. A common interface can preserve a software operation
while losing part of its practical meaning. Such findings help assess the domain
application and the shared arrangements that were supposed to support it.

These emphases do not divide the work into exclusive territories. Root needs
evidence about its own methods. The App makes normative choices in its defaults
and permissions. Piping depends on workable operations and values that cannot be
read from a result table. Each thesis takes a different position from which to
examine the same relations.

## Four questions throughout

Ontology, epistemology, praxeology, and axiology give this inquiry a second frame.
They apply within each of the three perspectives.

**Ontology asks what the undertaking consists of and how its parts relate.** A
physical support, a model object representing it, a proposed change, an applied
operation, and an acceptance are distinguishable subjects. The distinction matters
when someone acts. A file or field can represent an object or an act without
establishing that the represented condition holds.

**Epistemology asks what supports understanding and a claim.** A source has a
scope; a calculation has assumptions; an observation concerns particular
conditions. Evidence can support an inference, contradict it, or leave a question
unsettled. The presence of a citation, a passing test, or an approval record cannot
settle all of these relationships.

**Praxeology asks how intent becomes usable work.** Inquiry, production,
examination, repair, and integration must connect. A contribution helps the
undertaking when it reaches a use that preserves its relevant meaning. Continuing
ownership, suitable tools, and recoverable outcomes can support that connection.
Their value is assessed through the activity they enable.

**Axiology asks what matters, to whom, and with what consequences.** A candidate
result may serve one purpose while frustrating another. Applicable obligations
and adopted constraints must be distinguished from preferences that admit
tradeoffs. Attention, delay, maintenance, and lost opportunities also count among
the costs of a method. Deciding what deserves investigation already involves
values, before any final comparison of results.

The four questions correct one another. A new consequence can reveal that the
model omitted an important relation. That omission can change the evidence needed
and the action worth taking. A costly examination can still be warranted by a
consequential failure; an unnecessary control can divert attention from that
failure. No one perspective provides a complete account of the undertaking.

## Iteration as learning

Iteration gives these relationships continuity. An outcome can call for repair
within an established method. It can also show that the method addressed the
wrong question or that its objects and criteria need revision. The participants
must be able to distinguish these cases and act within the relevant authority.

Learning requires more than repeating a cycle. A discovered limitation must
affect the next relevant action. A corrected method must reach the place where
it is used. A useful numerical reference must remain available when the engine
changes. When an implementation is replaced, the earlier code, failures, and
successful interactions can contain lessons that its written requirements do
not exhaust.

The iterative relation therefore runs among the theses as well as within their
subjects. A difficulty in SWBPIPE can disclose a weakness in the App's account of
perception or action. That weakness can require a revised shared method. A burden
in that method can prompt a renewed examination of the normative reason for
requiring it. A finding supplies grounds for reconsideration; changes to reserved
commitments remain with the person who has authority to make them.

## Knowing, reckoning, and judgment

The common account depends on a distinction between recorded information and
situated knowing. Sources, models, methods, and explanations make material
available for understanding. They do not contain everything a participant brings
to the work. In this framework, *knowledge* names a knower's situated achievement
and can be incomplete or mistaken. Evidence and criticism matter because that
understanding remains answerable to its subject and open to revision.

Agents contribute **reckoning**: investigation, inference, planning, criticism,
comparison, and adaptive action. The term includes substantial initiative and
reasoning. **Judgment** names the person's situated, committed engagement with
what the work means, what matters, and what they will stand behind. It shapes the
framing, the choice of evidence, the response to an unexpected result, and the
acceptance of reliance. An approval can express that engagement without
exhausting or proving it.

The allocation of responsibility in these theses concerns the professional and
institutional setting being examined. Greater agent capability can change suitable
delegation and supervision. Capability alone does not transfer the person's
commitment or supply a new decision right. The [shared vocabulary](glossary.md)
keeps these distinctions available across the collection.

## What the reader can expect

The theses combine a philosophical account, architectural proposals, and a
development case. These have different standing. Commitments state an adopted
orientation. Design hypotheses propose means of serving it. Observations supply
evidence about identified implementations and circumstances. The collection does
not claim a controlled productivity result or a completed demonstration of every
proposed integration.

Implementation observations retain the common repository basis
`a602024416ace9652f61bb2043889c307fd4e09d`. Publication of this revised argument
does not advance those observations to a later software version. Regulatory
discussion retains its separately identified source editions and interpretive
limits. The [historical appendix](appendix_e_development_history.md) explains
the development that informs the argument. The [philosophical conjecture](appendix_d_framework_s.md)
records a deeper orientation whose acceptance is not required for the practical
claims.

Read Root for the developed account of purpose, knowing, responsibility, and
revisable means. Read App for the conditions of participation within software.
Read Piping for the demands that a particular practice places upon those
conditions. The [worked example](WORKED_EXAMPLE.md) follows one illustrative
design inquiry across both frames. The [shared conclusion](CONCLUSION.md)
returns to what the three establish together and what further experience must
test.