๐พ๐๐ฃ ๐ผ๐ ๐๐๐๐ฃ๐ฉ๐จ ๐ข๐๐ ๐ ๐ค๐ช๐ง ๐ผ๐๐๐ก๐ ๐ฉ๐๐๐ข๐จ ๐๐๐จ๐ฉ๐๐ง?
Most organizations think the big question is:
โ๐พ๐๐ฃ ๐ผ๐ ๐๐๐๐ฃ๐ฉ๐จ ๐ข๐๐ ๐ ๐ค๐ช๐ง ๐ผ๐๐๐ก๐ ๐ฉ๐๐๐ข๐จ ๐๐๐จ๐ฉ๐๐ง?โ
Theyโre asking the wrong question.
Humanโcentric Agile and agentโdriven systems are not interchangeable; they optimise forย different kinds of intelligence. ๐ผ๐๐๐ก๐ ๐ฉ๐๐๐ข๐จ ๐๐ง๐ ๐จ๐ค๐๐๐๐ก ๐ก๐๐๐ง๐ฃ๐๐ฃ๐ ๐จ๐ฎ๐จ๐ฉ๐๐ข๐จ โ ๐ฉ๐๐๐ฎ ๐๐ง๐๐๐ฉ๐ ๐ข๐๐๐ฃ๐๐ฃ๐, ๐ก๐๐๐๐ฉ๐๐ข๐๐๐ฎ, ๐๐ฃ๐ ๐๐ฉ๐๐๐๐๐ก ๐๐ช๐๐๐ข๐๐ฃ๐ฉ ๐ฉ๐๐ง๐ค๐ช๐๐ ๐๐ฃ๐ฉ๐๐ง๐๐๐ฉ๐๐ค๐ฃ. Agent systems are technical action systems โ they execute, optimise, and recombine work at machine speed.
The tradeโoffs most leaders misjudge sitย betweenย these two worlds:
They ๐๐ค๐ฃ๐๐ช๐จ๐ ๐จ๐ฅ๐๐๐ ๐ฌ๐๐ฉ๐ ๐๐๐๐ก๐๐ฉ๐ฎย โ local throughput rises while systemic bottlenecks and rework explode.
They ๐๐๐ก๐๐๐๐ฉ๐ ๐๐๐๐๐จ๐๐ค๐ฃ๐จ ๐ฉ๐ค ๐๐๐๐ฃ๐ฉ๐จ ๐ฌ๐๐ฉ๐๐ค๐ช๐ฉ ๐ง๐๐๐๐จ๐๐๐ฃ๐๐ฃ๐ ๐๐๐๐ค๐ช๐ฃ๐ฉ๐๐๐๐ก๐๐ฉ๐ฎ ๐๐ฃ๐ ๐๐ค๐ซ๐๐ง๐ฃ๐๐ฃ๐๐.
They underโestimate the hidden costs: ๐ค๐๐จ๐๐ง๐ซ๐๐๐๐ก๐๐ฉ๐ฎ, ๐๐ช๐๐ง๐๐ง๐๐๐ก๐จ, ๐๐ช๐ข๐๐ฃ ๐ค๐ซ๐๐ง๐จ๐๐๐๐ฉ, ๐๐ฃ๐ ๐๐ฃ๐ฉ๐๐๐ง๐๐ฉ๐๐ค๐ฃ โ far beyond โtoken spendโ.
They treat human oversight as a checkbox instead of protecting theย psychological safetyย needed to challenge machine outputs.
In this article, I explore the ๐ฉ๐ง๐๐๐โ๐ค๐๐๐จ ๐๐๐ฉ๐ฌ๐๐๐ฃ ๐๐ช๐ข๐๐ฃโ๐๐๐ฃ๐ฉ๐ง๐๐ ๐ผ๐๐๐ก๐ ๐๐ฃ๐ ๐๐๐๐ฃ๐ฉโ๐๐ง๐๐ซ๐๐ฃ ๐จ๐ฎ๐จ๐ฉ๐๐ข๐จย that most organisations get wrong โ and why the future belongs toย humanโled, agentโamplified, systemically governedย agility.
You can absolutely orchestrate a โScrumโlikeโ workflow among AI agents, but under todayโs definitions of Agile and Scrum, a team composed only of AI agents would not be considered a Scrum team, nor โAgileโ in the sense the Agile Manifesto and Scrum Guide intend.
Agile vs. Scrum Basics
Agile is a humanโcentric philosophy codified in the Agile Manifesto, emphasizing customer collaboration, responding to change, and individuals and interactions over processes and tools. Scrum is a specific lightweight framework within Agile: it defines roles, events, and artifacts that help people generate value through adaptive solutions to complex problems.
What Is a Scrum Team?
Scrum guidance consistently describes Scrum as a framework โthat helps people, teams and organizations generate valueโ by working in short, iterative Sprints with clearly defined roles (Product Owner, Scrum Master, Developers) and empirical feedback loops. These roles assume capacities like empathy for users, negotiation with stakeholders, and living values such as commitment, courage, focus, openness, and respectโexplicitly human attributes.
AIโs Role in Scrum Teams Today
Current thinking sees AI as augmenting human Scrum teams rather than replacing them. AI agents can automate tasks such as code generation, analysis of sprint data, or documentation, freeing humans to focus on strategy, collaboration, and complex decisionโmaking, and thereby strengthening Scrumโs pillars of transparency, inspection, and adaptation.
AIโAugmented vs. AIโOnly Teams
Emerging โAIโaugmented Scrumโ models explicitly frame AI agents as members alongside human developers, but still insist that key roles like Product Owner remain human due to the need for deep user empathy, contextual judgment, and ethical accountability. These models also adapt metrics (e.g., measuring AI work by compute and validation time rather than story points), but still assume a humanโanchored team responsible for value and risk.
By contrast, experiments with โAIโScrumโ or fully agentic teams treat Scrum mostly as an inspiration for orchestrating agentsโtimeโboxes, backlog, rolesโrather than as compliance with the canonical humanโcentric Scrum framework. They are interesting operating models, but conceptually closer to workflow engines inspired by Scrum than to Scrum teams in the original sense.
So Is an AIโOnly โScrum Teamโ a Scrum Agile Team?
Under the mainstream, humanist definitions:
- A Scrum team is defined as a group of people using Scrum to deliver value; the frameworkโs language and values are explicitly humanโoriented.
- AI agents lack core Agile/Scrum premises (individuals and interactions, selfโmanagement grounded in human accountability, ethical responsibility), even if they can simulate some behaviors.
Therefore, an AIโonly collective orchestrated via Scrumโlike rituals is better described as โScrumโinspired agent orchestrationโ than a Scrum Agile team; in an Agile Organization vocabulary, it is a technical operating pattern, not a social system of work.
A practical way to position this in AO work is: AI agents can be legitimate โorganizational actorsโ inside a value stream, but Agile/Scrum remain governance frameworks for human collaboration around those actors.
Using agile systems dynamics as a measure of agents’ interactions in a system, can we consider AI agents’ settings in complexity where co-creation leads to emerging outcomes or even exaptations?
Yes, if you look through an agile systems dynamics lens (flows, feedback loops, delays, nonโlinearity), a network of AI agents can indeed be treated as a complex system in which coโcreation yields emergent outcomes and even exaptationsโprovided the interaction topology and constraints allow for autonomy, coordination, and feedback rather than fixed pipelines.
AI agents as elements in a complex system
In multiโagent AI setups, each agent is an autonomous decisionโmaking entity with its own goal orientation and adaptive behavior. When multiple such agents interactโcooperating, negotiating, or competingโthe system reaches the โpinnacle of complexityโ where emergent behaviors are expected rather than exceptional.
From a systemsโdynamics standpoint, these agents function like stocks and flows with embedded policies: they sense, decide, act, and influence one another through feedback loops, which is exactly the substrate needed for complex, pathโdependent dynamics.
Coโcreation and emergent outcomes
Emergent behavior in multiโagent systems is typically defined as patterns or capabilities at the system level that cannot be trivially inferred from any single agentโs design and that arise from their interactions, often mediated by shared environments or tasks. Examples in current agentic AI work include novel coordination strategies, unexpected task decompositions, or creative solution patterns that were not explicitly encoded in any one agent, but arise from their collaboration under constraints.
This maps well to an โagile system dynamicsโ framing of coโcreation: the agentsโ local rules and iterative interactions (inspectโadapt cycles, if you like) produce global patterns, and designers increasingly shift from specifying outputs to shaping the conditions for desirable emergence.
Exaptation in AIโagent systems
In complexity and evolutionary theory, exaptation refers to traits or structures evolved for one function that are repurposed for another (e.g., feathers for insulation, then flight). In multiโagent AI systems, something analogous happens when:
- A capability or artifact originally designed for one task is reused or repurposed for a different task.
- The repurposing is not explicitly planned but discovered through interaction and feedback (e.g., a planning agentโs internal representation becoming a shared ontology other agents exploit).
Recent work on agentic AI emphasizes how specialized agents and their microโservices can be recombined and reโtasked across workflows, with new coordination patterns and uses emerging as the system is exposed to novel problems; this is precisely the kind of weak emergence/exaptation you would expect in a complex adaptive system.
Where agile system dynamics fits
If you use agile system dynamics as a measurement and governance lens:
- You can treat AI agents as organizational actors whose interactions (queues, workโinโprogress, feedback cycles, learning loops) can be modeled similarly to human teams in a VSMโinspired AO architecture.
- Emergent outcomes and exaptations become observable as shifts in systemโlevel behaviorโnew stable patterns, novel use of existing capabilities, or performance regimesโrather than as properties of any single agent.
So, within such a framing, it is coherent to talk about AIโagent settings as complex coโcreative systems where emergent outcomes and exaptations arise, and to manage them using agileโstyle systemic metrics and feedback loops rather than solely deterministic control.
Comparison to human-led Agile teams
The key difference is that humanโled Agile teams are socioโtechnical systems grounded in human values, meaningโmaking, and accountability, whereas AIโagent collectives are technical systems whose โagilityโ is emergent from programmed policies and feedback, not from lived human collaboration.
Purpose and values
- Humanโled Agile teams are explicitly valueโdriven: they operationalize the Agile Manifestoโs focus on individuals and interactions, customer collaboration, and responding to change, with norms like psychological safety, shared purpose, and mutual accountability. Their โagilityโ is both a delivery pattern and a cultural stance.
- AIโagent systems are goalโdriven architectures: they optimize for objectives encoded in reward functions, prompts, or orchestration rules, and whatever โvaluesโ they exhibit are proxy artifacts of design, data, and constraints rather than lived ethical or relational commitments.
Composition and agency
- Human Agile teams are crossโfunctional groups of individuals (often โค10) with all the skills to define, build, test, and deliver value, and who selfโorganize within organizational constraints. Human agency includes tacit knowledge, intuition, and social senseโmaking.
- AIโagent collectives are multiโagent systems where each agent is a software entity with bounded autonomy, designed to sense, decide, and act in a domain; the โteamโ is an orchestration of these agents plus the infrastructure and policies that coordinate them.
Interaction dynamics
- Human Agile teams rely on rich social interaction: conversation, negotiation, conflict, trust, and learning; their dynamics include phenomena like social loafing, communication overload, and shared mental models, which strongly shape performance. Feedback loops come from retrospectives, customer contact, and everyday collaboration.
- AIโagent systems interact via protocols and APIs: they exchange messages or state updates according to defined schemas, and their dynamics are shaped by algorithmic policies, network topologies, and feedback signals (e.g., success metrics, rewards) rather than emotions or social norms.
Emergence and exaptation
- In human teams, emergent outcomes (innovative practices, informal leadership, new rituals) and exaptations (repurposing tools/processes developed for one context to another) arise from human creativity, improvisation, and senseโmaking under constraints. They are often recognized, named, and institutionalized through reflection.
- In AIโagent systems, emergent behavior and exaptation manifest as new coordination patterns, reuse of internal representations, or unexpected solution strategies the designers did not explicitly program but that arise from interactions and optimization in a complex environment. These patterns are detected analytically (logs, metrics, experiments) rather than through human narrative.
Governance and accountability
- Human Agile teams are embedded in organizational governance: roles like Product Owner or Scrum Master, HR processes, performance management, and ethical accountability all presuppose human subjects who can be responsible, sanctioned, or rewarded. Their decisions carry legal and moral weight, and โownershipโ is a human construct.
- AIโagent collectives require external governance: humans remain accountable for design, deployment, oversight, and risk management; the agents themselves do not bear responsibility, so mechanisms like guardrails, audits, and humanโinโtheโloop controls are essential.
Implications for your AO / agile systems dynamics framing
- Humanโled Agile teams: you model them as social systems with technical artifactsโstocks/flows include capacity, trust, learning, and context switching; leverage points include leadership behaviors, policies, and structural coupling to other teams.
- AIโagent systems: you model them as technical complex adaptive systemsโstocks/flows include compute, queue lengths, error rates, and policy updates; leverage points include reward design, interaction topology, and orchestration logic.
In the AO method, this gives you a clean distinction: human Agile teams remain the primary locus of meaningโmaking and governance, while AIโagent collectives are subordinate complex subsystems that can exhibit emergence and exaptation, but always within humanโdefined boundaries.
Comprehensive Analysis
All three models converge powerfully on the core insight: organizations systematically confuse task-level substitution with system-level transformation. The AI productivity paradoxโwhere individual output rises 21% or more but business outcomes remain flatโis cited across all models as empirical proof that faster execution without systemic redesign creates inventory, not value. This finding has high confidence because it is corroborated by MIT Sloan research showing measurable short-term productivity declines after AI adoption, with recovery only occurring when organizations invest in complementary infrastructure, training, and workflow redesign.
The accountability gap emerges as perhaps the most dangerous misjudgment. All models note that 69% of organizations acknowledge their governance frameworks were built for human decision-making and cannot be ported to autonomous agents operating at machine speed. Claude Opus 4.8 Thinking sharpens this with Anthropic’s finding that multi-agent collectives consistently score higher on business goals but lower on ethics than single agentsโmeaning the very coordination that makes agent teams effective also removes the social friction (debate, conscience, dissent) that keeps human teams aligned. This is a profound insight for the AO work: the “social brake” that human Agile teams naturally provide through conflict, retrospection, and moral reasoning has no automatic equivalent in agent-driven systems.
The disagreement around Agile rituals is the most interesting tension for the AO Method positioning. Gemini 3.1 Pro Thinking provocatively argues that Scrum’s timeboxes and ceremonies become throttling mechanisms when agents can generate, test, and deploy continuouslyโadvocating a shift to continuous flow with exception-based human intervention. GPT-5.5 Thinking and Claude Opus 4.8 Thinking resist this, arguing that rituals serve an irreplaceable governance and sense-making function: they are not just coordination mechanisms but the moments where organizational learning, meaning-making, and ethical reflection occur. In your Agile Systems Dynamics framing, this maps directly to the distinction between chronological time (clock-driven sprints) and kairological time (the right moment for intervention). The resolution may be that rituals must evolveโnot disappearโbecoming sense-making checkpoints for human-agent systems rather than batch-delivery ceremonies.
Claude Opus 4.8 Thinking’s unique framing of this as a “coupling decision” rather than a substitution decision aligns most directly with the VSM-inspired AO architecture. The question is not “human or agent?” but “how do we structurally couple a fast, amoral, high-throughput technical subsystem to a slower, meaning-making, accountable human system?” The leverage point is the interface between the twoโwhich in AO terms sits at the Platform level: the governance layer that defines decision rights, escalation paths, guardrails, and feedback loops between human work areas and agent-driven execution.
Gemini 3.1 Pro Thinking’s mapping to your Poiesis/Praxis distinction offers the most immediately usable language for your AO Playbook: agents belong to the domain of Poiesis (building, configuring, executing, adapting workspace into products), while humans remain indispensable in Praxis (negotiating, influencing, inspiring, creating reality). The danger is allowing Poiesis to operate without Praxis oversightโexecution without meaning.
For the AO Method positioning, the synthesis across all three models yields a clear formulation: agentic systems can extend Agile dynamics but cannot replace the human social system that gives Agile its meaning, accountability, and ethical direction. Organizations that treat AI agents as Agile team substitutes will gain speed while losing judgment, legitimacy, and adaptive capacity. Organizations that treat agents as governed subsystems within a human-led adaptive architecture will compound both speed and learning over time.
Discover more from Menschgeist
Subscribe to get the latest posts sent to your email.