Sign inGet started
Skills / Learning-education

Connectivism

The pipe is more important than the content within the pipe.

Connectivism is a learning theory for the digital age that reframes knowledge as something that exists in networks, not just in heads. Developed by George Siemens, it argues that in fast-changing environments the ability to form and traverse connections across people, ideas, tools, and systems is more critical than memorizing facts. Built for instructional designers, L&D professionals, and educators who want learning experiences that match how knowledge actually works today.

By George Siemens · Free
Specimen 01 · Live diagnosisConnectivism
Input

“Honestly, I Google it or ask a couple of colleagues. I have a bunch of newsletters I subscribed to but I don't really read them anymore.”

Diagnosis
Connectivism starts from one uncomfortable premise: in a world where knowledge changes faster than any course can track, what you know matters less than who and what you're connected to.
Full transcript ↓
Calibrated referenceagent-skills.ai
The gap

Your network is your knowledge — design connections, not just curricula

Connectivism holds that learning in the digital era occurs through forming and traversing connections across distributed networks — between people, ideas, databases, and machines. Its eight core principles establish that knowledge rests in diversity of opinions, may reside in non-human systems, and that the capacity to know where to find knowledge is more critical than what one currently knows. The theory critiques behaviorism, cognitivism, and constructivism as pre-digital frameworks inadequate for networked environments. In practice it is applied through designing Personal Learning Networks (PLNs), evaluating courses against the eight principles, and creating cMOOC-style learning architectures where learner-generated connections — not instructor-transmitted content — drive understanding. Currency (keeping knowledge accurate and current) is a continuous obligation, not a one-time task.

The problem

Most learning programs are designed to transfer fixed content from expert to learner — a model that assumes knowledge is stable, locatable in one place, and transferable intact. In fast-changing digital environments this produces learners who can recall what they were taught but cannot navigate what they weren't. Siemens identified this gap: behaviorism, cognitivism, and constructivism were all formulated before ubiquitous computing and fail to account for how distributed networks have changed where knowledge lives and how it moves.

The solution

Apply Connectivism's eight principles to audit and redesign learning experiences — shifting from content consumption to deliberate connection-building, so learners develop the network literacy to find, evaluate, and apply knowledge in a world that won't stop changing.

You bring
  • A learning design, course, or training program you want to evaluate or redesign
  • A description of your current knowledge sources, communities, and go-to people
  • A specific domain or skill area where your learning feels stuck or siloed
  • Questions about how to structure distributed or networked learning at any scale
You get
  • A PLN Node Map — a structured inventory of your current network nodes with gap identification
  • An Eight-Principle Audit Report scoring your learning design against each connectivist criterion
  • A Network Diversity Index showing where your network is monocultural and where new connections would add the most value
  • Specific redesign recommendations for shifting a program from content consumption to connection-building
In action

Watch the methodology work.

Three specimens from a single real session: the same situation, unaided and calibrated, the full transcript, and the skill answering live in the channel where the work happens.

Fig.01The same situation, two ways
Specimens A · B
Specimen AVague
Unaided

“You're a corporate L&D manager who just launched a 40-module e-learning course. Every module has a video, a quiz, and a completion certificate. Metrics show 80% completion. But six months later, nothing has changed: people in different teams still reinvent solutions the other team already found, and employees say the training felt disconnected from their actual work. Knowledge is still siloed and the course is already out of date.”

×Vague — nothing concrete to act on.
Specimen BCalibrated
With Connectivism

“After a connectivist audit, you restructure the program: modules become launch pads, not endpoints, with each one connecting learners to external communities, curated practitioner feeds, and cross-team peers working on adjacent problems. Learners build and present a PLN as a core assessment — not a quiz score. Six months later, cross-team knowledge sharing has measurably increased because the program built real connections between people who now know who to call, and the learning continues past the course's official end date.”

Specific, grounded, and ends with one clear next step.
Fig.02A real session, unedited
In-app · assistant
ConnectivismClaude
Connectivism
Connectivism starts from one uncomfortable premise: in a world where knowledge changes faster than any course can track, what you know matters less than who and what you're connected to. I want to map your actual learning network — not the ideal one, but the real one. When something new comes up in your field and you need to get up to speed, what do you actually do first?
Honestly, I Google it or ask a couple of colleagues. I have a bunch of newsletters I subscribed to but I don't really read them anymore.
That's a very common network shape: a few strong nodes you lean on heavily, and a lot of dormant nodes that produce noise you've learned to ignore. In connectivist terms, Siemens calls this a brittle network — you've centralized your learning access in a small number of connections, so your understanding is only as current and diverse as those few sources. The newsletters aren't a failure — they're a symptom. They were the wrong kind of node for how you actually learn. Tell me about those colleagues: are they all at your organization, and do they span different disciplines or mostly overlap with your work?
They're all at my company. Same team, actually. We know each other well but we all came up through the same training.
That's what Siemens would call a monoculture network — high trust and low friction inside, but a shared blind spot outside. His first principle is that learning rests in diversity of opinions: a homogeneous network recirculates the same ideas rather than introducing new ones. This isn't a criticism of your colleagues — it's a structural issue. Your network currently has no cross-disciplinary connections, which means the adjacent fields that are quietly reshaping your domain aren't showing up in your awareness at all. What are one or two disciplines adjacent to your work that you feel underexposed to — things your team talks about but where nobody has deep expertise?
Probably data analytics and behavioral science. We reference both but we're guessing most of the time.
Those are exactly the right gaps to target — they're adjacent enough to be immediately useful, and distant enough to introduce genuinely new thinking. Here's the connectivist move: you don't need to become an expert in either. You need one reliable connection in each domain. Siemens' pipe principle says the pipe — the connection to a person in analytics or behavioral science — is more important than any specific thing they ever share. One practitioner whose work you follow regularly will pull you toward ideas you wouldn't find on your own. Should we sketch a minimal PLN expansion? Three to five specific new nodes targeting these gaps, with a clear strategy for making each connection real rather than passive.
Yes — that's exactly what I need. I've been meaning to do this for months but it always felt too abstract to act on.
Reply to Connectivism
What the skill is doing
01Personal Learning Network Audit
02Eight-Principle Course Assessment
03Network Gap Analysis
Fig.03The same skill, in the channel you already use
WhatsApp · live
9:41
CConnectivismtyping…
Messages are end-to-end encrypted. No one outside of this chat can read them.
Today
Honestly, I Google it or ask a couple of colleagues. I have a bunch of newsletters I subscribed to but I don't really read them anymore.9:14✓✓
I want to map your actual learning network — not the ideal one, but the real one.9:14
When something new comes up in your field and you need to get up to speed, what do you actually do first?9:15
Message

The same skill, where the work happens.

No new app to learn. The methodology runs over the WhatsApp Business API, so the answer lands as a reply in the thread you’re already in — same rigour, zero context-switch.

Reads the situation, names the pattern, returns one concrete next move.
Delivered in seconds, inside a conversation that already exists.
Specimen · WhatsApp Business API · live
Capabilities

What it does, specifically.

Each capability is a distinct move drawn straight from the source methodology — not a generic assistant guessing.

CapabilityC-01

Personal Learning Network Audit

Map the nodes and connections in your current Personal Learning Network — the people, communities, tools, publications, and information systems you rely on for learning. Identify which nodes are redundant, which are missing, which are monocultural, and where your network is brittle.

Based on Siemens' fifth principle — that nurturing and maintaining connections is essential for continual learning — and his argument that the capacity to know more depends on the quality and diversity of the network, not just what one currently knows.
CapabilityC-02

Eight-Principle Course Assessment

Evaluate a course, training program, or learning experience against all eight connectivist principles — from whether it supports diversity of opinion to whether it builds learner capacity to form connections that outlast the course itself.

Directly applies the eight-principle framework from Siemens' 2005 paper 'Connectivism: A Learning Theory for the Digital Age' as a structured evaluative lens for any learning design.
CapabilityC-03

Network Gap Analysis

Identify missing nodes in a knowledge network — disciplines underrepresented, communities absent, or information sources that are outdated or too homogeneous. Prioritize which gaps most limit current learning capacity.

Grounded in Siemens' sixth principle that 'the ability to see connections between fields, ideas, and concepts is a core skill,' and his first principle that learning rests in diversity of opinions across the network.
CapabilityC-04

Knowledge Currency Review

Assess whether key knowledge sources and network connections are still providing current, accurate information — and surface nodes that have become stale, are producing noise rather than signal, or are no longer maintained.

Reflects Siemens' seventh principle: 'currency (accurate, up-to-date knowledge) is the intent of all connectivist learning activities' — the network must be continuously maintained and pruned, not just initially assembled.
CapabilityC-05

cMOOC Design Evaluation

Apply connectivist design philosophy to a course or program, evaluating whether it enables distributed discussion, learner-generated content, and emergent knowledge — or merely replicates broadcast-style instruction online with a new delivery mechanism.

Based on design principles operationalized in CCK08 (2008), the first connectivist MOOC co-facilitated by Siemens and Stephen Downes, which used RSS aggregation, open web discussion, and distributed content creation as core learning mechanics.
Tested

Graded before it shipped.

Every skill is scored against independent scenarios for methodology fidelity before it goes live — not vibes, a rubric.

What it produces
OutputD-01

PLN Node Map

A structured inventory of your Personal Learning Network organized by node type — people, communities, tools, publications, systems — with connection strength ratings, currency scores, and identified gaps for each category.

OutputD-02

Eight-Principle Audit Report

A scored evaluation of a learning design against all eight connectivist principles, with specific gaps identified, evidence cited from the program's structure, and redesign recommendations for each underperforming principle.

OutputD-03

Network Diversity Index

A cross-discipline assessment of how diverse a knowledge network is across fields, perspectives, and source types — highlighting echo chambers, monocultures, and the highest-leverage entry points for expanding the network.

The source

Grounded in the original work.

Every answer traces back to a real source and the practitioner who wrote it — not a secondhand summary. Here is the source of record.

Source authorA-01

George Siemens

George Siemens is a Canadian researcher and learning theorist who proposed Connectivism in his landmark 2005 paper 'Connectivism: A Learning Theory for the Digital Age.' He co-facilitated CCK08 (2008), widely recognized as the world's first Massive Open Online Course. His open-access book Knowing Knowledge (2006) has been adopted in educational technology and instructional design programs globally, and his work at the University of Manitoba and Athabasca University helped establish learning analytics as a discipline.

Status · Inspired by George Siemens’s work — not yet claimed. Are you George Siemens?
Primary sourceS-01

Knowing Knowledge (2006) and 'Connectivism: A Learning Theory for the Digital Age' (2005)

by George Siemens

Creator of Connectivism theory; co-creator of the MOOC format (CCK08, 2008); researcher at University of Manitoba and Athabasca University; author of Knowing Knowledge (2006).

Read the original ↗
Citationconnectivism.ca
In the build queue

Be first to run it.

Connectivism is being built right now. Leave your email and we’ll tell you the moment it goes live.

Notify meEmail
At launchI want to audit my course against the eight connectivist principles — can we go through each one and assess where my learning design falls short?