THE LOCAL TRANSMISSION · ONLINE SEASON 1 · UES-205
Collective Intelligence Studio: Humans, Agents & Editorial Judgment
AI + COLLECTIVE
Build human-agent workflows in which tools expand the field of possibility while people remain accountable for sources, decisions, omissions, and the finished public claim.
Course boundaryNo sensitive personal data, deceptive synthetic media, unlicensed imitation, or unsupported factual publication.
- Module time
- About 2.5–3 hours per module
- Pace
- Start anytime · no deadlines · pause and return.
- Completion
- Any four modules plus the final course outcome.
- Materials
- Browser and text editor · Notebook with separate columns for claim, source, tool or method, candidate output, human edit, uncertainty, and decision · Optional AI system the learner already chooses to use; paper-based role cards fully replace it · No coding experience required
WHY THIS CLASS EXISTS
Make observation useful to somebody else.
Build human-agent workflows in which tools expand the field of possibility while people remain accountable for sources, decisions, omissions, and the finished public claim.
Builds from Season 0: UES-106, UES-107, UES-108.
HOW THE ROOM RUNS
Prompt. Fieldwork. Studio. Receipt.
- 01Module prompt
One central question opens each module. The source shelf is optional; the page itself contains the full path.
- 02Field task
One 60–90 minute act of looking, making, recording, or hosting.
- 03Self-guided studio
A 75-minute making, editing, or reflection session you can complete alone.
- 04Module receipt
A 20-minute useful trace kept privately or shared only when you choose.
YOUR PRIVATE COURSE DESK
Start here. No account required.
Check off modules as you work. Progress stays in this browser; the university never receives your name, work, location, email, or wallet.
0 of 5 completion steps · finish any four modules plus the final outcome.
Local progress is ready. You can also use the class without saving anything.
THE SIX-MODULE ROOM
A complete first syllabus.
Everything required is printed here. References named inside modules are optional; use this on-page toolkit whenever a module asks for a check, scenario, ledger, or handoff.
- MODULE01
Which work can a tool propose, and which decisions must a named person own?
Define the Roles
On-page prompts + optional references
- On-page role rule: researcher gathers, generator proposes, critic challenges, verifier checks evidence, editor decides, and approver signs off; one learner may perform every pass
- On-page ledger fields: time, role, input, tool or manual method, output, source, human change, uncertainty, decision, and reason
- No-model role cards: apply three constraints by hand, create three candidates, then switch roles before judging them
Self-guided studio
Decompose a small project into proposing, retrieving, checking, deciding, making, editing, and approving.
Field task
Observe one existing workflow and mark where automation helps, obscures, or falsely appears authoritative.
Module receipt · private by default
A first human-agent responsibility map naming the learner’s final editorial decision point; optional collaborators may be added.
- MODULE02
Can every important public claim travel back to evidence a person can inspect?
Build a Trustworthy Source Trail
On-page prompts + optional references
- On-page source test: prefer firsthand records, identify the creator and date, open the cited evidence, compare an independent source, and label conflicts
- Citation, quotation, paraphrase, and uncertainty examples
- Model hallucination and retrieval-failure cases
Self-guided studio
Trace claims through search, retrieval, model summaries, and human verification without treating fluency as evidence.
Field task
Build a five-source shelf around the research question and independently verify one tool-, search-, or manually generated candidate claim from primary evidence. No AI use is required.
Module receipt · private by default
A source notebook excerpt showing one confirmed, one corrected, and one unresolved claim.
- MODULE03
How can prompting widen a search without quietly deciding the answer?
Prompts Are Sketches
On-page prompts + optional references
- On-page variation exercise: make one factual, one counterfactual, and one constraint-heavy approach; without AI, write the three candidate outlines yourself before editing
- Creative constraint and editorial brief examples
- Image, text, and code provenance prompts
Self-guided studio
Run divergent prompts, compare outputs, annotate assumptions, and write an editorial brief before selecting material.
Field task
Generate or manually draft three meaningfully different approaches and document why the learner’s editorial pass rejects at least one.
Module receipt · private by default
A prompt triptych with output differences, editorial notes, and material model disclosure.
- MODULE04
Where does information get lost when a project moves between people and agents?
Design the Handoffs
On-page prompts + optional references
- On-page gate for every pass: define the input, expected output, evidence check, access check, stop condition, saved version, and who or which role decides
- Structured brief, schema, and handoff patterns
- Version, source, and approval ledger examples
Self-guided studio
Turn an improvised one-person process into explicit inputs, outputs, checks, stop conditions, and self-attested decision gates; optional team handoffs may be mapped too.
Field task
Run one simulated self-handoff between two named passes and record ambiguity, duplication, and failure points. An optional collaborator handoff uses the same standard and counts equally.
Module receipt · private by default
The revised human-agent process map and one concrete rule added after the test.
- MODULE05
What would make this work misleading, harmful, derivative, private, or wrong?
Red-Team the Work
On-page prompts + optional references
- Bias, privacy, fabrication, and sensitive-data review prompts
- Copyright, style imitation, and synthetic-media disclosure cases
- Adversarial fact-check and counterexample methods
Self-guided studio
Run the safety-and-rights pass in the solo toolkit, then try to disprove every major claim, find one counterexample, identify a missing affected perspective, and mark what would make the work unsafe to release. An exchanged dossier is optional.
Field task
Resolve or explicitly label every high-risk issue in the self-generated red-team report. Optional peer findings use the same standard.
Module receipt · private by default
A red-team disposition list: fixed, disclosed, removed, or unresolved.
- MODULE06
Can another person understand how the work was made and where judgment entered?
Publish the Ledger
On-page prompts + optional references
- Public process-ledger examples
- Model and dataset disclosure fields
- Use the source-trail and handoff-package fields printed in the solo toolkit
Self-guided studio
Complete editorial review, source audit, authorship statement, limitation note, and correction route.
Field task
Package the final dossier with its process ledger and record the learner’s final self-attestation. If optional collaborators are named, their approval is needed only for their contributions.
Module receipt · private by default
A private-by-default work package with inspectable sources, process ledger, limitations, credits, and correction note; publication is optional.
WHAT COMPLETION MEANS
No grades. Real work.
- 01
Prompt and source notebook · suggested after module 2
Keep claims, sources, prompts, model outputs, human edits, uncertainties, and discarded paths in distinct fields. - 02
Human-agent process map · suggested after module 4
Diagram which human pass or tool proposes, checks, decides, edits, attributes, and signs off at each stage of a one-person workflow; collaboration is optional. - 03
Dossier and process ledger · suggested after module 6
Package the finished work privately with sources, limitations, authorship statement, material model use, and the learner’s final sign-off. Publication is optional.
Complete any four of the six module receipts and finish the course outcome or a private equivalent. There are no grades, deadlines, peer requirements, or public-posting requirements.
ACCESS IS PART OF THE SYLLABUS
More than one way through the room.
- Every instruction is readable on the public course page; audio or video references require a transcript or equivalent text path.
- Every required prompt, scenario, rubric, and checklist is written on this course page; named sources are optional references, not missing course materials.
- Low-bandwidth, print-friendly syllabus with no paid platform or subscription required.
- No live attendance, camera, account, wallet, or public posting is required.
- Progress stays in this browser unless the learner chooses to download a private completion receipt.
- No AI system is required. A complete no-model route uses search, index cards, manual variations, and the same source and editorial checks.
- Independent route
- Active now. The complete sequence, studio prompts, access paths, and private checklist are on this page.
- Optional faculty profile
- An editor or creative technologist with strong source verification, authorship, privacy, model-literacy, and collaborative production practices.
- Supported cohort
- Optional and funding-dependent. Human review or scheduled sessions never gate access or completion.
- Planning cost
- $3,300 for maintenance, access, materials, and an optional supported cohort—not tuition or admission.
Learners retain copyright. Public licensing and Tezos minting are optional and separate. A wallet, public identity, public artifact, or blockchain transaction is never required for this class.
THE ROOM IS OPEN
Bring one place. Leave one useful trace.
Start now, move at your own pace, and keep the work private if that is the right path. Human help and supported cohorts can be added without changing anyone’s right to learn independently.
Support does not buy admission, curriculum control, governance rights, or faculty appointments.