Lab / method
Source-Backed Team Memory
Developing a bounded lab method for source-backed team memory: reviewable, human-correctable, source-linked operating memory for knowledge-heavy teams.
Early research / method / consulting practice. Not a finished production SaaS, chatbot, surveillance system, AI replacement for judgment, or private archive browser.
Method
Source-Backed Team Memory is a bounded lab method for preserving decision lineage, onboarding context, meeting synthesis, and human-correctable AI workflows without turning private archives into an unsafe browsing surface.
I do not hear this as a need for more notes. I hear it as a need for operating memory.
Operating memory helps a team understand what has been decided, why it was decided, what source material supports that understanding, what remains open, who holds which context, and what new collaborators need in order to join intelligently.
What It Is
It is an early method and consulting practice for teams that need source-backed operating memory: what happened, which decision was made, which source supports a claim, what remains uncertain, and what should stay protected.
What It Is Not
It is not a finished production SaaS, a chatbot, a surveillance system, a replacement for judgment, a legal, medical, or financial advice system, or a private archive browser. The point is not to automate trust. The point is to make context easier to review, correct, and transfer.
Working Pattern
The pattern is Known / Open / Protected. Known material is public-safe or source-backed. Open material needs review, correction, or more context. Protected material is intentionally withheld because privacy, consent, law, safety, or client trust requires it.
Approved source -> structured record -> source-linked draft -> ideas / decisions / open questions -> trust / privacy check -> accepted team memory.
AI drafts. Humans review. The shared record remains inspectable and correctable.
Example Deliverables
- knowledge-friction map
- source / workflow inventory
- decision-memory template
- meeting-memory template
- onboarding or "how we know what we know" starter page
- privacy, access, and retention notes
- 30-day continue / revise / stop recommendation
Role Fit
The work connects technical project management, product operations, documentation architecture, AI-readiness, human review, and source-backed memory. It is visible in V1 as a lab page, not as the lead homepage case study.
Worked example
One source enters; three review states remain visible
This synthetic example shows the method without exposing a private archive. The system does not force disagreement into certainty. It preserves what is supported, what needs review, and what should stay outside the public record.
Known
A public project brief records the launch date, intended audience, and approved owner of a decision.
Open
Two meeting summaries describe adoption differently, so the shared record flags the discrepancy for review.
Protected
Private transcripts, contact details, and unapproved collaborator context remain outside the public memory.
Concrete correction trace
The public record changed the portfolio
Earlier portfolio copy dated CallNYC to 2014-2015. A recovered Council hackathon announcement, the fuller CouncilStat data-release chronology, and contemporaneous Politico coverage placed the work in 2016.[2][3][4] The correction was applied to the work index, case study, and resume while the prior wording and reason remained visible in the Knowledge Wiki.
- Before
- 2014-2015
- After
- 2016
- Handoff
- One correction propagated to every public surface that carried the date.
Evaluation practice
Human review is part of the system
Completed AI Evals for Engineers & PMs with Shreya Shankar and Hamel Husain through Maven.[1] The coursework supports this lab's emphasis on error analysis, annotation, traces, retrieval quality, and reviewable failure modes.
Sources and notes
These notes preserve what each source supports and where its limits remain. See something that needs correction? Contact Jamie.
View 4 source notes
Boundary: This source does not establish an evaluator license, instructor affiliation, employment by Maven, endorsement of Jamie's lab method.
The archived Civic Hall page preserves the embedded social post. It is not a recovered Civic Hall calendar listing or event-detail page.
Boundary: This source does not establish a recovered Civic Hall calendar listing, a dedicated event-detail page, the complete formal event title, the agenda, the participant roster.
The reporting connects Jamie to the January event, the fuller data release, and his independent development and iteration of CallNYC.
Boundary: This source does not establish CallNYC as an official Council product, CallNYC as a formal hackathon submission, CallNYC as a documented winner.
[4] Public CallNYC source repository.
The repository documents the surviving implementation of the independent, archived prototype.
Boundary: This source does not establish official Council ownership, formal hackathon submission status, current resident-service guidance.
