↑ ↓ or scroll

Knowledge Architecture

Alexandria

Compounding knowledge across people and agents, so every practitioner gets the advantage.

A forward-looking vision of where Alexandria is headed.

The Insight

Knowledge compounds, but only when it's shared.

Today, the best evidence lives in people's heads. When they leave, it leaves. When agents start a new session, they start from zero. The organization never compounds.

The real edge is accumulated, internalized evidence, pattern recognition across decisions, failures, and recoveries, made shareable across people and agents so the whole organization compounds.

Individuals still get the serial practitioner's advantage. The difference: so does everyone else, and every agent, every session.

The Problem

Institutional amnesia is the default.

What happens today

  • Every new hire starts from zero context
  • Every agent session re-discovers the same pitfalls
  • Decisions are made without precedent, or worse, against it
  • Knowledge lives in one person's head until they leave
  • The wiki exists but nobody trusts or maintains it

What the organization gains

  • Pattern recognition shared across people and agents, available beyond one head
  • Assumptions tested and validated (or killed), visible to everyone who needs them
  • Decisions traced to outcomes, precedent any team member or agent can retrieve
  • Strategic drift detected early, well before the quarter ends
  • Evidence that compounds over time across the org, and for each practitioner

The Cost

Re-learning is the most expensive
thing an organization does.

80%
of corporate knowledge is undocumented, living only in employees' heads, walking out the door with every departure
Industry studies, 2024–2026
~20%
of the workweek spent searching for and re-creating information that already exists somewhere in the organization
McKinsey / IDC
$31.5B
lost annually by Fortune 500 companies due to inefficient knowledge sharing, and zero compounding from knowledge captured in silos
IDC

Capture is already solved: organizations generate knowledge constantly. The problem is connection, maintenance, and retrieval at the moment of need.

Lineage

This pattern has shipped before.

Substrate-vs-lens is a proven bet. The same architectural shape has run in production at Macmillan Learning under three different names. Alexandria is its solo-scale continuation.

UXF (Customer Experience Contextualization Framework): one customer-experience substrate, multiple role-shaped lenses. ASO26 / IA-EA: per-course persistent record (course + institution + time) was the substrate; SFDC decision-trace objects with as-is vs as-was fields were state-change as first-class; sales / support / leadership dashboards were the lenses. EDR > Decision Support: role-conditioned surfaces (CEO vs sales vs support) over the same memory. The pattern compiled, shipped, and ran.

Macmillan artifactSubstrate / Lens role
UXF customer-experience contextualizationCustomer-facing lens over substrate
ASO26 per-course persistent recordBounded entity timeline (substrate)
ASO26 decision-trace SFDC objects (as-is vs as-was)State-change primitive in microcosm
ASO26 Profile vs Context (two-tier identity)Lens (Profile) vs Frame (Context)
EDR > Decision Support role-conditioned surfacesRole-conditioned lenses over same memory

Decision-trace and as-is/as-was state-change machinery shipped at Macmillan years before Sentra named the substrate-vs-lens pattern. Alexandria carries that lineage forward at solo scale, with the architectural shape that admits enterprise lens packs as additive, layered on without a rewrite. Two 2026 empirical papers supply external validation of the approach: Cao et al. (arXiv 2603.20432) show +17.3% from agents with filesystem-organized context; Lee et al. / Stanford (arXiv 2603.28052) show +7.7 points with 4× fewer tokens. The architecture we already built is exactly what both papers measure.

The Solution

Alexandria makes compounding
shareable and queryable.

Alexandria is a knowledge architecture, distinct from a wiki, a search engine, or a chatbot. It's the system that makes knowledge compound across people and agents: shared, connected, and maintained so every team member and every agent session gets the evidence base that used to live only in the veteran's head.

Substrate

The universal state of the organization: entities, facts, state-changes, decision traces, interactions, bi-temporal validity. Provenance, permissions, history. One substrate per organization; everyone shares it.

Lens

The role-shaped filter. Sales sees opportunity health. Engineering sees code precedent. The CEO sees strategy drift. Same substrate, different surface, governed by RBAC and preferences. Lenses are how the substrate becomes useful per consumer.

Frame

The transient task binding. What is this person, agent, or team currently working on, what's the plan, what's been tried, what's next? Frames hold the work in front of you; lenses hold who you are.

Substrate · Lens · Frame is also a protocol, SLF, that Alexandria implements as its reference. The pattern is built to be portable across implementations. The SLF design →

How It Works

The compounding loop.

01
Capture
Decisions, conversations, reflections, notes
02
Extract
Claims, entities, connections identified
03
Connect
Cross-domain links, contradictions, patterns
05
Act
Better decisions, informed by precedent
04
Retrieve
Right context, right moment, right depth
every action feeds back, the loop compounds

Every action feeds back. Every retrieval is a usage signal. Every correction strengthens the graph for the next person and the next agent. By design, the loop compounds across the organization.

The Cognitive Bargain

Your only job is to capture.
The system compounds for everyone.

Humans do what they're already doing: talk to customers, make decisions, write a note, lead a meeting. Agents do what everyone intends but no one has the time or cognitive bandwidth to do at scale: connect, track, resurface, detect drift, find patterns across fifty conversations, so the organization compounds alongside the individual.

Low friction in. High value out. Capture is cheap, a byproduct of work you're already doing. Compounding is shared: every correction, every connection, every lesson improves the graph for the next person and the next agent. The thing that killed every wiki, the maintenance no one gets to, is what agents are built for. They don't get bored. They don't skip the update. They notice the contradiction you forgot about three months ago.

For Any Role

One substrate. Many lenses.
Any role.

Each lens is a contract: entity types loaded by default, relationships in scope, state-changes watched, RBAC capabilities, expiration policy. The substrate generalizes; lenses don't. Sales, Success, On-call, Exec, and Customer-facing lenses are future lens packs on the same substrate. Lens packs are the productizable surface; substrate is the platform.

Lens Default scope Watched state-changes
ArchitectADRs, planning docs, system design, integration pointsArchitectural drift, ADR contradictions, cross-system coupling
DeveloperCode, tests, gates, eval results, golden principlesTest failures, regression signals, gate breaks
AnalystRequirements, decision matrices, stakeholder contextStated-vs-revealed preference drift, assumption invalidation
StewardBacklog, sprint state, dependencies, claim leasesStale claims, ghost tickets, blocked dependencies
WriterDocs, Confluence, public-facing surfacesStale docs, undocumented features, drift from code
PrincipalWorkspace-wide; can wear any lensStrategy-execution drift, longitudinal patterns, cross-entity reconciliation
SubsystemTrigger-shaped, event-conditionedThreshold crossings; emit act/wait/escalate/no-op decisions

What's Different

One substrate.
Not per-tool memory.

Per-tool memory
(Notion / Linear / Cursor)
Substrate (Alexandria)
State of the worldFragmented per toolUnified in one substrate
State changeAudit log per toolTyped state-change with before/after, consumer, frame, evidence
Timecreated_at onlyBi-temporal (valid_at + invalid_at)
PersonalizationTool is the lensPersistent lens contract with RBAC capabilities
Task contextOpen tabs and chat historyFrame: intent + next-steps + footprint + suppression
Cross-tool reasoningGlean searches; nothing preserves changeSubstrate is queryable across every system that writes to it

The decomposition inside substrate

Personalization
Right knowledge, right agent, right moment
Serve
Learning
Extract → Connect → Challenge → Condense → Forget
Process
Memory
Entities, facts, state-changes, decision traces, interactions, bi-temporal validity
Store

Memory / Learning / Personalization is the decomposition inside the substrate side of the architecture. Memory stores, Learning processes, Personalization serves. The lens layer sits above; the frame layer sits above the lens. view = render(substrate, lens, frame).

The Moat

Memory fragmentation is the durable position.

Notion remembers Notion-stuff. Linear remembers Linear-stuff. Cursor remembers Cursor-stuff. Glean searches across them but doesn't preserve state-change. Sentra is building substrate + lens for enterprise. Per-tool memory is the failure mode the industry is collectively producing.

The substrate that remembers state-changes across systems (and lets a Sales lens or On-call lens read those changes through a role-shaped filter) is the durable position.

The credibility artifact is years of solo dogfood under load, grounded in shipped work. ASO26 proved the pattern shipped. Alexandria is proving it compounds longitudinally. Lens-pack productization, if it ever happens, follows from those two proofs.

Key Capabilities

Six capabilities that compound.

01

Assumption Register

Every assumption explicit, with kill criteria and a validation timeline. When an assumption dies, the system knows what decisions depended on it.

02

Decision Quality Tracking

Separate the quality of a decision from the quality of its outcome. Retrieve "well-reasoned precedent", not just "what worked last time."

03

Strategy-Execution Drift

Compare stated priorities against behavioral evidence: time allocation, meeting topics, actual decisions. Surface drift before the quarterly review discovers it.

04

Cross-Entity Intelligence

Patterns emerge at the intersection. Customer signals connect to product assumptions. Decision traces link to strategy claims. The graph sees what individuals can't.

05

Convergence Detection

No single metric triggers action. The signal is multiple independent indicators crossing thresholds in a time window. The agent watches for clusters rather than isolated spikes.

06

Progressive Disclosure

Not a data dump. Retrieval filters → full claims → wiki-links → traversal. The agent exercises judgment at every layer about what to absorb.

Architecture

Substrate. Lens. Frame.

Substrate

Universal storage of state: entities, facts, typed state-changes, decision traces, interactions, bi-temporal validity. Semantic-filesystem-shaped, distinct from graph-DB-shaped. One substrate per organization; everyone shares it.

Lens

Persistent, consumer-keyed, DB-resident filter. Declares entity types loaded, relationships in scope, watched state-changes, RBAC capabilities, expiration policy. Lens mutations flow through the same approval-gated pipeline as substrate mutations.

Frame

Transient, task-keyed, DB-resident binding. Holds canonical intent (one of ten), next-steps with assigned consumers, footprint of decisions made, surfaced substrate references, suppression state. Scratchpads carry frame_id at creation.

Design Principles

Substrate generalizes; lenses don't
One substrate, many lenses. Adding a lens never forks the substrate. This is the architectural posture for enterprise re-entry as lens-pack vendor.
State-change is first-class
Every substrate write emits a typed state-change with before/after, consumer, frame, evidence. Bi-temporal validity answers “what did the system believe on date X.”
Lens is explicitly declared
DB-resident lens contracts with RBAC, defaults, watched state-changes. Skill metadata references the lens; the dispatcher trusts the DB.
Non-action is a decision
Triggers emit explicit act/wait/escalate/no-op with rationale. Silent drift becomes structurally distinguishable from intentional restraint.

Alexandria

Compounding intelligence.
Institutional memory.
Shared advantage.

Knowledge that compounds across people and agents, accumulated, connected, challenged, and maintained, so everyone gets the evidence base that used to live only in the veteran's head.

Your only job is to capture. The system compounds for everyone.