Customer briefing  ·  Lexenne  ·  August 2026

Your data has warehouses. Your judgment has nothing.

Your organization runs on decisions, corrections, definitions, and precedent. Almost none of that lives anywhere a system can find; it lives in people, and it leaves with them. remember is the system of record for that judgment layer: governed, receipted, portable by construction, running on your infrastructure.

Subject   remember + SLF Format   Walkthrough in two acts More   lexenne.com/remember
01The problem

"It used to be Tom."

Organizational knowledge today is socially routed. Every company has its Toms, the people who hold the pricing history and the reason the workflow bends in that one spot. When Tom leaves, the answers and the index walk out together.

10 people

One desk away

The answer sits close by, and everyone knows whose desk to stop at.

100 people

Team walls

Knowledge pools inside teams. What marketing learned in March, sales relearns in May.

400 people

No head holds the map

The size of Meridian Learning, the model company in this deck. Pricing history, workflow rationale, customer promises: each lives in a different head, and the map of who holds what is itself unwritten.

The real search index is the org chart.
02The cost

You are already paying for organizational forgetting

The repeat question

Answered until someone leaves

"Why does this discount need VP approval?" The answer exists, it has been given four times, and it is written down nowhere.

The lost commitment

Promised in June, rediscovered in October

A rep promises a follow-up on a call. The promise lives in a transcript, the transcript lives in a folder, and the renewal conversation starts without it.

The ramp

Six weeks of asking around

A new hire's first real orientation is learning who to ask, one favor at a time.

The retelling

Work described three times

The same week's work gets restated in a thread, a deck, and a status meeting. None of the three tellings is findable by December.

Everyone in these scenes is doing their job. The company has no place to put what they know, so people serve as the storage, the index, and the retrieval. All three go home at five.

The organization pays to rediscover every answer it loses.
03What it is

A new, small system of record for the class of data that has none today

Decisions and their rationale. Corrections. Definitions. Precedent. The operations view of how the business actually works. remember references your enterprise data; it never copies it, and it never competes with the data stack.

Your warehouse

What happened

Billions of rows, event streams, snapshots for reporting, star schemas built for aggregation. Terabytes in Snowflake. It stays exactly where it is, doing exactly what it does.

remember

What you know, decided, and why

Tens of thousands to a low number of millions of curated facts at maturity, each individually valuable, with temporal validity. Gigabytes in Postgres, single-tenant, on your infrastructure.

Topology

It enters your data landscape the way Jira or Confluence did: an application system of record. A spoke, never a hub. It asks the data team for nothing and hands them a clean, well-governed new source.

04Meridian Learning · use cases

One sales rep's day. Existing flows unchanged; the surfaces just got smarter.

MomentWhat changes
Morning playbookThe playbook arrives already knowing what was promised in June. Nobody briefed it.
Customer callThe account page got smarter. The call's commitments become recorded facts with one confirming tap.
Product meetingProduct sees cited customer voice from every rep's calls. Nobody filed a report.
Workflow change shipsThe org stopped forgetting its own rules: the change records its own supersession, and the why rides in from the dev ticket.
Manager 1:1Opens with a pre-read of last session's commitments, visible to the two of them alone.
Slack, all day"Does anyone know…" gets a cited answer at any hour. An emoji-react saves a decision from a thread.
Sales mgr

1:1s compound

Instead of resetting every week.

Product

Customer voice, cited

Aggregated across every rep's meetings, without running a survey.

CFO

Every exception has a why

Recorded rationale on pricing exceptions; the audit takes an afternoon.

New hire

Onboarding against memory

Scoped to their lens, instead of six weeks of asking around.

remember is never a destination app. People meet it inside surfaces they already use, and every surface is also an input.

05The loop

Every surface reads AND writes. That is why this one compounds.

Use

Recorded, not surveyed

Retrieval receipts chain to downstream write-backs, so what was retrieved and acted on is a matter of record.

Correction

The highest-value capture

Retrieved-and-corrected becomes a correction fact chained to the fact it corrects.

Addition

One-tap capture

Confirm-taps on distilled meeting facts, emoji-reacts on chat decisions, forwarded email.

Absence

Recall gaps

Searched-and-not-found is recorded as demand data. It drives which connector or curation effort comes next.

Build-it-and-they-will-come knowledge bases die because the loop never closes. Here the loop closes through engagement, by construction.
06What you can prove

The proof runs on your numbers. The memory is yours to keep.

Receipted

A signed record per disclosure

What was shared, with whom, under which rules. An audit is reading a ledger, and the AI answers your people act on stop being unattributable.

Measured

By your analysts, on your numbers

Memory activity joins to pipeline, renewals, and cycle times in your own BI. No phone-home: Lexenne cannot see the numbers, so the ROI claim is yours to make.

Portable

Open-format export

The corpus exports against public specifications, deletion semantics included. The export demo is part of every evaluation.

The forty questions

"Here are the forty questions your organization asked last month that nothing could answer, and the sixty from last quarter that now have answers." The gap ledger is the prioritization instrument, the compounding record, and the renewal conversation, all at once.

The one question for any AI vendor, Lexenne included: what can I take with me if I leave?
07Where to start

Five questions that tell you whether this conversation matters

Two or more uncomfortable answers is a qualified conversation.

  1. Do you have AI or copilot projects stalled at security or legal review?The commonest blocker is access control the AI layer cannot honor. Gates that travel with each fact are the unblock.
  2. When your AI answers from company data, can you show where the answer came from?If not, every AI output is an unattributable liability under the logging rules now arriving.
  3. Can you prove that who sees what through your AI matches your access model?A signed record per disclosure is the difference between asserting compliance and demonstrating it.
  4. If you changed vendors tomorrow, what happens to everything your AI has learned?A loop you cannot carry out is one you rent, and the rent compounds with the value.
  5. Who on your side owns the AI-governance obligations landing through 2027?If nobody owns the dates, compliance-as-byproduct lands hardest here.
Contact   andrew@lexenne.com Detail   lexenne.com/remember · lexenne.com/slf · lexenne.com/partners render(substrate, lens, frame) → receipt
Act II

How it works

Act I is the business case; a business room can stop at the five questions. The rest is the machinery underneath: the governance primitive, the integration contracts, curation, models, security, and what is running today. Written for the architects and security reviewers who take this into evaluation.

08The market moment

The industry just agreed the learning loop is the asset. It has not agreed you can keep it.

Microsoft · Jul 2026

Frontier Company

A $2.5B unit, 6,000 engineers embedded at customers. The word "leave" appears nowhere; the lock moved down the stack, into memory.

Palantir · Jul 2026

The sovereignty playbook

Fifteen steps arriving at this same architecture one layer up: model agnosticism, signed audit trails, knowledge outside the model. Every step runs on Palantir's own control layer.

Google · Jun 2026

Open Knowledge Format

An open, Apache-2.0 spec for organizational knowledge at rest. Platform, incumbent, and open standard converged within weeks. The category is consensus.

Regulators · through 2027

Obligations on a schedule

EU AI Act logging and oversight, Australian automated-decision transparency, India's data-fiduciary duties. The recurring asks: event logs, traceability, provable access control.

Venture · Aug 2026

The startup wave

Venture-backed launches now sell the category itself: "the coordination tax," a brain that "should know before you ask." Loud on vision, silent on ownership.

And a gap no standard contract covers: data rights are not learning rights. Retention and training opt-outs say nothing about the derived judgment a vendor learns from watching your experts work.

09The primitive

Three terms carry the whole governance story

render(substrate, lens, frame) → receipt

Gate
A per-fact access rule that travels with the fact itself. Assigned at the write door; unknown tags fail closed.
Lens
The named view a reader reads through. It binds role and jurisdiction to the exact gates that reader may see past. Nobody queries the substrate directly.
Frame
The outcome being pursued: the unit a grant authorizes, for a human surface or an AI consumer alike.
→ Receipt
The signed, hash-chained record of what was disclosed, to whom, under which rules. The first-class output.

Underneath: an append-only ledger of typed facts (decision, correction, definition, precedent, business rule, process), each with provenance back to its moment of entry and the person behind it, temporal validity instead of snapshots, and supersession instead of deletion. Every index is rebuildable from the ledger.

A lens cannot see past its gates, by construction. There is no privileged query path.
10Where it sits

Your systems, unchanged. One small new system. Surfaces you already use.

Remember at Meridian Learning — system topography Meridian's systems — unchanged Remember — new, small Engagement layer — reads AND writes write-back: use · corrections · recall gaps metadata · entity keys threads · calls backfill gated facts export (optional) model calls · by config SalesforceCRM + business rules Marketo · Amplitudemarketing · product Slack · Gong · Emailwhere decisions happen Docs · Wiki · Drivestale knowledge today Snowflake DWfeeds stay theirs existing nightly feeds — unchanged Capturemsgs·calls·docs KNOWN scanrules·metadata Judgment ledger (Postgres)facts · gates · entities · provenancetemporal · append-only · curated SLF /v1 doorlens-scoped reads · receipted write-backs CRM memory panelinside Salesforce Slack ask-botcited answers Rep playbook AItheir model, /v1 consumer Bespoke AI projectseditorial automation Push digests · briefs1:1 pre-reads, signals Human audit doorapprove · audit · veto Curator (AI)dedupe·supersede·triage Their LLM subscriptionAzure·Bedrock·Anthropic·local existing systems + their people/AI (unchanged) Remember (new)

The model company here is "Meridian Learning," a fictional but deliberately ordinary 400-person publisher. More on their day in slides 09 and 10.

11Integration surface

Three intentional contracts with your stack. Nothing else.

IN · 01

Reference sync

A nightly upsert of entity keys and display labels from your CRM or MDM. Tiny, read-only from your side. Facts anchor to the same "customer 123" the rest of your stack uses.

IN · 02

Knowledge acquisition

Three doors: capture connectors (chat, forwarded email, documents, meeting transcripts, CRM notes) on a published envelope contract; KNOWN scanners deriving the operations view from system metadata; and the engagement layer writing back as it is used.

OUT · 01

The SLF /v1 door

Governed, receipted reads for human surfaces and AI consumers alike. Every disclosure lens-scoped, every disclosure receipted.

OUT · 02

Warehouse projection

An optional gated facts export into your own warehouse, receipts stamped at export. Your data team becomes a beneficiary, never a landlord.

Explicitly not in the design

Query federation over your warehouse. Proxying your analytics. Replacing any existing system of record. The knowledge remember wants was never in the warehouse; it lives in threads, meetings, and free text. There is nothing to migrate.

12KNOWN · no blank slate

It does not start empty. It reads your systems and loads your documents.

Leg 1 · Derived KNOWN scanned, mechanically re-verifiedDerived from
Business logic validation rules, approval processes, discount thresholds, routingCRM metadata APIs (Salesforce is the reference provider)
Campaign structure and scoringMarketing platform APIs
Product taxonomy, events, funnelsProduct analytics configuration
Feed topology what flows nightly whereWarehouse lineage metadata
System cards what exists, who owns it, how it connectsThe above, plus a short install interview
The why underneath each ruleNowhere machine-readable. Authored and captured: the judgment layer only remember holds

Drift demands a why. On re-scan, a changed rule auto-supersedes, chain preserved, and asks for its rationale once, the week it changed. "Why does my discount need VP approval now?" has a cited answer forever.

Two hard lines for every scanner: read-only credentials, and metadata only, never data rows. Those two lines keep your security review short.

Leg 2 · Loaded KNOWN. Your document corpus (product docs, onboarding, Confluence, diagrams): one scan and load per source, curated at folder and space granularity, synced by a per-container "sync to remember" flag. Facts land as cited claims; on contradiction, the scanner wins.

13Curation

Code for certainty. Models for ambiguity. Humans for named judgment.

Everything entering remember passes a three-stage intake, and the corpus is maintained the same way.

1 · Deterministic gate
Code, synchronous, cheap: envelope validation, exact-duplicate rejection by hash, gate vocabulary that fails closed, entity anchoring by exact key. Zero model calls.
2 · Judgment layer
LLM, batched: near-duplicate detection, supersedes-versus-relates, fact typing, gate suggestions, distilling transcripts into proposed facts. Semantic judgment does not decompose into rules.
3 · Human door
Consequential actions only: merges of load-bearing facts, gate changes, tombstones, redactions. Everything else flows.

The curator is AI. Corpora die when they demand human librarians who never materialize. So deduplication, supersession, drift triage, staleness checks, and distillation run on scheduled loops. Lexenne runs this pattern internally, in production, today.

The human holds an audit door. A few hours a week approving consequential actions, auditing receipts, holding veto. Visibility and veto, never labor. Every curation action is receipted, so an audit is reading a ledger.

14Models

The memory never lives in a model. Your LLM subscription plugs into three sockets.

All three sit behind one OpenAI-compatible seam. Swapping models is configuration, never code, and remember never resells inference.

Curation & distillation
Batch and cheap, on your own key (Azure OpenAI, Bedrock, Anthropic enterprise) or a local model.
Answer synthesis
Ask surfaces compose answers over lens-scoped slices. The model only ever sees what the lens disclosed, and the receipt records exactly what that was.
Your AI systems as consumers
Your playbook generators and bespoke automation register as /v1 consumers and bring their own models. On this path remember serves governed slices, never completions, and is model-free.
Always local

Embeddings and lexical indexing run in place. The corpus is never shipped out to be indexed, and there is no per-token tax that scales with corpus size.

15Landscape

What separates a real company brain from a toy

CapabilityRAG toy / DIYA real brain
Permission inheritanceVector store ignores source permissions; a good question leaks.Per-fact gates enforced at read time.
ProvenanceA similar passage, no citable chain.Every fact links to its source and moment of entry.
Temporal validityServes stale facts confidently; deletes history.Records when a fact was true and when it stopped.
Conflict resolutionWhichever contradictory fact scored higher.Supersession chains; the open frontier of the whole field (best published benchmark: single-digit accuracy).
PortabilityWhatever the platform lets you export.Open-format export, checkable against a public spec.

The funded tier (Glean, Sentra, and the memory-infrastructure layer under them) is racing at these from the recall side. The hyperscaler and Palantir stacks sell sovereignty as a heavy, platform-bound model for the largest institutions. remember is the proportionate, partner-delivered answer for organizations that will never buy those, with the one property the platforms structurally cannot offer: the loop lives on your infrastructure and leaves with you.

16Security · access · audit

Governance is enforced in the retrieval engine, not bolted on beside it

Gates

Travel with each fact

Assigned at the write door. Unlabeled entries default-restrict; unknown tags reject the write. Fail-closed, at the door.

Lenses

Cannot see past them

A fact whose gates the caller's lens does not cover is excluded before ranking. No privileged query path exists.

Receipts

One per disclosure

What was asked, disclosed, and withheld, under which lens, signed and hash-chained. What logging obligations actually ask for, produced by default.

Actors

Chains of accountability

Captures carry the acting agent and the human principal. When an AI acts, the person whose intent drove it is never lost.

Deployment posture: customer-hosted, single-tenant, inside your network and compliance envelope. Air-gap capable because models and indexing can run entirely locally. No phone-home. Scanner credentials read-only and metadata-scoped.

Regulatory alignment: event logging (receipts, by default), traceability (per-fact provenance), provable access control, erasure (tombstone with proof, versus "we cannot un-embed it"), residency (runs in place). Compliance evidence as a byproduct of architecture.

Centralizing risk? Your judgment is already centralized, in retiring heads and six ungoverned systems a well-phrased question can leak from. This replaces N unaudited surfaces with one audited one.

17Measurement

CFO-grade value, measured in your own warehouse, on your own numbers

The governance machinery is the instrumentation: receipts record every disclosure, lineage ties reads to what happened next, and everything anchors to your own entity keys. The gated facts projection lets your analysts join memory activity to pipeline, renewals, and cycle times in your own BI. Lexenne provides the join surface and never the ROI claim; with no phone-home, Lexenne cannot even see the numbers.

T0

Adoption

Asks per day, capture rate, corpus growth. Necessary, insufficient.

T1

Operational deltas

Time-to-answer, new-hire ramp by cohort, and the repeat-question rate: the organizational forgetting rate as one declining number.

T2

Activity linkage

Memory-touched versus untouched cohorts, presented as honest quasi-experiments with confounders named. Your analysts confirm the delta, not our marketing.

T3

The compounding loop

The recall-gap ledger with closure tracking, and time-to-answer bending as the corpus compounds.

18Portability · maturity

Portable by construction, and honest about the edges

The corpus is yours, and the export is checkable against public specifications rather than our word: knowledge projections emit OKF-shaped bundles (Google's draft Open Knowledge Format), including deletion and tombstone semantics. The capture contract and the SLF protocol are published, Apache-2.0. The export demo is part of every evaluation.

What is running today, and what is in build
Running
The governed substrate. Lens-scoped, permission-differentiated retrieval; signed, hash-chained receipts for governed reads; the capture envelope contract; the standalone memory server; compiled no-source container deployment for pilots.
In build
Commercial hardening. The Postgres commercial tier, the KNOWN scanner engine and first providers (specification complete), the engagement surfaces (ask-bot, CRM panel), the analytics projection exporter, and reasoning across contradiction, the hardest open problem in the field.
Shaping
The standard. SLF as a standards contribution; active engagement in the OKF conversation, including a proposed memory profile; the remaining grant taxonomy.
Contact   andrew@lexenne.com Detail   lexenne.com/remember · lexenne.com/slf · lexenne.com/partners render(substrate, lens, frame) → receipt