AUSA 2026 · alpha · prototype site

The meeting record a denied network can still keep.

Lucid Meeting Hub captures a meeting from the machines already in it, no bot, no third party, no tenant, transcribes and reasons over it with a model that can run on a CPU-only laptop, seals it in a local vault, and moves it as a signed, end-to-end encrypted journal over any folder: a share, a satellite link, or a USB stick in a vehicle.

0 bots in the calllocal-first models, CPU includedzero telemetryno server required to syncno shared fate with any cloud
0
Bots in your call
0
Telemetry events
0
Servers required to sync
0
Minimum accelerator

This site is a prototype for review, not a deployment. Sections headed “today” describe the build we will put on your machine; sections headed “next” describe where it is going.

01 The briefing

Two films. One is real today; one is the argument for tomorrow.

Film 1 was filmed from the running application, the real interface, on a machine with no network, against a vault of simulated meetings. Nothing in it is a mockup. Film 2 is the roadmap, clearly marked as such throughout, because it is where the product is going rather than what you can install today.

Invented people, invented units, invented meetings. No recording of any real person was used, and both films say so on screen.

Film 1 · 2 min 35 · The application running, narrated A meeting in progress with nothing invited, live local transcription, a question answered from the encrypted history, decisions with owners, and model routing on a machine with no GPU. Download MP4
Film 2 · 4 min 37 · Where this goes next Two Humvees forward and their commander at the TOC, with no route to any tenant: a chat becomes a call, the crews are pulled in peer to peer, every device transcribes its own side with no bot, video is shed to hold the voices when the link fails, and only then does the commander bring in the Lucid Agent, which relays everyone's transcripts as text because text still gets through. Then a record that gets home over a thin link, and a server outage that changes nothing. Download MP4

Short cuts

Thirty to sixty seconds each, for a quick walk-through or a follow-up email. Same footage, same labels, a short can never claim more than the long film it came from.

Sixty seconds: what it does today · 0:44MP4
The day the server dies · 0:34MP4
Two tools, one conversation · 0:31MP4
No route to anybody's tenant · 2:08MP4
An AI participant with papers · 0:30MP4

02 Who it is for

One product, three ways of living with it.

There is no “government edition” with a different security story bolted on, and no crippled free tier. The capture path, the encryption and the local-first model routing are identical for a single person on a laptop, a company under client confidentiality, and a unit inside an enclave. What changes is what you switch on, where it runs, and which problem you are actually solving.

Personal

The problem: you are in six meetings a day and remember none of them, and you are not willing to feed your life into somebody's cloud to fix that.

  • Install it, use it offline, no account and no subscription to start.
  • Your own notes, decisions and action items, searchable months later.
  • Nothing leaves the machine unless you connect a model and say so.
  • Sync your own devices through a folder you already have.

Commercial & regulated

The problem: AI is useful, but counsel, clients or contracts will not let the content leave, and per-seat AI pricing is outrunning the value.

  • Client, patient, counsel or contract material never leaves the host.
  • No bot in a client's call, and no request to their IT for permission.
  • Local inference by default, so cost does not scale with headcount.
  • Retention and export on your storage, on your schedule.
  • Partner on Slack, you on Teams, one conversation, provenance intact.

Government & defence

The problem: the collaboration tool is blocked, absent or unreachable, and the record of what was decided still has to survive.

  • Operates with no internet: local segment only, record on removable media.
  • Self-hosted inside your boundary, with no path out of the enclave.
  • Identity from your own CA; card-based enrolment on the roadmap.
  • Coalition work without federating tenants.
  • Degrades honestly on a bad link instead of freezing.

The defence page, written for AUSA →

Where the three actually diverge

DimensionPersonalCommercial & regulatedGovernment & defence
Network assumptionOnline most of the time; offline whenever you wantOnline, but never requiredAssume it fails: local-segment and courier transfer are supported modes
Where it runsYour laptopYour machines or your own tenancySelf-hosted inside the boundary, or nothing
IdentityA key on your device, no account neededYour existing single sign-on, on the same device keyYour certificate authority, with card-based enrolment
ModelsLocal by default; connect a cloud model if you likeLocal by default; commercial models enabled per feature and vendorLocal, or an accredited gateway where one exists
What gets auditedNothing, it is yoursRetention, legal hold, export for counselControl-family mapping and an assessor-readable evidence pack
Who decidesYouA practice lead, a security officer, a finance owner watching AI spendA program office, a communications staff, an accrediting authority
What kills it“It wants my email address to start”“Our client content trains someone's model”“It needs a route to somebody's cloud”

Three things are deliberately identical in every column: no telemetry, your content is never training data, and the encryption does not change with what you paid.

03 Current capability

What the alpha actually does, today.

A recording-and-understanding tool for one person on one machine, Windows first. That is the honest starting line, and everything below can be opened in the source.

Capture without a bot

System audio via WASAPI loopback, attachable per process, plus opt-in microphone with voice isolation. The other participants see no extra attendee, because there is none.

Transcription & diarization

faster-whisper locally with timed segments, a cloud path if you opt in, hybrid auto in between. Speaker attribution uses enrolled voiceprints that never sync and never export.

Screen & video capture

Change-detected screenshots with OCR, and opt-in H.264 video using hardware encoders. Both land encrypted in the vault, never in a temp folder.

Notes, decisions, action items

The routed model extracts the record (decisions, owners, risks and tasks) and pushes the tasks to Microsoft To Do or classic Outlook Tasks, or nowhere at all.

Briefs, question detection, coach

A pre-meeting brief assembled from what the vault already knows; live detection of questions aimed at you, with the facts to answer them. A companion, not a replacement.

Ask across your history

Plain-language questions over every stored meeting, answered with the meetings cited. Governed by the privacy veto, which outranks the model router.

Calendar & roster

Classic Outlook COM, Microsoft Graph/MSAL and Google calendars, including new-Outlook detection and routing. Roster and participant intel merge window titles, OCR and contacts.

Knowledge sync, phase 1 & 4

A signed, end-to-end encrypted, append-only journal over any folder, plus cross-user share bundles gated on mutual approval, with future-only revocation.

macOS & Linux

Window, tray, hotkeys and TTS shipped for macOS/Linux; Linux system audio from the PipeWire/Pulse monitor. The macOS system-audio path is written but has not yet run on real Apple hardware, we would rather tell you that now than in a pilot.

What is absent entirely, stated plainly: no WebRTC, no SFU, no presence, no messaging, no outbound screen share, no multi-user identity, no tenant model, no admin console, no retention or legal-hold machinery, no mobile client. We publish that list because a gap you name is one a customer can plan around; a gap you hide is one they find in a pilot.

04 Local & small-hardware AI

It does not need your GPU, your account, or your network.

The install profiles the hardware and dispatches a per-platform backend. On a machine with no accelerator, the pipeline runs on quantised CPU models, slower, and the app says so rather than silently reaching for a cloud model to hide the wait.

The local path, end to end

  • Transcription, faster-whisper, int8 on CPU, timed segments.
  • Notes, decisions, Ask, Ollama on the box; the router probes /api/tags to prove the server is actually there before it routes.
  • Diarization, local voiceprints, never transmitted.
  • Nothing egresses, with no provider connected, the product is still whole.

The privacy veto outranks the router

power.prefer_local and integration.allow_external_ask govern /query and /ask regardless of what the model picker would prefer. A surface that reads stored meeting notes must honour the veto, not merely route through the router.

When an external model is refused, the refusal is shown and the local model answers. The UI names which model produced the answer.

And when there is a GPU, it uses it

CPU-only is the floor, not the target. The app profiles the machine at install and takes whatever acceleration it finds, a discrete card, the integrated GPU in a modern laptop, or the NPU/APU silicon now shipping in mainstream business machines. Most laptops bought this year have something worth using, and the difference is large:

  • Transcription goes from slower-than-real-time on a thin CPU to comfortably faster than the meeting, so notes are ready when you stand up.
  • A bigger local model becomes affordable, which shows up directly in the quality of summaries, decisions and answers.
  • Video capture uses the hardware encoder rather than the processor, so recording does not compete with the meeting you are in.
  • Battery and heat improve, because accelerated work finishes and the machine goes idle instead of grinding.

The important part is that nothing about the product requires it. The same build runs on an issued laptop with no accelerator at all, tells you which path it took, and never quietly swaps in a cloud model to cover for the hardware.

Providers present in the code today

Ollama local, no egress OpenAI opt-in Google Gemini opt-in xAI Grok opt-in Anthropic present, disable per tenant

A government tenant that cannot use a given vendor simply does not enable it, every provider is off until a key, an OAuth sign-in, or a local endpoint is supplied. The AskSage accredited gateway is a LUCID Agent IDE capability, not a Hub one; wiring it into the Hub router is a request we would take, not a claim we make.

A CPU-bound laptop is a supported deployment, not a degraded one.

Small quantised models, longer waits, the same pipeline, and an interface that states which model ran and where. It is the configuration most forward users actually have, so it is the one the demo shows. Give it a GPU, an integrated graphics chip or an NPU and everything gets faster and better; take it away and nothing stops working.

Film 1, chapter “CPU-only”

05 How the comms are secured

Security is the substrate, not a tier.

The crypto does not change between a personal laptop and an enclave. What changes between tiers is deployment, identity root and attestation, never whether encryption is on.

01

Captured locally

Audio is taken from the session already playing on your machine. No service is trusted with it.

02

Fenced before a model

Untrusted text is wrapped by prompt_fence so a participant's words cannot impersonate an instruction.

03

Sealed at rest

Vault: Fernet under an AES-256-GCM-wrapped master key, PBKDF2 600k, protector hierarchy, re-wrap on password change.

04

Auto-locked

Idle timeout locks the vault; sync pauses and the dashboard states the paused reason instead of pretending.

05

Signed on the wire

Ed25519 signatures, X25519 key agreement, ChaCha20-Poly1305 AEAD, RFC 8785 canonicalisation, frozen as envelope v1.

06

Nothing phones home

Zero telemetry is an invariant in the contributor contract, not a setting. Analytics are computed locally and stay there.

The API is localhost, and stays there

Host allow-list, a session cookie issued by the dashboard itself, rate-limited unlock, and a separate bearer-scoped /ext/* surface for the IDE panel. Bandit reports zero medium or high findings; pip-audit is clean.

Destructive actions are reversible

Deletes ride a five-second undo window: nothing is sent until it elapses, and every renderer filters pending rows, so the interface never shows a state the system is not actually in.

FIPS is named, not claimed

The current wire format uses X25519 and ChaCha20-Poly1305. CMVP has no validation path for X25519 key agreement today, so a FIPS profile needs a deliberate suite decision and a validated cryptographic module. That decision is open, and we would rather argue it with you than quietly ship around it. We do not claim FedRAMP or IL-anything until an authorising official writes it down.

Degrade honestly, never silently. If the vault is locked, sync says paused and why. If a capability is not implemented on your platform, it is listed as planned rather than shown as a dead button. If an external model was refused, the refusal is on screen. A product that lies about its own state cannot be deployed where it matters.

06 Forward deployed

Denied is a first-class mode, not a downgrade.

The customers who need this most are the ones without a route to the internet. This is where the product is going next, and the requirement we most want argued at AUSA.

Sneakernet

The signed journal on removable media, carried. Ciphertext before it ever touches the drive, so the courier is not a trust boundary.

Shared folder

Any drive both sides can see. This rung exists today as knowledge-sync phase 1, the rest of the ladder builds on it.

LAN swarm

Peers discover each other on the local segment and gossip the journal. No directory, no relay, no internet.

Enclave node

One self-hosted node inside the boundary when an organisation wants a durable rendezvous that still never egresses.

Bandwidth is a requirement, not a preference

If the product cannot hold a working conversation on a bad satellite link, with audio intact, video shed and the quality named rather than silently collapsing, then for the forward user it does not work at all.

  • Quality adapts continuously; audio is never sacrificed for video.
  • The degraded state is displayed, so nobody guesses whether they are still heard.
  • If the media plane fails completely, the conversation survives, the record is not the media.
  • Hostile networks: discovery off by default, relay-only candidates, and an honest statement of what traffic analysis can still see.

What a FOB meeting looks like

Four machines on a local segment. mDNS discovery answers, device certificates verify against the org CA, and the session forms directly between peers, because there is no server to form it for them.

The agent participant is a labelled node with its own certificate, announced on join and ejectable mid-meeting. It thinks on the laptop it is running on.

Reachback to the TOC is a 128 kbps intermittent link: the journal is append-only, so a dropped transfer resumes from the last acknowledged entry instead of restarting.

One codebase, five deployment shapes

TierWhoTransportsIdentity rootCryptoInfrastructure
T0 Personalindividualfolder · LAN · P2P meshself-generated user keydefault (v1)none
T1 Proprosumer+ relay · TURN · guest linksLucid accountdefaulthosted, zero-knowledge
T2 Teamcompany+ SFU · org directoryEntra / OIDC / Google, SCIMdefault or FIPShosted or self-hosted
T3 Enclavegov · CUI · DIBself-hosted only, no egressorg CA + CAC/PIVFIPS profilecustomer enclave appliance
T4 Deniedair-gapped · DDILLAN + sneakernet journalorg CA, offline licence fileFIPS profilenone, or one enclave node

The enclave and denied tiers map to control families (AC, AU, IA, SC, CM, IR) as an honest SSP annex, published as a mapping, never as an accreditation claim. The FIPS profile itself is (D1/D2).

07 Bridging what you already run

Bridge first. Replace only as a fallback.

Two organisations that both bought good tools cannot work together, because the tools are destinations rather than protocols. Slack Connect federates Slack to Slack; Teams and Slack cannot exchange messages natively at all. So the work degrades to email, a personal device, or a shadow tenant, and the record is lost to everyone, including the AI that was supposed to help.

1

Use theirs

Ride the sanctioned integration of the platform the org already runs, its API, its connector, its compliance path. Today that is calendar (Outlook COM, Graph/MSAL, Google) and tasks (Microsoft To Do, Outlook Tasks), plus capture of any meeting that plays audio on your machine.

when the capability exists and is permitted
2

Bridge theirs

Sit between two platforms that cannot talk. A Teams org and a Slack org become one conversation with provenance on every message, and neither party has to leave its tool. The bridge joins people, not tenants: each participant's node stays under its own organisation's policy, which is what makes it approvable.

when both sides exist but cannot interoperate
3

Run ours

Provide messaging, calls and screen share natively over whatever transport is reachable, including LAN-only with no internet at all. This is a fallback for people who are blocked, not a bid to replace the incumbent. On a FOB it is the only rung that exists.

when the capability is blocked, absent, or unreachable

Companion

Record the Teams, Zoom or Meet call you already attend, locally, with no bot and no tenant permission (because nothing joins).

Connector inbox

Slack, Teams and Google normalised into one provenance-carrying inbox and thread, so a cross-org conversation has one record instead of four.

Sanctioned recorder

For tenants whose policy forbids local capture: the compliance-recording path their own platform blesses, with the same downstream record.

“How do I collaborate with you if your org is on Teams and mine is on Slack?”

The blocker is usually policy, not technology, the client is right there and IT says no. A bridge that normalises both sides, keeps provenance, and asks neither party to migrate is the shortest path from that sentence to a working conversation.

Two organisations, two sanctioned tools, one conversation

08 Feature-rich comms without a server

The cheapest, most deployable server is the one you never stand up.

Peer-first is not an economy measure; it is what makes the product work where there is nothing to connect to. It also drives the marginal cost of a conversation toward zero, which is why the free tier can be honest rather than crippled.

Serverless sync, already running

Knowledge sync phase 1 needs no service at all. Two devices, one folder, a signed append-only journal: each entry is sealed with a per-epoch key and wrapped to the recipient device's X25519 key before it is written.

Phase 4 adds cross-user share bundles: one file, one recipient, one named grant, gated on mutual approval, with revocation that is honestly future-only.

The folder can be a NAS share, a synced drive, or a USB stick. The transport is deliberately dumb, because the security does not live there.

How a meeting happens with no server

  • Discovery, mDNS on the local segment; no directory service, and discovery is off by default on hostile networks.
  • Trust, device certificates issued by the org CA; identity is a keypair, not an account.
  • Media, WebRTC mesh for small groups. An SFU appears only when the group outgrows a mesh, and it is one optional peer role: run by us, by the org, or by nobody, with no code fork.
  • Record, every node captures its own side and contributes to a co-produced journal, so the record does not depend on the media path surviving.
0
Servers required to sync a meeting record today
1
Folder, the entire phase-1 transport contract
v1
Frozen wire format, digest-pinned across two repos
E2E
Ciphertext before it touches any transport

09 No shared fate

Run the server. Survive the server.

An organisation should run a Lucid node. That is where tighter control lives: directory, revocation, retention that actually deletes, legal hold, an audit log on your own metal, and an SFU when a group outgrows a mesh. What it must never be is a single point of failure you do not own. When Teams goes down, your organisation stops talking and waits for someone else's status page. That is the failure mode this architecture is built to remove.

What the HQ node buys you

One signed binary inside your boundary, with zero external egress. It is the R3 rung of denied-mode operation and the home of the org tier:

  • Directory and revocation, who exists, whose device is dead, enforced centrally.
  • Rendezvous, TURN and store-and-forward, reach for peers that cannot see each other, and delivery for peers that are offline.
  • SFU for calls past mesh size, self-hosted, so the metered line disappears.
  • Governance that enforces, retention schedules, legal hold, eDiscovery export, an audit log you hold.

What happens the day it dies

Power, a patch window, a severed WAN, a bad config, pick one. The node disappears and the conversation does not:

  • Peers that can see each other connect directly; the LAN keeps working when the WAN does not.
  • Calls and messages continue, because the media plane is the only plane allowed to be lossy, if it fails, the conversation survives.
  • Every node keeps appending to its own journal; when the server returns, the missed range is replayed, not re-said.
  • The UI names the degraded state rather than spinning on a dead endpoint.
The milestone's exit criterion is literally: “the same call works with the relay stopped.”

Not a slide, not an aspiration, the binary test native calling has to pass before it is called done. A call is established, the relay is killed mid-session, and the call continues and produces one canonical record. If that test fails, the milestone fails.

Acceptance test for the native-calling milestone

Where your organisation's availability actually comes from

When this breaksTeams / SlackLucid Hub
The vendor's cloudEveryone stops. You read a status page.Not in the path. There is no vendor cloud to lose.
Your internet linkEveryone stops.The building keeps talking on the LAN; the record queues for reachback.
Your own Lucid noden/aPeers fall back to direct connections. Control features pause; conversation does not.
Identity provider outageSign-in fails, sessions expire, people are locked out.Identity is a device keypair. SSO is an attestation on top, not the gate to your own record.
Everything at onceEmail, phones, and a shadow tenant.LAN swarm, and a signed journal on removable media if it comes to that.

Honest framing: none of the multi-user rows exist today, they are designed, not built. What exists now is the half that already proves the principle: the encrypted journal syncs between machines over a folder with no service of any kind running. The rest of the ladder is built on that same property.

Why an organisation should still run the node: control, not uptime. Directory, revocation, retention, legal hold and audit are worth owning, and a self-hosted node is also the cheapest configuration, because mesh calling costs nothing to serve and self-hosting removes the metered line entirely. Buy it for governance; you are not buying the right to keep talking, because you already had that.

10 The agentic ecosystem

The Hub owns the conversation. The IDE owns the synthesis.

Lucid Meeting Hub and LUCID Agent IDE are two products with one contract. The Hub turns a meeting into a governed, provenance-carrying record; the IDE is where an agent stands on that record and does work, under a fail-closed gate that scans every tool call.

A read-only surface, bearer-scoped

/ext/meetings, /ext/meeting/<file>, /ext/todos, /ext/analytics, /ext/premeeting. The IDE panel reads the record; it cannot mutate the vault through this door.

One wire format, two products

The Hub and the IDE share a single frozen format for knowledge items, and an automated check fails the build the moment either side's bytes drift from it. Two implementations, one contract, no silent divergence.

Shared model plumbing

The Hub can reach models through the IDE's bundled omp engine instead of duplicating credentials, and checks the CLI contract on startup so an IDE update cannot silently change behaviour.

Why the ecosystem matters more than either product

An agent that can only read your code is guessing about your intent. The intent was stated out loud, in a meeting, and then evaporated into a recording nobody watches. Close that loop and the agent stops guessing:

  • A decision made at 0930 becomes a scheduled change at 0935, with the meeting it came from cited in the change.
  • The brief for your next meeting is assembled from what the graph already knows, not from your memory.
  • Every AI-authored line carries attribution, so a reviewer can see which model wrote what.
  • The same fail-closed posture applies on both sides: untrusted text is fenced, and silence is a deny.

Is the IDE required?

Today the installer warns when LUCID Agent IDE is absent, and the app keeps saying so until it is there. That hard dependency caps the addressable deployment, a government user may never get the IDE approved.

The proposed answer: the Hub standalone is a complete communication and meeting-record product; the IDE adds the personalisation graph, cross-app recall and the agentic workspace. That is not settled, and we are not going to pretend otherwise on a slide.

11 Roadmap & open decisions

The order it has to happen in.

Milestones are addressed by id and exit on a testable statement. A milestone is done when its test has been run, not read. The first one is gated on the open questions below, which is exactly the conversation we want to have at AUSA.

01foundations

Foundations that make the rest honest

The plumbing every later milestone depends on: a frozen interoperability contract, a capability model that can honestly say a feature is off, and licensing that works with no internet.

Exit: a disabled capability holds no credential and opens no listener, proven by test.
02presence + DM

LAN discovery and direct messaging

Presence that is knowable and honest (in-a-meeting is already derivable from the listener), plus 1:1 and group messaging as journal projections.

Exit: two machines on an isolated LAN exchange messages with no internet and no directory.
03native calls

1:1 and small-group mesh, co-produced record

Rung 3 becomes real: WebRTC mesh, E2EE media, and a record assembled from every participant's own capture.

Exit: a call completes and produces one record on all platforms, including a denied LAN.
04presentation

Screen share and encrypted document sharing

Outbound presentation and files that stay inside the same envelope and provenance model as everything else.

Exit: a shared document is revocable and its access history is auditable.
05scale

SFU, MLS group keys, SFrame, guest join

Where a mesh stops being viable, an optional relay takes over, without the server ever seeing plaintext.

Exit: 8-50 participants with E2EE media, and the UI states the trust model in force.
06spaces + interop

Channels, connector inbox, mobile presence

The bridge rung ships: Slack/Teams/Google normalised into one provenance-carrying inbox. Mobile is presence, chat and join, explicitly not capture.

Exit: a Teams user and a Slack user hold one threaded conversation with provenance intact.
07org tier

Identity, admin, retention, legal hold

Enterprise identity, an admin surface, retention that actually deletes, and a forget that propagates.

Exit: a retention policy deletes on schedule and an eDiscovery export is reproducible.
08denied cert pack

FIPS profile and air-gap proof

The tier the forward user needs: a validated crypto provider, an air-gapped test matrix, and the evidence pack that goes with it.

Exit: the full denied matrix passes on a machine with no network interface up.
09agentic plane

Agent participants and in-thread AI

Agents as labelled, certificated, revocable participants whose output carries provenance and confidence, off by default in managed tenants.

Exit: an agent can be ejected mid-meeting and its prior output stays attributed.

The questions we want pushed on at AUSA

Open questionWhere our thinking currently sitsStatus
Can the current encryption suite be FIPS-validated?Not on today's key agreement, a validated module and a deliberate suite change are required before an enclave build is honest
CAC/PIV and org-issued device certificatesIdentity is a device keypair; the card and the org CA sit on top as the enrolment and attestation path
Is the agentic IDE a required dependency?The Hub standalone should be a complete product; the IDE adds synthesis and recall on top
Should AI participants be allowed inside a governed tenant?Off by default, enabled by an administrator, always announced, always ejectable
Publish the interoperability format?Yes, an open wire format is a trust asset; the implementation stays ours
Who runs the relay and directory, us, you, or nobody?Build it so all three work with no fork: your enclave, our hosted convenience, or none at all
Maximum meeting size, and when a mesh becomes a serverMeasured from real uplink headroom rather than a hardcoded ceiling

There are around thirty of these open questions on the programme. Your feedback is recorded verbatim, with your name on it, and answered rather than absorbed.

12 Who built it

Built by soldiers, for the person on the worst link.

We are not a start-up that surveyed the problem. We are two soldiers who have sat in the meeting that could not happen, on the network that would not carry it, under a policy that would not allow the tool, and then went and built the thing we wanted issued to us.

EM

Enrique Mertins

Soldier · creator, Lucid Meeting Hub

Wrote the product in Film 1: the capture path that needs no bot, the encrypted vault and its key hierarchy, the single-screen interface, the local model routing that survives a machine with no accelerator, and the signed journal that moves a meeting record between machines with no server anywhere in the middle.

The design bias is deliberate and comes from the uniform: the first user in every argument is the one on a degraded link, on a locked-down laptop, with no route to anybody's tenant.

NC

Nick Chadwick

Soldier · creator, LUCID Agent IDE · TechLead 187 LLC

Built the agentic development environment this product was written inside, the security-first harness that scans every action an AI agent takes, keeps provenance on what it produced, and is built so leadership can actually approve AI-assisted work rather than ban it.

On this programme he holds the approval lens: whether a capability can clear policy, survive an assessor, and be fielded, because a capability nobody is allowed to install is not a capability.

Why that matters at this show: the requirements on this site were not gathered from a customer interview. They are the constraints we have personally been on the wrong side of, a tool blocked by policy, a tenant with no route to it, a link that would not carry the client, and a decision made out loud that nobody could find a week later.

How two people built this much

Agentic development, gated

The work is done with AI agents inside a harness that scans every action before it runs and fails closed on anything it cannot verify. Speed comes from the gate, not from skipping it, nothing lands without passing its checks.

Provenance on the work itself

Which model wrote which lines is tracked, the same way the product tracks which model wrote which note. If we would not accept unattributed AI output in your meeting record, we do not accept it in our own source.

Nothing presented as done that is not

The rule we work to: no stub presented as finished, no mocked state presented as live verification. That is why the roadmap film is presented as a roadmap instead of demoed as a product.

The product tells the truth about its own state, because the team is built that way first.

Honest degradation is not a feature we added late. It is the same discipline we hold ourselves to while building it: name the gap, label the unverified, and never let a demo imply a capability that will not be there in a pilot.

The working agreement behind both products

13 Insider test

Run the alpha before it is a product.

We want operators, S-6/G-6 staff, program offices and integrators who will tell us where it breaks. Insider testers get the current Windows build, the forward-deployed design work, and a direct line to the two of us, your objection gets written down with your name on it, and answered.

Used once, to send the build. Nothing else.
Queued on this device: 0

What happens when you press this: your details go to our own small server, not to a marketing platform, and the only thing that comes back is the build. The form runs a short check in your browser to prove you are a person: no puzzle, no images, no third-party script. If the network is down, the entry is held on this device until you press Send queued.

14 Questions we expect

Straight answers, including the uncomfortable ones.

Does a bot join our meetings?
No, and it structurally cannot. The Hub captures the audio session already playing on your machine, the same sound your speakers get, with optional per-process attachment. Nothing joins the call, no tenant permission is required, and no third party is ever trusted with audio. The trade is honest: it records what your machine can hear, which is why the design calls for every participant's node to contribute to a co-produced record.
Can it run with no internet at all?
Today: yes for capture, transcription, notes, decisions, search and Ask, provided you use the local engines (faster-whisper and Ollama). Sync works with no server through a shared folder or removable media. What does not exist yet is native messaging or calling between Lucid users, that is what we are building next.
We cannot use Anthropic. Is that a problem?
No. The app ships with a local engine plus OpenAI, Google Gemini, xAI Grok and Anthropic as options, and every one of them is off until you supply a credential or point it at a local endpoint. An organisation that cannot use a vendor simply never enables it, and power.prefer_local keeps the product fully functional with no external provider at all. An accredited government gateway is supported in LUCID Agent IDE; routing the Hub through one is a request we would take, and we are not going to claim it before it exists.
Does it use a GPU if the machine has one?
Yes, and it should. The app profiles the machine and uses what it finds: a discrete card, the integrated graphics in a modern laptop, or the newer NPU/APU silicon in mainstream business machines. With acceleration, transcription runs faster than the meeting, a larger local model becomes practical, which you feel directly in summary and answer quality, and video capture moves to the hardware encoder instead of the processor. Without it, everything still works on a plain CPU, slower, and the app tells you which path it took. Acceleration is an upgrade, never a requirement.
What does it need to run on a forward laptop?
Windows 10/11 today, and no accelerator. The hardware probe picks a CPU backend with int8 quantisation for transcription and a small quantised instruct model for extraction. It is slower than a GPU box and the app says so. macOS and Linux have shipped window, tray, hotkey and Linux system-audio support, but the macOS system-audio path has never run on real hardware and is labelled planned rather than advertised.
Is it FIPS validated? Is it accredited?
No, and we will not say otherwise. The vault uses Fernet under an AES-256-GCM-wrapped master key with PBKDF2 600k; the wire envelope uses Ed25519, X25519 and ChaCha20-Poly1305. The algorithms are defensible but the module is not validated, and CMVP currently has no validation path for X25519 key agreement, which makes the FIPS profile a real engineering decision (D1/D2), not a checkbox. We publish an honest control-family mapping and claim nothing an authorising official has not written down.
Teams went down last quarter and we lost a day. Does this solve that?
That is the design intent, and it is proposed, not shipped, the multi-user half is designed, not built. The architecture removes the shared failure you have today: there is no vendor cloud in the path at all, an organisation runs its own node for control rather than for uptime, and when that node is unreachable the peers that can see each other keep talking directly. The acceptance test for native calling is that a call survives the relay being stopped mid-session. What exists today already proves the property at the record layer: two machines sync an encrypted journal through a folder with no service running anywhere. See No shared fateDefence vs commercialGuest web clientAUSA page.
How is this different from a meeting-notes SaaS?
Three ways. It never sends your audio anywhere. It works when the network does not. And the artifact it produces is a signed, encrypted, provenance-carrying journal that an agent can act on, not a transcript in someone else's tenant. The strategy is coexistence: use the platform you already have, bridge it to the one you cannot talk to, and only run ours where neither is reachable.
What can I use today, and what is still ahead?
Today you can install the app and get everything in Film 1: capture with no bot, local transcription and notes, decisions and action items, search and Ask across an encrypted history, and serverless sync between your own machines. Ahead of us, and shown as a roadmap film, not a demo, are native messaging and calling between Lucid users, the bridge between two organisations, the group media server, organisation administration, and the validated crypto build for enclaves. Film 2 is watermarked for its whole runtime for exactly this reason.
Who supports it if we pilot it?
It is an alpha built by a very small team, and the insider test is the support relationship: a direct line to the people who wrote it, and an append-only feedback log where your objection is recorded and answered. If you need a vendor with a 24/7 desk today, this is not that yet, and saying so now is cheaper for both of us than saying it after a pilot.

The transport changes. The artifact does not.

Watch the films, argue with the roadmap, and take the insider build home. The most useful thing you can give us at AUSA is the constraint that blocks you today.

NO BOTLOCAL-FIRSTDENIED-CAPABLENO SERVERZERO TELEMETRY