A project knowledge plane: cited answers and governed skills, not personal AI paste

A document controller finds the tab at 4:40 p.m. A coordinator has pasted six pages of the client’s executed contract — retention, liquidated damages, the confidentiality schedule — into a personal ChatGPT account to “check the wording.” The answer looks clean. There is no project boundary, no revision stamp, and no record of what left the building. IT’s draft policy arrives the next morning: ban consumer AI for client files. By Friday, people are still pasting — from home laptops, from personal phones, from the same hunger that made the ban feel urgent.

Or the other version of the same failure. A PM asks an assistant which fire-rating detail applies to Level 3. The model answers from a sheet that was superseded two weeks ago. The RFI goes out citing Rev B. Shop drawings move. Field work starts. The document controller finds the mismatch when Rev D was already current. Nobody can show what the model retrieved, because the session lived in a personal account that was never part of the job.

That is not an AI capability gap. It is a missing project knowledge plane: tenanted spaces, mandatory citations, permissioned skills and an auditable trail — before anyone treats chat as production practice.

Banning paste does not stop the hunt

Project Directors and Innovation leads already know the demand. People want answers from the job — drawings, contracts, specs, RFIs, submittals — not from generic training data. They want reusable skills that travel across jobs: contract readers, RFI drafters, rate look-ups, scheduling helpers. They want something that feels like an operating system for that work, not one more chat window.

What they do not have is a way to run that practice on live projects without three unacceptable outcomes: client PDFs leaking into personal accounts, agents that write into Procore or email without a named human, and a trail that evaporates when counsel or the owner asks what touched the job.

IT bans push usage underground. Personal Claude and ChatGPT sessions become the unofficial knowledge layer. Custom GPTs and laptop skills accumulate on individual machines. Excel “company memory” of rates and lessons never links back to project provenance. The firm still pays for Procore, Aconex or SharePoint as the document store — and still cannot prove what an assistant saw or did.

The competing status quo is not “no AI.” It is shadow AI with no tenancy, no citations and no approval gates.

Wrong revision is not a soft error

Knowledge failures on jobs were expensive before generative tools. Wrong drawing revision cited. Outdated rate used. Lesson learned never found. Models amplify the risk because the answer looks authoritative while the source is invisible.

Supersede has to be structural. When a drawing or spec revision is superseded, default retrieval must prefer current. Historical revisions stay available for deliberate history queries — with that fact disclosed in the citation — so yesterday’s sheet cannot silently answer today’s question. Document controllers already own revision discipline in the CDE; the knowledge plane has to honour the same map, not invent a second filing tree that drifts.

Uncited answers that export into RFIs, emails or commercial packs are how field and commercial errors get dressed as confidence. If an answer cannot name document identity, revision, page or chunk locus and retrieval time, it should be marked ungrounded and blocked from export. Citation is not etiquette. It is the difference between assist and liability.

Prove what touched the job

Owner contracts and confidentiality clauses make personal uploads structurally unacceptable for many firms. Data residency and retention are not policy PDFs — they are product obligations. When a dispute or owner audit arrives, the firm needs an append-only record: who asked, which space, which skill version, which model route, which tools were called, which citations were used, who approved any side effect, and a hash of what went out.

That is the question Innovation and IT both care about, even when they use different words: can we show what AI touched on this live project, under whose authority?

An agent that drafts an RFI from cited sources is useful. An agent that files it, emails the client or mutates a schedule without a named approver is a commercial and legal liability. Side effects outside the knowledge plane — create, send, write, mutate — belong in an approval queue with the proposed payload and citations visible until an authorised human confirms. Deny-by-default tool grants. No privilege escalation at runtime. Fail closed and audit the attempt.

Safety-critical means and methods stay human-owned. The plane drafts and retrieves. It does not certify how to build.

The unit is the knowledge space, not the chat thread

The unit of tenancy is the knowledge space — project space and company space. Documents, retrievals, skill runs and agent actions are scoped to a space. No silent cross-space retrieval. Client A drawings do not appear in Client B answers. Company memory — historical rates, lessons, standard procedures — does not leak into another client’s space without an explicit, audited promotion path with named approval and optional redaction of client identifiers.

Skills are first-class, versioned artefacts: declared inputs, tool allow-lists, model policy, space scopes. Ad-hoc prompts may help draft a skill; they cannot permanently elevate privileges. Digital champions author and publish versions; document controllers own ingest quality and supersede maps; security owns residency, retention and legal hold.

The plane stays model-agnostic. Skills declare an allowed model class or pin; operators re-route providers when quality or cost shifts. Claude-to-elsewhere churn must not destroy the library. Locking the firm to one vendor’s proprietary skill format as the sole runtime contradicts how buyers already behave.

Contextkeep is not the system of record for drawings, contracts or RFIs. It syncs with Procore, Aconex, SharePoint and peers, records external object identifiers, and keeps indexed derivatives and citations so truth can be reconciled upstream. Firms will not rip out the CDE. Adoption starts by mirroring a live project’s document tree into a space — not by promising another mega-platform replacement.

What people actually open: a space home for the live job; a document library with supersede maps and ingest fitness flags; Ask with citations where every answer carries document, revision and page or chunk — plus a citation proof viewer when counsel asks how you knew; a skills gallery and studio for versioned estimating, contracts and scheduling skills with tool allow-lists and model routes that can change without rewriting the skill; skill run detail showing retrieval, tools and citations for one run; an action approvals queue for anything that would write to Procore, email or schedule; company memory promotion with redaction; connectors health; and org admin for residency, permissions and audit export. Ungrounded answers stay in the console — they do not export into an RFI or a bid.

What “better” looks like on the ground

Value shows up in measures Project Directors and Innovation leads already argue about:

• Hours hunting docs — time PMs and coordinators spend searching instead of acting, once answers come from the space with citations.
• Share of answers with complete citations — grounded runs versus ungrounded assists that never leave the console.
• Wrong-revision rework — RFIs and submittals rooted in superseded sheets, driven toward near zero when export is blocked without citations and supersede is enforced.
• Governed usage versus shadow AI — skill runs and approved actions on tenanted spaces versus personal consumer accounts of client PDFs.
• Side effects through the gate — count of agent writes that passed approval versus anything that would have fired unsupervised.
• Time-to-first useful skill run on a new project, and dispute-ready audit export time when counsel asks.

Those are operational outcomes. They do not require a foundation-model training story on customer documents. Training on client corpora is a later, planned question — not the first cut.

What this is not

It is not a Procore feature-parity pitch. The CDE stays the system of record. The knowledge plane is the governed practice sitting on top of how people already try to use AI — with citations, permissions and audit.

It is not Quantspan. Rate libraries and past-bid memory may live here for cited retrieval into estimating; the estimating worksheet and bid package export stay Quantspan’s lane.

It is not Planvector. Drawing PDFs and metadata are stored and cited here; sheet geometry and take-off-ready vectorization stay Planvector’s job.

It is not Crewspan. Cited answers and draft payloads can feed the execution cockpit; the PM’s daily home for RFIs, look-aheads and field issues is Crewspan.

It is not Awardbind. Clause and exhibit citation feeds commercial instruments; award recommendations and the commercial spine stay Awardbind.

It is not a “build a knowledge base with Claude” tutorial. Consumer chat tools remain outside and unsupported as a store of client documents. The product is tenanted retrieval and permissioned skill runs — not another prompt library on a laptop.

First cut on one live space

Start narrow. Pick one live project where personal paste is already the pain, and where document control can stand behind the ingest:

1. Stand up one project knowledge space that mirrors the job’s CDE folders — Procore, Aconex or SharePoint — with ACLs, residency and revision supersede enforced.
2. Publish a small pack of governed skills (typically a handful, not a marketplace): declared tool allow-lists, version pins, deny-by-default scopes. Skills may draft; they may not act outside the plane without approval.
3. Require citations on anything exported — RFI language, email paste, clause packs, rate seeds. Ungrounded answers stay in the console; they do not leave.
4. Put agent side effects in an approval queue with payload and citations visible. Measure approval latency and the share of side effects that never bypass the gate.
5. Leave estimating worksheets in Quantspan, sheet geometry in Planvector, day-to-day coordination in Crewspan and commercial instruments in Awardbind. Measure hunting hours, citation rate, wrong-revision incidents and shadow-AI displacement on the Contextkeep slice alone.

That is what Contextkeep is built to be: Atlas’s project knowledge plane and governed skills OS — the operating layer between consumer chat tools and the systems of record contractors already run. Mid-market GCs and specialty trades already experimenting with Claude Skills and “chat with the job folder” are the natural wedge: enough AI hunger to hurt, enough confidentiality pressure that bans alone will not hold.

Scope the cut in a Solution Definition Sprint: which project, which document classes, which skills, which approvers, which residency and retention rules, which audit export path.

See AEC and built environment, explore Contextkeep on the Atlas, or bring us the paste problem IT cannot ban away.