Platform

Agents orchestrate. Tools execute. The Ledger remembers.

EveryShall is built as a mesh of narrow agents rather than one assistant. Each agent has a single responsibility, a fixed set of tools it may call, and an obligation to write what it did to the Ledger.

The mesh

Six agents

AgentResponsibilityDeterministic tools
ScoutIngests new solicitations from SAM.gov and the state and local portals you configure, deduplicates them, and downloads every attachment.API pulls, feed reads, document download, deduplication
FitScores each solicitation against your go/no-go rules, NAICS codes, set-asides, and past performance, and writes out the reasons for the score.Rule evaluation, retrieval over your firm documents
ComplianceReads the full solicitation package and builds a matrix of every "shall", "must", deadline, format rule, and required form.Document extraction, structured table build
DrafterProduces an outline and first-draft sections. Every sentence is tied to one of your documents or to the solicitation, or it is flagged as unsupported.Retrieval, generation with citations
ReviewerChecks the draft against the compliance matrix and lists gaps, unsupported claims, and page-limit problems before you see it.Rule checks against the matrix
LedgerRecords every decision, source, model call, and human edit in an append-only log you can open for any bid.Append-only audit log
Why this shape

Reasoning and execution are separated on purpose.

EVERYSHALL RUNTIME · one firm partitionScoutFitComplianceDrafterReviewerLedgerTools: normalize · retrieve · evaluate rules · renderno tool has network egress except declared connectorsPublic sourcesSAM.gov · portalsread onlyYour exports.docx · .pdfledger .jsonProcurement portalsubmissionno path from runtimeYousubmitsreview + edit
Trust boundary. Sources are read only; exports go to you; the runtime has no path to any procurement portal. Submission is yours.
Agent Ae.g. ComplianceemitsArtifact envelopeartifact_type · schema_versionproducer · run_id · sha256Schema checkrequirement.v1validAgent Be.g. Drafterinvalidretry with error, ≤ Nthen fail the stepAgents never call each other. They exchange schema-validated artifacts; an invalid artifact never reaches the next agent.
Artifact handoff protocol. The envelope is validated against its declared schema before the next agent can consume it.

Models decide what to do next

A model classifies a candidate sentence as a staffing requirement. It does not decide which sentences are candidates, and it does not decide what the requirement says: candidates are selected lexically, and the verbatim text is byte-checked against its source span before the record is accepted.

Tools do the work

Source polling, document normalization, rule evaluation, retrieval, table construction, and file export are ordinary code with ordinary tests. Each tool call is logged with its arguments and a hash of its result. When a tool fails, the step fails and the Ledger shows exactly where.

Every sentence carries a source

Drafter writes only from retrieved passages and attaches, per sentence, the (document hash, page, character range) it used. Reviewer re-verifies each sentence in a separate call that sees only the sentence and its spans. Unsupported sentences are flagged in the editor and blocked from export until acknowledged.

Humans hold the pen at the end

No agent has a tool that writes to any external system, and no portal credentials are stored. You review, edit, export, and submit. Every edit is a Ledger entry with the text before and after.

Read the architecture, including record schemas

The Ledger

An append-only record for every bid

For each solicitation you pursue, the Ledger holds the ordered list of what happened. It is the answer to "why did it say that?" and to "who changed this?"

EntryRecorded
IngestionSource portal, notice ID, timestamp, attachments fetched and their hashes
Fit decisionScore, the rules that fired, the documents retrieved, the model and prompt version used
Compliance matrixEach requirement with its verbatim text and page reference in the solicitation
Draft sentenceText, cited source document and location, or an "unsupported" flag
ReviewGaps found, page counts, unsupported sentences listed
Human editWho changed what, when, and the text before and after
ExportFile produced, format, timestamp, and the matrix version it was checked against
Integrations and sources

What is connected today

This table is kept current. A connector appears here only after it has been run against live postings.

SystemDirectionStatus
SAM.gov Contract Opportunities APIReadIn build
State and local procurement portalsRead, one connector per portalPlanned
Document upload (PDF, Word, text)ReadIn build
Export to .docx and .pdfWrite, to youIn build
Email digests and alertsWrite, to youIn build
Any procurement portal submissionNone, by designNever
Infrastructure

Hosted in the United States. Built to be inspected.

Models

Two model tiers: a small model for classification and scoring, a large model for extraction, drafting, and verification. Model identifier and prompt version are recorded on every call. No customer data is used for training.

Orchestration

Each solicitation runs through the agents as a retryable, step-by-step workflow whose execution history is part of the Ledger.

Storage and access

Encrypted storage, separated per firm, with sign-in protected by multi-factor authentication. Details on the Security page.

We are onboarding a small number of pilot firms.

Bring a live solicitation to the first call. We will build its compliance matrix while you watch.

Request access