From the CLC Bid Desk · the deep tool inside the bid pursuit
Crew Bio · Bid Breakdown · v0.4 production
BecomingIQ · becomingiq.com
FROM THE CLC BID DESKDEPTH POSITION · BID PURSUIT

Breaks the bid down. Holds the boundary clean.

Nineteen skills in three tiers, plus a bypass lane. Tier-0 reads the multi-volume bid corpus and emits structured canonical state. Tier-1 reads canonical state — never the base — across seventeen scope-filtered specialists. Tier-2 reads Tier-1 only and reconciles across submittal · risk surface · schedule.

Procore reads the bid. Document Crunch reads the bid. The CLC vertical-IP reads it as a scope-filtered operator — Division 32 and its cross-references, not the whole spec book. The schema is the edge. The Breakdown is what walks it.

Three Cardinal-edge defensible-edges encoded at envelope level: regime_applicability typed third-state · boundary_state typed lifecycle · substrate_gap_propagation_chain typed actionable register. Industry-standard tools flatten all three.

PositionBid Breakdown · CLC Bid Desk · Depth Position
ENVELOPE-V0.SCHEMA.JSON · 19 SKILLS · 26-OUTPUT REGRESSION BENCH · 3 TIERS + BYPASS
19
numbered skills
3 Tier-0 · 12 Tier-1 · 3 Tier-2 · SK-18 bypass
6
genres absorbed
env · financial · testing · safety · DBE · Tier-2-reconciler
26
outputs in regression
all VALID against v0.4 envelope
~$19
full Wagner cascade cost
Sonnet 4.6 · 33 dispatches · 3.5 hrs end-to-end
— And here is your crew

Three tiers and a bypass lane. One architecture.

Each position does one job and hands off cleanly. Tier-0 produces; Tier-1 reads-from-canonical-state; Tier-2 reads-Tier-1-only; the bypass lane handles single-source corpora that have no canonical state to read from.

Coming out of the multi-volume spec book to the per-trade scope cut — at three tiers and a bypass lane, weighing in at nineteen skills and a typed third-state envelope — meet the Bid Breakdown crew.
01Tier-0 · The Foundation

The Canonical State

— Reads the bid. Builds the ground every other read stands on.

Three skills produce the structured base. Section provenance, addendum reconciliation, multi-revision merge. Subject 2 alone carries twelve downstream Tier-1 + Tier-2 consumers. Six corpus shapes recognized; Wagner BP#6D's bound-multi-revision-with-RFI-log shape is the v0.2.1 baseline.

Roster
MS-01 · addenda-merger · the canonical state itself
MS-02 · completeness-auditor · what's missing from the corpus
MS-03 · drawing-register · the sheet index
3 skills19 Subjects on Wagner1 ground truth
02Tier-1 · The Cascade

The Specialists

— Seventeen scope-filtered reads. None of them sees the whole packet.

Each Tier-1 reads canonical state + scope_filter, never the base corpus. Four-axis ownership-clean separation on shared event-class: substantive (#04a) · procedural (#08) · instrument (#12) · financial-geometry (#07). The bet that ownership-axes scale at multi-skill density — empirically validated on Wagner.

Roster · 17 specialists across 5 families
SK-04a/b/c · environmental (SWPPP · 404 · ESA §7)
SK-05a/b · materials specs + substitutions
SK-07/08 · billing-SOV + change-management
SK-09/09b · QA-QC + testing programs
SK-10–SK-17 · safety · DBE · insurance · LDs · PW · restoration · permits · sequencing
17 specialists6 genres0 base-corpus reads
03Tier-2 · The Reconcilers

The Cross-Walks

— Reads Tier-1 only. Reconciles the conflicts. Names the dependencies.

Three reconcilers cross-walk Tier-1 outputs without re-reading the base. Submittal compresses 75 raw contributions to 32 unified entries (~57% dedup). Risk Surface ratifies the four-axis split. Schedule preserves multi-period rhythm. Single Subcontract Agreement acquisition unblocks 14 of 18 MS-12 negative-tests + 4 of 11 MS-13 — the President's actionable recommendation.

Roster
MS-11 · submittal-reconciler · 5 reconciliation conflicts
MS-12 · risk-surface-reconciler · 4-axis split ratified
MS-13 · schedule-reconciler · multi-period rhythm preserved
3 reconcilers57% dedup compression0 base-corpus reads
04SK-18 · The Bypass Lane

Direct Read

— When there's no canonical state to read from. When the source is the source.

Single-source corpora skip Tier-0 with canonical_state_version='n/a'. Peer-bid decomposition, single safety report, single env audit. First seventh-genre v0.4 envelope absorption; first Tier-1-internal substrate-gap-propagation chain; structurally-inapplicable lifecycle phase first observed. The architecture's portability test, passed.

Roster
SK-18 · competitor-bid-decomposition · MH/unit benchmarks · gap-evidenced peer reads
7th genreVALID first attempt0 fix iterations
— The four-axis play

Clean separation on shared event-class. The architectural bet.

Procore and Document Crunch read a risk-event in one column and call it done. The CLC vertical-IP carries four ownership-axes around the same event — and they hold cleanly across multi-skill density on Wagner.

The bet was that ownership-axes scale at >2-skill density. Wagner Day 4 said yes.
— Axis I

Substantive

SK-04a · the WHAT

What regime applies. The clause body. The statutory citation. The thing the bid is asking the contractor to do.

— Axis II

Procedural

SK-08 · the HOW

How it's enforced. Notice procedures, change-management, the procedural cadence around the substantive obligation.

— Axis III

Instrument

SK-12 · the WHO-CARRIES

Who carries the risk. Insurance instrument, SDI election, indemnification chain, additional-insureds, waiver-of-subrogation.

— Axis IV

Financial-Geometry

SK-07 · the WHEN-IT-PAYS

Billing & SOV shape. Pay-when-paid, retainage, fields-the-Cowork-flagged. The dollar-cadence around the obligation.

— What · How · Who · Why

The four reads on a deep tool.

Every framing question on a Bid Breakdown output is one of these four. The architecture is built so each one has a clean answer.

Scope-filtered reader · typed third-state · substrate-gap-as-finding. Three Cardinal-edge defensible-edges, encoded at envelope level.
What.

A 19-skill cascade decomposing a multi-volume bid corpus into typed canonical state + 17 scope-filtered Tier-1 reads + 3 Tier-2 reconciliations. Plus a single-source bypass lane. Self-contained Python handler; live AnthropicBackend.

How.

Two-lane dispatch shape. Canonical-state-driven (Wagner) runs MS-01 → 17 Tier-1 → 3 Tier-2. MS-01-bypass (SK-18) runs single-source direct. Per-skill schemas validate every emission. Full Wagner cascade: ~33 dispatches, ~$19 list price, ~3.5 hours end-to-end.

Who.

For the operator who needs the bid taken apart at depth — the BD beyond Bid Scan, the estimator before takeoff, the PM before NTP. First install: Cardinal-State CLC vertical-IP. Productized for the commercial landscape construction band.

Why.

Industry-standard tools flatten regime applicability to binary. They miss substrate gaps. They conflate ownership-axes. The CLC vertical-IP carries the typed third-state, the substrate-gap propagation chain, and the four-axis clean separation as schema — not as guidance.

— Architectural receipts

What's true about Bid Breakdown today.

Empirically held across the build cycle. Receipts in the schema, not in the slide deck.

Verify against current state via git log + the regression bench at use time.
Tier-0 produces canonical state.

Every Tier-1 reads from canonical state, never the base. Without it, every downstream extraction is silently wrong. Empirically validated against Add-5 (Shape A) + Wagner (Shape C).

Scope-filtered, not whole-packet.

A landscape contractor reading a multi-trade bid processes Division 32 + cross-references, not the whole spec book. Envelope-level scope_filter flows declared scope into Tier-0 prompts and preserves through to output for downstream audit.

Negative-tests first-classed.

Cited-source negatives (e.g., RFI #2 Buy America “Not required” → SK-05a negative_tests[]) propagate through canonical state into Tier-1 outputs. The discipline Procore and Document Crunch don't carry.

Tier-2 reads Tier-1 only.

Architectural non-negotiable, asserted at the dispatch layer (Tier-2 dispatch with non-empty corpus_text raises ValueError). Held empirically across three parallel reconcilers on Wagner. The reconcilers don't get to peek at the base.

“Reads the canonical state. Reads only the canonical state.
Holds the boundary at the dispatch layer.
Names the substrate gap. Names what acquiring it would unblock.”

— BID BREAKDOWN · v0.4 · production · 2026-05-06