crop · 3682 × 2605
p01_r01 plan
not analysedgdot_plan_cd20f264c9164e3c92bc28ede80ff308_p01_r01_plan
Not read yet. Press Analyse crops, or read this one on its own.
Mindmap builder
SR21 Bridge Widening
1Read the crops15 crops · 0 readconfigured openai/gpt-5.6-terra-pro · about 9¢ for 15 crops · default
Every cropped image from the cropping run, page by page, with what the model read off it: view, objects, measurements, notes and labels. Click a crop to see it beside its JSON.
15 crops, none read yet.
Page 115 crops · 0 read
crop · 961 × 660
p01_r02 proposed vertical curve data
not analysedgdot_plan_cd20f264c9164e3c92bc28ede80ff308_p01_r02_proposed_vertical_curve_data
Not read yet. Press Analyse crops, or read this one on its own.
crop · 1283 × 599
p01_r03 endfill control diagram
not analysedgdot_plan_cd20f264c9164e3c92bc28ede80ff308_p01_r03_endfill_control_diagram
Not read yet. Press Analyse crops, or read this one on its own.
crop · 957 × 657
p01_r04 proposed vertical curve data
not analysedgdot_plan_cd20f264c9164e3c92bc28ede80ff308_p01_r04_proposed_vertical_curve_data
Not read yet. Press Analyse crops, or read this one on its own.
crop · 974 × 562
p01_r05 construction clearance diagram
not analysedgdot_plan_cd20f264c9164e3c92bc28ede80ff308_p01_r05_construction_clearance_diagram
Not read yet. Press Analyse crops, or read this one on its own.
crop · 1056 × 667
p01_r06 table
not analysedgdot_plan_cd20f264c9164e3c92bc28ede80ff308_p01_r06_table
Not read yet. Press Analyse crops, or read this one on its own.
crop · 2432 × 1246
p01_r07 plan
not analysedgdot_plan_cd20f264c9164e3c92bc28ede80ff308_p01_r07_plan
Not read yet. Press Analyse crops, or read this one on its own.
crop · 1897 × 1430
p01_r08 title block
not analysedgdot_plan_cd20f264c9164e3c92bc28ede80ff308_p01_r08_title_block
Not read yet. Press Analyse crops, or read this one on its own.
crop · 1162 × 290
p01_r09 notes
not analysedgdot_plan_cd20f264c9164e3c92bc28ede80ff308_p01_r09_notesNotes
Not read yet. Press Analyse crops, or read this one on its own.
crop · 1178 × 330
p01_r10 notes
not analysedgdot_plan_cd20f264c9164e3c92bc28ede80ff308_p01_r10_notesNotes
Not read yet. Press Analyse crops, or read this one on its own.
item · 3706 × 2621
Other P01 R01
not analysedother_p01_r01
Not read yet. Press Analyse crops, or read this one on its own.
item · 1009 × 1408
Other P01 R02
not analysedother_p01_r02
Not read yet. Press Analyse crops, or read this one on its own.
item · 1331 × 630
Other P01 R03
not analysedother_p01_r03
Not read yet. Press Analyse crops, or read this one on its own.
item · 1022 × 592
Other P01 R05
not analysedother_p01_r05
Not read yet. Press Analyse crops, or read this one on its own.
item · 2480 × 1276
Other P01 R07
not analysedother_p01_r07
Not read yet. Press Analyse crops, or read this one on its own.
2Map the itemsnot mapped yetconfigured openai/gpt-5.6-terra-pro · $1.00 → $6.00 per M · default
One set of distinct items across every page. The same bent read as “BENT”, “Interior bent” and “Bent No. 2” is one item here, carrying every page and crop it was seen in. One model call over all of step 1’s readings; the page mapping is resolved from its grouping rather than retyped by it.
Read the crops in step 1 first — there is nothing to group yet.
No items yet. Read the crops in step 1, then map them.
3Match the ontologynot matched yetconfigured openai/gpt-5.6-terra-pro · $1.00 → $6.00 per M · default
Every item from step 2 compared against the project’s engineering ontology, and then, for each one that lands in a class, a take-off of what that class asks for. The class list goes up as a closed vocabulary, so regional wording resolves without a synonym table — BENT to a pier system, PSC BEAM to a prestressed girder. Any class id that is not in the ontology is rejected rather than stored. The take-off reads every crop behind an item, derives what the drawings imply, shows its arithmetic, and says plainly when a number is not there.
Map the items in step 2 first — there is nothing to classify yet.
Nothing classified yet. Map the items in step 2, then match them here.
◈Index for the agentnot indexed · 0 points ready
Everything steps 1 and 2 know, written to the vector store for a chat agent to answer from. Cut fine — a point for each object, each measurement and each note, not one per crop — with the page, the crop and the drawing written into every one, so a retrieved number arrives with enough context to be an answer. The readings as a whole and step 2’s items are indexed too, for the questions that are about a drawing rather than a figure.
Re-runnable at any time: each point is keyed to the record it came from, so re-indexing replaces what changed, adds what is new, and drops what the drawings no longer support. Re-read a crop or correct one by hand, then press this.
Nothing to index yet — read the crops in step 1 first.
Collection mindmap_vectors, filtered on projectId = gdot_plan-cd20f264c9164e3c92bc28ede80ff308.