Skip to content

FeatureAI

UpCodes, Inc. via PR NewswireAI Plan Review: results reportJune to October 2026

AIPreconstructionOctober 13, 2026

UpCodes says its AI Plan Review flagged 180,000 potential code issues across 1,300 plan sets

Plan Review reads a drawing set against the codes adopted where the job will be built and returns a list of issues. By UpCodes' count, the average set came back with 21 critical issues, and 46% of those involved life safety.

Potential issues flagged
180,000More than, since the June 2026 launch
Plan sets reviewed
1,300More than
Critical per set
21Average
Jurisdictions
73Covered by the plan sets
Code editions
14Covered by the plan sets
An average plan set came back with about 138 flags, and 21 of them were rated critical
ABOUT 10 INVOLVE LIFE SAFETY21 RATED CRITICALABOUT 138 FLAGS IN ALL ABOUT 10 INVOLVE LIFE SAFETY21 RATED CRITICALABOUT 138 FLAGS IN ALL

Each square is one flag in the average plan set. The 138 comes from dividing more than 180,000 flags by more than 1,300 plan sets, so it is approximate. About 10 life-safety issues is 46% of 21. Plan sets reviewed June to October 2026. Source: UpCodes via PR Newswire.

UpCodes, an Austin company that sells building code research software, said on October 13, 2026, that its AI Plan Review feature has checked more than 1,300 construction plan sets since it launched in June and flagged more than 180,000 potential issues. Plan Review reads an uploaded drawing set and compares it with the codes and amendments adopted where the project will be built. UpCodes named Dallas-Fort Worth Airport, BDG Architects and Hereford Dooley Architects among the organizations now using it.

The workflow it touches is the code check on a drawing set before it goes to the building department for permit. On a contractor's side, that is the design manager on a design-build job or the preconstruction team reviewing a set before bid.

Section 1

Plan Review checks each set against 11 million code sections

UpCodes describes most QA/QC today as manual review, often done by one person working through the sheets against the adopted code. Plan Review takes the same set and returns a list of issues. UpCodes' June launch release describes the steps in the order a user takes them.

A run takes seven steps, and the issue list comes back at step 5
  1. Set up the projectEnter the jurisdiction, code year and building type once
  2. Upload drawingsThe drawing set goes into the UpCodes QA/QC platform
  3. Pick the analysisA general code review, or a checklist review built on the firm's own QA/QC template
  4. Pick disciplinesOptional runs for architecture, structural, MEP, fire protection, life safety, and accessibility and energy
  5. Read the issuesIssues sorted by severity and category, each linked to the drawing page and the governing code section, with plan and spec discrepancies flagged
  6. Work the listFilter, comment on, assign and track issues, and ask the Copilot assistant for a code interpretation
  7. Rerun and exportRe-upload revised drawings to run the check again, and export the report for consultants, clients or government officials

How a Plan Review run works, as UpCodes describes it in its June 2026 launch release. Source: UpCodes via PR Newswire.

The October release says Plan Review runs on multimodal AI, meaning a model that reads the drawing images along with the text on them. That lets it read a dimension string or a door location on a floor plan together with the notes. UpCodes says each run checks against 11 million sections of locally adopted codes and amendments, with amendments from more than 6,000 jurisdictions.

Code sections checked per run
11 million
Jurisdictions with amendments
6,000+
Each issue carries
Severity, category, sheet, code section

Each issue in the output carries a severity, a category, the sheet where it appears and the code section behind it. The tool also flags places where the plans and the specifications disagree, the kind of conflict a project engineer would otherwise write up as an RFI once the job is in the field.

UpCodes calls Plan Review a first-pass analysis and says the tool does not replace review by a licensed design professional or approval by the authority having jurisdiction. Someone with code knowledge still has to read each flag and decide whether it is real. A similar tool from Buildcheck, which raised $12 million in September, has its own staff check each flag before a customer sees it.

Section 2

UpCodes counted 21 critical issues per plan set, 46% of them in life safety

The evidence is UpCodes' own count of every plan set run through the tool since the June launch. The three new users the release names are an airport owner and two architecture firms. These figures come from UpCodes' October 13 announcement.

UpCodes reports more than 180,000 flags from plan sets in 73 jurisdictions
MeasureValueHow UpCodes states it
Plan sets reviewed since the June 2026 launchmore than 1,3001,300more than 1,300
Potential issues flaggedmore than 180,000180,000more than 180,000
Jurisdictions covered by the plan sets737373
Code editions covered by the plan sets141414
Critical issues per plan setaverage21average
Share of critical issues involving life-safety systemsnearly half (46%)46%nearly half (46%)
Share of critical issues that were cross-discipline coordination conflictsroughly one in ten10%roughly one in ten
Estimated potential construction error cost per projectmore than $1 million on average, estimated$1,000,000more than $1 million on average, estimated

UpCodes Plan Review results, June to October 2026, as reported by UpCodes. The cost figure is UpCodes' estimate. Source: UpCodes via PR Newswire. Download the data (CSV).

The plan sets ranged from single-family homes to commercial and medical buildings. Missing exit signage was the most common critical finding. The life-safety group covers means of egress, fire protection and fire-resistance-rated construction. The coordination conflicts are clashes between the architectural, structural and MEP sheets.

46% of critical issues involved life-safety systems, and 10% were coordination conflicts
TYPE OF CRITICAL ISSUESHARE OF THE 21 CRITICAL ISSUES PER SETSHARELife-safety systemsEgress, fire protection, rated construction46%Coordination conflictsArchitectural, structural and MEP clashes10%0%25%50%75%100% Life-safety systems46%Coordination conflicts10%0%25%50%75%100%

Share of the average plan set's critical issues, by type, in percent. The two groups can overlap, so the shares are drawn on separate bars. Plan sets reviewed June to October 2026. Source: UpCodes via PR Newswire.

The release gives totals and averages, and two more figures follow from them.

  1. Dividing 180,000 flagged issues by 1,300 plan sets gives about 138 issues per set. With 21 of those rated critical, about 15% of what the tool flags is critical. Both inputs are "more than" figures, so treat the ratio as approximate.
  2. Applying the 46% life-safety share to 21 critical issues gives about 10 critical life-safety findings per set. About two per set were coordination conflicts between disciplines, and the two groups can overlap.
Of about 138 flags per set, 21 were critical and about 10 involved life safety
ItemPer plan set, on one scalePer setHow it was derived
All flagged issues180,000 issues divided by 1,300 plan sets (both are lower bounds from UpCodes, so approximate)138180,000 issues divided by 1,300 plan sets (both are lower bounds from UpCodes, so approximate)
Critical issuesAverage reported by UpCodes21Average reported by UpCodes
Life-safety critical issues46% of 21 critical issues9.746% of 21 critical issues
Cross-discipline coordination conflictsRoughly one in ten of 21 critical issues2.1Roughly one in ten of 21 critical issues

Issues per plan set, derived from UpCodes' reported averages, June to October 2026. Source: UpCodes via PR Newswire. Download the data (CSV).

The $1 million figure is an estimate. UpCodes built it from the average issue counts and its estimated cost to resolve comparable issues during design, permitting and construction. The share of flags that a reviewer confirmed as real code issues, and the time a reviewer spent working the list, are not yet public.

Section 3

Count the comments in three to five permit letters before a pilot

The metric to track is permit review comments per submission. It is the number of comments in the building department's plan review letter for one permit submission, counted by category such as egress, fire protection, accessibility, structural, MEP and energy. A tool that catches code issues before submission should lower that count and the number of resubmission rounds.

Capture the baseline from projects you have already permitted:

  1. Pull the plan review comment letters for three to five recent projects in the same jurisdiction and of a similar building type.
  2. Count the comments in each letter by category, and record the number of review rounds and the calendar days from first submission to permit issue.
  3. Note which comments turned into RFIs or change orders after construction started.

During a pilot, log each flag the tool raises and whether your reviewer accepts it. The share accepted is the tool's precision, the portion of its flags that are real code issues. A low share means your reviewer spends more of the pilot clearing flags that turn out to be fine. Then, when the building department's letter arrives, count how many of its comments the tool had already flagged. That share is the tool's recall, the portion of real issues it caught.

A pilot log needs two checkboxes per flag, one for precision and one for recall
FlagCategorySheetCode sectionReviewer acceptsIn the department's letter
1
2
3
4
5
Precision
Flags the reviewer accepts, as a share of all flags logged. Read it from the "Reviewer accepts" column.
Recall
The department's comments the tool had flagged, as a share of all its comments. Read it from the last column.

A blank log for a Plan Review pilot, built from the fields UpCodes says each issue carries and the two measures described above. Fill one row per flag.

A first step on one job is a backtest. Take a set that has already been through permit, with the comment letter in hand, ask the vendor to run it, and count how many of the building department's comments show up in the tool's list.

Section 4

Plans list from $39 a user a month, and Plan Review sits on Enterprise only

UpCodes' pricing page lists AI Plan Review in early access on the Enterprise plan only, priced through its sales team. The Enterprise plan also lists bulk discounts for teams of 25 or more.

Essentials and Professional run $39 to $68 a user a month, without Plan Review
PlanBilled annuallyBilled monthlyIncludes AI Plan Review
Essentials$39$45
No
Professional$59$68
No
EnterprisePriced by sales
Yes, in early access, priced by sales

UpCodes plans and list prices in US dollars per user per month, October 13, 2026. Bars share one scale. Source: UpCodes pricing page. Download the data (CSV).

The Professional plan adds UpCodes' Copilot assistant, which answers code questions limited to a chosen jurisdiction and cites the code sections it used. Essentials and Professional come with a two-week free trial. The pricing page does not list a trial for Plan Review.