TORONTO — November 2, 2026 — 91¶¶Òõ, the AI workforce planning platform built for construction, today announced that Swinerton Builders (Swinerton), one of North America’s most respected general contractors, has selected 91¶¶Òõ to strengthen how it plans for its people, projects, and future opportunities.

Swinerton will use 91¶¶Òõ to bring workforce information together in one place, with real-time visibility into its pipeline and projects alongside the experience, skills, and qualifications across its teams. 91¶¶Òõ connects with the tools Swinerton already uses, and its AI-powered features and agents will help teams share resources and expertise across offices and regions and identify the people best suited for each opportunity.

“As one of the most respected general contractors in North America, we’re proud to partner with Swinerton,” said Mallorie Brodie, CEO and Co-Founder of 91¶¶Òõ. “Their decision reinforces the value of strategic workforce planning, especially for large contractors operating across multiple offices and regions that need cross-company visibility. We’re excited to help Swinerton put the right people on the right projects, and build on their legacy of delivering exceptional work.”

One Source of Truth Across the Business

For a contractor operating at Swinerton’s national scale, workforce decisions rarely sit in one office or one department. 91¶¶Òõ gives leaders across operations, Human Resources, preconstruction, and business development a shared view of capacity, so they can forecast further in advance, evaluate staffing scenarios, and bring workforce considerations into project and financial decisions.

Looking Beyond Availability

91¶¶Òõ captures the detail that informs stronger staffing decisions, including sectors, project types, certifications, client relationships, and locations. That fuller context helps Swinerton look beyond who is available and consider the experience and qualifications best suited to each opportunity.

“One of the most important roles technology can play at Swinerton is helping our teams make better, more informed decisions,” said Kim DeYoung, Vice President, Business Technology at, Swinerton Incorporated. “Our investment in 91¶¶Òõ reflects that priority. Bringing workforce information together in one place gives us the visibility to share resources and expertise across offices and regions, and to better align the right people with the right opportunities.”

About 91¶¶Òõ

91¶¶Òõ is the only AI workforce planning platform built exclusively for construction. Trusted by 40% of top contractors, 91¶¶Òõ gives teams instant answers about their people, their pipeline, and their workforce gaps, so the right crews are on the right jobs, every time. Contractors get stronger project teams, smarter staffing and bidding decisions, and a workforce strategy that stays ahead of demand instead of reacting to it. 91¶¶Òõ is a privately held company backed by investors such as Autodesk, Salesforce Ventures, and Sands Capital, among others.

For more information, visit gobridgit.com.

Media Contact:
Amy Palmer, Vice President of Marketing
91¶¶Òõ
amy.palmer@gobridgit.com

About Swinerton Builders

Swinerton Builders (Swinerton) provides commercial construction, construction management, design-build, and self-perform services throughout the United States. Founded in 1888, Swinerton is 100% employee-owned and is the preferred builder and trusted partner in every market it serves—proudly leading with ownership, integrity, leadership, passion and excellence. Swinerton has 24 nationwide offices in Spokane and Seattle, WA; Portland, OR; Boise, ID; Sacramento, Fairfield, Fresno, Concord, San Francisco, Oakland, Santa Clara, Los Angeles, Santa Ana, and San Diego, CA; Honolulu and Maui, HI; Denver, CO; Dallas and Austin, TX; Atlanta, GA; Charlotte and Raleigh, NC; Summit, NJ and New York, NY. For more information, please visit .

Media Contact: 

Danielle Ridgeway, External Communications Manager, Public Relations

Swinerton

dridgeway@swinerton.com

The post Swinerton Selects 91¶¶Òõ to Power Cross-Region Workforce Planning appeared first on 91¶¶Òõ.

Only gets done that week, and that number comes from the people who teach the practice. There is no equivalent number for staffing, because there is no equivalent practice to produce one.

Sellen used to spend its weekly operations meetings coordinating spreadsheets. Its planning meetings now run an hour instead of two. The change rests on a weekly brief of assignments starting, assignments ending, time off, and the gaps those create. Producing that brief by hand every week across all active jobs has always cost more than the week’s planning is worth, which is why almost nobody has ever done it. The four settings below are the ones the task-side look-ahead already has. The people-side version needs the same four.

Workforce gaps take longer to fill than schedule slips

A task that slips gets resequenced on Thursday afternoon. A general foreman rolling off in three weeks does not get fixed that fast. Replacing them means finding somebody qualified for that scope, available in that window, not already committed to one of the other four jobs, and, on the specialty side, current on the licenses and certifications the work requires. That search takes longer than a resequence, so the people-side read has to arrive earlier.

A weekly brief is worth exactly what the assignment record underneath it is worth. At most firms, assignments, time off, and certifications are spread across spreadsheets, whiteboards, text threads, and separate HR and field systems. A weekly read built on that will be confidently wrong every Monday. Running it more often does not help. Firms in that position have a data problem first and a cadence problem second.

Where the workforce plan changes during the week

Every input already exists in the records the firm keeps. Nobody has to add a sensor to know that the mechanical foreman finishes on the twenty-second. What breaks the plan is how fast those facts move. A general contractor accelerates a rough-in. An inspection fails. A job slips two weeks and the effect lands on three other jobs the same day.

A staffing change gets caught or missed in the weekly planning meeting, and a firm without a brief pays for the miss right there. “We have weekly meetings for business development and operations, and we would spend the operations meetings talking about staffing, not the business,” said Jamie Miller, Director of Engineering Development at Sellen. “We were too busy coordinating our different spreadsheets.” An hour spent working out who is where is an hour not spent deciding anything.

What the meeting misses becomes a problem on site the following week. The crew shows up short. The job starts unstaffed. Somebody calls an agency on Thursday hoping for a body on Monday.

Four settings for a weekly workforce planning look-ahead

The task-side practice has a definition, a window with a reason behind it, a named owner, and a number that says whether it worked. Give the people-side version the same four and it holds up week to week.

What goes in a weekly workforce look-ahead

91¶¶Òõ’s Workforce Brief, the lookahead agent, generates the weekly brief and flags gaps and bench risk before they cost anything.

Read the endings first, not the starts. A start is already staffed by definition. An ending means a person comes free and a job goes short on the same day, and it is the only line on the brief with a deadline attached. Daniel Barry, VP of Operations at Schimenti, described what reading the endings buys: “91¶¶Òõ Bench helps us keep a house of information, so we know, ‘Hey, this superintendent on the seventh week of their 12-week project, they’re going to be gone for a week.’ Then, I can start planning ahead so I have the right person.”

Set the window by how long a replacement takes

How often you run the brief and how far ahead it looks are two different settings, and they get confused constantly. Run it weekly, because that is the rhythm the rest of the operation already moves in. Set the window by how long it actually takes to fill the role, using your own recent replacements rather than an industry average.

For a crew-based operation the window varies by trade. A rough-in crew that moves as a unit needs more notice than a single fixture hand. A scope gated on certification currency needs more still, because the pool of qualified replacements is small before you even check who is free.

Scott Kramer, President and CEO at Spartan Contracting, described the read that sets it: “We can quickly see who’s on what job, how long they are there for, and when they’re going to be available. If a client wants to start a job on a specific date, we can see who will be available.” A firm that can answer that in a minute also knows how long its last three replacements actually took. That is the number to set the window from.

Give the look-ahead one named owner

One named owner reads the brief, decides what to act on, and carries the decision the way they always have. The agent pulls the facts together. It does not make the call, so the risk stays where a contractor can carry it.

The meeting survives this. Firms that expect the software to remove the meeting are surprised. “We still meet once a week as a group to run through what we’re proposing and what we want to change, but it’s dramatically changed the attitude of workforce management,” said Shawn Gallant, COO at Columbia Construction. What changes is what the hour gets spent on.

Measure how much you knew a week earlier

The task side has a completion figure. The people side has never had one, which is one reason the practice never took hold. Borrow the idea. The number worth keeping is the share of next week’s staffing changes that were already on last week’s brief. A firm that knew about four of five is running a look-ahead. A firm that knew about one of five is running a status report with a forward-looking title.

Nothing else needs measuring, and the figure only means anything against the same firm’s own history. The point of tracking it is to notice the quarter it slides, which is usually the quarter somebody stopped updating the assignment record.

What the weekly look-ahead fixes and what the planner decides

The practice fixes four things about the week and leaves the staffing decisions where they were.

For specialty contractors the left column is close to how the week already runs. The crew is already the planning unit and the week is already the horizon. AI workforce planning for specialty contractors mostly means automating the assembly of the brief inside a rhythm that already exists. The labor curve on a job says how many pipefitters week nine needs. The weekly brief is where a coordinator finds out whether they will be there. For general contractors working to a longer planning horizon, the weekly brief is the operational layer underneath the forecast. It replaces nothing above it.

Start counting next week

Set the window from your last three replacements, name the owner, and next Monday count how many of the week’s staffing changes were already on last week’s brief. That one number tells you whether you are running a look-ahead or a status report, and it costs nothing to keep.

Assembling the brief is the part that has always cost more than the planning was worth. Workforce Brief generates it, with the starts, the endings, the time off and the gaps they create, so the practice costs the owner fifteen minutes of reading rather than an afternoon of building.

The post What an AI Workforce Planning Look-Ahead Contains, and Who Runs It appeared first on 91¶¶Òõ.

TORONTO — October 14, 2026 — 91¶¶Òõ, the AI workforce planning platform built for construction, today released its second annual State of Workforce Planning report. The 2026 findings confirm that with no end in sight to labor challenges, construction leaders are responding by doubling down on agentic AI, focusing on data foundations that support informed workforce planning, and ultimately even shifting their perspective on what is important when building strong teams.

The report shows how quickly contractors are turning to technology in response. As investment rises and confidence in workforce planning software grows, more than a third of leaders are now open to implementing AI that can act on its own. Technology is also behind one of this year’s other big changes: how leaders see the importance of integration. A year ago, being able to connect a planning tool to an HRIS was a priority for just under one-third of leaders. This year it is for 99%, and nearly half of leaders (43%) already name AI tools and MCP connections as essential to integrating with workforce planning.

Ongoing labor shortage and climbing costs trigger smarter workforce planning strategies

All 250 construction leaders surveyed said the labor shortage is affecting their business, up from 93% in 2025. Cost is a top concern, with 68% of contractors reporting higher costs as a result of the shortage, up from 43% last year.

With a shortage of available workers, leaders are having to rethink how they make decisions on project pursuits and team composition. When choosing which projects to bid on, 98% of leaders now put increased weight on workforce availability and capacity, up from 60% last year. It has also changed what leaders look for in a project team. With little time for ramp-up, the importance of identifying team members with previous experience working together nearly doubled, rising from 44% to 84%, and is now the top factor in building a successful team. Factoring in experience with the specific build type fell from 59% to 27%, a drop that could be due to the explosion of data center builds, which represent a brand new build type for many contractors.

“The labor shortage isn’t new, but what is changing is the way contractors are addressing it,” said Mallorie Brodie, CEO and Co-Founder of 91¶¶Òõ. “Our research shows that leaders are prioritizing more strategic bidding, stronger data foundations, and stronger team building in order to ensure successful project delivery with the workers they do have. They’re also willing to invest additional money into developing the workforce of the future.â€�

AI is moving from making suggestions to taking action

AI adoption has become the most prominent part of this shift. 80% of construction leaders have incorporated AI into their workforce planning, with 30% actively using it and 50% in the early stages of implementation. Fewer than one in five have yet to begin.

“Contractors are ready for AI that takes on real work, provided they can see what it’s doing and step in when needed,” said Brodie. “Our research shows that the majority of contractors are looking to leverage AI as part of their workforce planning workflows, especially in strategic capacities like forecasting and predictive analytics. The biggest concerns they have are trusting AI recommendations and dealing with tools that don’t support construction-specific workflows, and both are central to how we approach usable AI at 91¶¶Òõ.”

About the Data

91¶¶Òõ surveyed 250 construction leaders at firms with $100M or more in annual revenue across the US, Canada, the UK, and Australia. Respondents were 63% Directors and 37% VPs or above, spanning operations, project management, and field operations. Year-over-year comparisons refer to 91¶¶Òõ’s report.

To explore further industry findings, the full 2026 State of Workforce Planning report is now available at gobridgit.com/state-of-workforce-planning.

About 91¶¶Òõ

91¶¶Òõ is the only AI workforce planning platform built exclusively for construction. Trusted by 40% of top contractors, 91¶¶Òõ gives teams instant answers about their people, their pipeline, and their workforce gaps, so the right crews are on the right jobs, every time. Contractors get stronger project teams, smarter staffing and bidding decisions, and a workforce strategy that stays ahead of demand instead of reacting to it. 91¶¶Òõ is a privately held company backed by investors such as Autodesk, Salesforce Ventures, and Sands Capital, among others.

For more information, visit gobridgit.com.

Media Contact:
Amy Palmer, Vice President of Marketing
91¶¶Òõ
amy.palmer@gobridgit.com

The post New Data Shows Large Contractors Turning to AI in Face of Ongoing Labor Shortage appeared first on 91¶¶Òõ.

On public work, owners score the named key personnel as a category of their own and require written approval before anyone on the chart is replaced, so the chart stays binding after the contract is signed. 91¶¶Òõ’s Project Org Chart Builder draws the chart from the staffing plan instead of the bio library. It is the agent customers have reached for most since the set shipped this summer.

The org chart commits people who may not be free when the job starts

The org chart puts named people on a job the firm has not won yet, in roles that start at notice to proceed. Because the chart presents that commitment as a diagram, substitution clauses attach to it. The past-performance section carries none. requires written approval at §2.9 before a named key person can be removed, replaced or added, and any replacement has to be as qualified as the person named. Public work is where this language is enforced hardest. Plenty of estimators will tell you substitutions happen elsewhere and rarely get blocked. The commitment on paper is the same either way.

A strong submittal explains why those individuals are the right fit. It cannot show whether they will be free when the job starts.

How the org chart changes from prequalification to award

At prequalification the chart is mostly structure. Some packages ask for the shape of the team and the staffing counts without asking for names at all. It gets drawn in PowerPoint or Excel, whichever the coordinator has open. Ask a general-purpose AI tool to make an org chart and it does this part well: clean boxes, tidy reporting lines, and no idea who is free. Drawing boxes is generic work. Picking the right name for each box is a narrow job with a checkable answer, which makes it work worth handing to an agent.

At the RFP stage the names become the submission. The same WisDOT RFQ requires the organizational chart to “identify Key Personnel by name,” so the chart carries the people the owner is scoring. When the chart is built from the bio library, the strongest resume gets the seat, and nobody checks that seat against the schedule until the chart is already in the document.

A mistake is still cheap during internal review, before the package ships. That is also where the pursuit software market currently stops. Those tools run on a library of approved material. The most sophisticated thing the category does with an org chart is compare it to another document and ask whether the narrative and the chart agree. Nobody asks whether the chart agrees with the schedule.

South Carolina DOT’s on-call bridge design solicitation S-390-26, a professional services procurement, treats unauthorized changes to key individuals during selection as grounds to throw a proposal out. Changes after award may be a breach of contract. At award the chart stops being a proposal document and becomes a contract term. Nothing goes wrong on the day it is signed. It goes wrong in June, when the superintendent named in the package is still closing out the job that was supposed to finish in February, and moving him now needs the owner’s signature.

Four practices for building a credible construction project org chart

Draw the chart from the staffing plan

The archive knows who is approved. The plan knows who is committed, because it holds the same assignments operations is already working from. Build the chart from the plan and the availability question is answered before anyone asks it. 91¶¶Òõ’s Project Org Chart Builder builds project org charts in seconds from that data, and a planner reviews the result before it goes anywhere. 91¶¶Òõ’s describes the same workflow for pursuit and bid packages, where a credible team has to be shown quickly, as one of four available now.

Jamie Miller, Director of Engineering Development at Sellen Construction, describes what that looks like in a live pursuit: “We have the RFP in hand and are all on the same platform. We collaborate on the team we assemble immediately, which can help us win a project.”

Name people you can defend on availability

Finding a qualified name is the easy part. Any chart built during a pursuit goes stale before mobilization. 91¶¶Òõ’s puts median construction workforce attrition just under 20% for 2025.

Senior superintendents turn over at 4.1% a year, against 15.4% for everyone below them. The names you put on the chart are the most stable people you have. The churn is in the supporting roles under the named seats, which is the part of the chart nobody scrutinizes. A name also depends on the record behind it, and building that record is its own job.

Show the open role on the chart

An empty box looks like weakness under deadline, so it gets filled with whoever is plausible. That is the box most likely to be wrong. A chart drawn from the plan can show the gap and the plan to fill it. Project Org Chart Builder marks the open roles alongside the hierarchy and the reporting lines.

An owner may read an honest gap as weakness or as evidence of capacity. Ask whoever read the evaluation criteria which one this owner rewards. An open role with a fill date and a named backup still holds up in March.

Keep one version of the chart

The submittal and the plan should come from one chart and one source. If they are two separate files, the plan drifts within a week and the version the owner holds stops being true. A single version also speeds up the go/no-go conversation, because the bid decision and the submitted chart sit on the same data.

“The speed-to-decision that 91¶¶Òõ gives us helps in planning go/no-go scenarios,” says Ed McCauley, VP of Corporate Services at Wohlsen Construction. “We can ensure we have the talent to put on the project to be successful for ourselves and our clients.”

What a project org chart locks and what it leaves open

The locked column deserves more attention than the chart’s page count suggests.

Draw the next one from the plan

On the next pursuit, build the chart from the staffing plan before anyone opens the bio library. Show the seats you have not filled, with a fill date and a named backup. Then keep watching after the package ships, because the commitment runs to notice to proceed and the schedule keeps moving after the bid goes out.

Project Org Chart Builder, one of the agents in 91¶¶Òõ AI, draws the chart from the same assignments operations is already working from. That is the only way the availability question gets answered before the owner asks it.

The post How to Build a Construction Project Org Chart for a Bid Package appeared first on 91¶¶Òõ.

Ask Miller to write her process down and she can give you the rules, the inputs, and a clear description of a good staffing call. The steps in between come out as half a page, because most of what happens there is judgment she has never had to explain. An AI agent needs those steps spelled out. Writing them down means building the process in more detail than anyone at the firm has ever needed before.

A staffing call leaves nothing behind

Most of what a contractor does leaves a record you can work backwards from. An estimate carries its assumptions. An RFI log shows what was unclear and when. A rejected change order preserves the argument. That is why the usual advice for documenting expertise works: sit the expert down with the estimate or the RFI log, walk back through it, and the reasoning comes out.

A staffing call leaves only the assignment. Four people were qualified, one name went on the job, and the reason is gone by Tuesday. Nobody had a reason to write it down. The experience behind the choice sits in someone’s memory, or nowhere at all. There is no document to walk back through, so the usual advice does not apply.

What your workforce planning process already covers

You almost certainly have a documented planning process, and it probably works. 91¶¶Òõ publishes a version of it: five steps that make planning systematic, from evaluation through forecasting to a monitoring loop. Contractors with ISO certification have considerably more.

That process tells you that you will be two superintendents short in Q3. It does not tell you which two people to move. The documented steps stop where the judgment starts, and the judgment is the part an agent needs. Anyone who has run a Lean program knows a process map is something you build deliberately. What is new is how fine-grained an agent needs it.

One objection came from the audience at a : “I do think you need to start with a clean or an optimized process before automating, because the last thing you want to do is automate a bad process.” Hugh Seaton, managing director of the AI consultancy AI Edge, agreed. A bad process handed to an agent becomes a faster bad process. You can learn your real process by watching an agent fail at it, but an afternoon with a whiteboard finds the same gaps as three months of bad assignments.

Where the steps go missing in a workforce planning week

Follow one routine staffing call through the week. A project manager comes free in six weeks, and a healthcare fit-out needs a PM in eight. Four things happen, and only the first and last leave a record.

1. The request gets written down: a PM for the fit-out, by a set date.
2. Somebody builds a shortlist by checking who is coming free, dropping anyone who hasn’t run this kind of job, then dropping anyone without history with this client or architect. It takes seconds, feels like a single step, and none of it is recorded.
3. One name goes forward, based on build type, who the owner already trusts, who has worked with the superintendent, and who is ready for a bigger job. David Pimuskarn, on 91¶¶Òõ’s product team, described what the team found when it tried to break this step down: “It takes a ton of human judgment, a ton of context that just lives up in people’s heads.”
4. The name goes into the plan. The system keeps who was assigned and loses why.

Steps two and three are the ones an agent needs written down, and nobody has ever had a reason to record them.

How to document a workforce planning process for an AI agent

This takes an afternoon and one decision.

Start with one recurring staffing decision

A whole workforce planning process is too big to describe and changes too often to hold still. It is also rarely one process. Before Rogers-O’Brien consolidated, three operations leaders planned resources across four regions on three separate spreadsheets. That is three processes with one name. A single recurring decision holds still long enough to finish. Assigning a PM to a fit-out, filling a superintendent gap on a running job, and staffing a pursuit you have a real chance of winning are three different decisions with different inputs. Pick one.

Write down the inputs and what good looks like

Seaton’s test for whether a task can become an agent is two questions. Can you list every input the task uses? Can you write down what a good output looks like? Both can be answered for a single staffing decision. Neither can be answered for workforce planning as a whole. The exercise pays off even when the answer is no: a decision you cannot define is one you should not hand to an agent yet.

Spell out the reasoning behind each choice

Seaton is direct about the cost: “you may have to break it down further than a human would, because we’re doing stuff in our brain or we’re just applying experience and so on.”

“I know Marcus is right for it” is a judgment. “Marcus has run three healthcare fit-outs, two of them for this owner, and has worked with this architect before” is the same judgment, spelled out so an agent can act on it. Getting from one to the other means writing down criteria the person applying them never listed. 91¶¶Òõ stores the result in Internal Resumes, which is the easy part. The experience only stops living in people’s heads once somebody has decided what counts as relevant experience.

Have a person check anything a model drafts

Asking a model to write the procedure for you is the obvious shortcut, and it produces the most confident version of the wrong answer. The FDA has written to a drug manufacturer that meant to satisfy federal requirements. The firm skipped a validation step before shipping product and told investigators it had not known the step was required, because the AI agent never mentioned it.

A model writing your staffing procedure will produce something clean and plausible that describes a firm that does not exist. The same goes for the workforce planning procedures you can download in ninety seconds. runs to ten steps of capacity arithmetic, tells you to multiply pipeline resource needs by probability of award, and never once covers who staffs what.

What to write down and what to leave alone

Everything that goes into a staffing decision belongs in one of two columns.

The left column is an afternoon per decision, and it is the whole of the preparation. The right column is why the work still belongs to a person. An agent that quietly takes those calls over is failing even when its answers look right.

91¶¶Òõ’s calls the right column institutional knowledge: which superintendent works best with which project manager, the right team for a sensitive client. It says plainly that agents cannot replace it. What they can take on is the pattern-recognition and data-gathering underneath it, which is the left column.

Start with the decision you make most often

Do not try to document workforce planning. Document one staffing decision: the inputs, what a good answer looks like, and the three or four narrowing steps you currently do in one move. That takes an afternoon, and at the end of it you have something you can hand to an agent, or a clear reason not to yet.

Software across the category now asks you to upload your procedures and teach an agent how your company works, and most contractors have nothing to upload. 91¶¶Òõ’s Team Builder asks a narrower version of the same question when it lets a firm configure the team types it prefers. Write your definition down first. The configuration is the easy part.

The post What to Do When Your Workforce Planning Process Isn’t Documented appeared first on 91¶¶Òõ.

About a quarter of contractors say . The standard advice is to clean the data first and automate second. That advice has held for a decade and it is good advice. Nobody had the budget or the hours, so nobody followed it. The change now is that cleaning the workforce record is a job you can hand to AI, and it should be the first one.

A firm of two thousand people cannot put somebody through every workforce record looking for stale assignments and expired certifications. The job has no owner, no budget line, and no end date. It is also exactly the kind of reading a model does quickly and cheaply.

What makes construction workforce data different

Construction has spent the past few years pointing AI at its messy data, and almost all of that effort went to the field. Badge events, job tickets, dictated notes, photos of equipment nameplates: all of it arrives from a sensor or a device, in volume, with a timestamp. The workforce record has no sensor. People assemble it, from what other people did on jobs, and it goes stale between the moments anyone needs it.

The questions an operations team asks of that record are experience questions. Who has run a hospital job? Who holds a current certification? Who has worked with this architect before? Generic HR systems do not carry those fields, and the tools that track the jobsite never touch them.

The standard data governance playbook assumes a company with a data team. It calls for a governance council, named data stewards, a warehouse table for quality results, automated checks on a schedule, and a ticketing queue with resolution targets. No construction operations department is getting budget for that.

Hugh Seaton, who works with construction firms on AI adoption, said this on a :

“So one of the things that you’ll hear people say is you can’t do AI if you don’t have your data in order. And the problem with that statement is the people who are listening to it are probably spending an hour a day on ChatGPT or whatever. So they’re already using AI and their data is where it is.”

Where errors enter the workforce record

The first errors arrive at setup, and none of them look like mistakes. Whoever configured the system in each office used the vocabulary that office already spoke. A firm that has grown by acquisition inherits one vocabulary per acquisition.

More errors accumulate once the work is running, as skipped updates. An assignment ends and nobody closes it, so the person shows as committed for another six weeks. A certification lapses on a date nobody is watching. Somebody moves between divisions and the old title follows them. Each of these takes thirty seconds to fix at the time. A year later it is an archaeology project.

Nothing in a contractor’s week amounts to an inspection of the workforce record. There is no submittal review for a roster. Nobody’s Monday includes reading it for things that stopped being true. A spreadsheet will hold a stale assignment forever and never mention it.

The error becomes expensive when somebody acts on it, and the most expensive version is a wage classification. Prevailing wage rules under Davis-Bacon classify a worker by the duties actually performed, not by the title on the payroll. Workers’ compensation reaches the same place from a different direction: where an employee’s payroll is split across classifications, the split has to be documented, and without those records an insurer can book all of that payroll at the highest-rated code. Neither regime accepts “that is what we call the role” as an answer.

Four ways to use AI on your construction workforce data

91¶¶Òõ’s lists four ways to point AI at the record itself: assisted audits, standardization, record enrichment, and ongoing health monitoring. Each move below is one of those, applied to a contractor’s roster.

Run the audit before you plan the cleanup

Start by reading the records. All of them. The reason the cleanup never begins is that nobody knows how big it is. A model can read every profile in the system and report what is wrong: expired certifications, assignments nobody closed, project histories that stop in 2023, offices that spell the same role three ways. Each of those is a plain-language question about the workforce, which is what Ask 91¶¶Òõ is built to take.

What comes back is a list with names and record numbers on it. Somebody on your staff still has to work through it, but a list can be assigned, split across a team, and finished. “Our data is a mess” cannot. The audit is the cheap half, and it turns the expensive half into a number you can take into a budget meeting.

Standardize role names across your offices

Sitzler eliminated 90 redundant role titles across roughly 250 staff. They did it by hand, before connecting their systems. That is the version of this move most contractors know: one analyst, one pass, a few hundred people. It was worth doing at 250. Nobody does it by hand across a national contractor’s whole roster, which is where the reading has to go to a model.

Matching records that describe the same thing under different names is close to a solved problem in other industries, and a roster of a few thousand people is a small instance of it. Two things make it the move to run first: the wage exposure above, and the fact that you can check the work.

More than half of contractors name as their chief concern about AI, ahead of data security. Pointing a model at the system of record is the highest-stakes version of that worry, and role normalization answers it directly. Write down the titles your company considers correct. That list is the standard. The model proposes a mapping from what is in the record onto the standard, and you read the mapping before a single field is written.

A model will match site superintendent to project superintendent without difficulty. What it cannot see is that a superintendent who runs a crew in one region and a superintendent who manages at job level in another are two different jobs with one name. Collapse those together and the data comes out cleaner and less true.

Fill gaps by cross-referencing the systems you already run

Most of the missing fields already exist somewhere in the company. The certification is in the HR system. The project history is in the PM system. The person who could confirm either is on a job site. The systems do not talk to each other. Scott Kramer, President and CEO at Spartan Contracting, described the cost of that: “Our software stack is mostly siloed information, which also leads to double, triple, sometimes quadruple data input.”

Cross-referencing what those systems already hold replaces that duplicate entry. The gaps that remain are not equally important, so rank them. A missing certification on somebody about to be proposed for regulated work is a different problem from a missing project from 2019. Working the ranked list keeps enrichment from turning into a completeness exercise nobody finishes.

Monitor completeness so the cleanup holds

A cleanup with no monitor behind it is a cleanup you will run again in two years. Pick the fields you would stake a pursuit on: certification status and expiry date, assignment end date, role title against the standard list, and the last two projects worked. Set a completeness threshold on those fields and put someone in charge of watching it, so a drop gets caught early, before it spreads across the roster. 91¶¶Òõ’s own guidance on building an internal resume database makes the same point from the other end. It recommends that firms set accuracy standards for workforce records and hold to them.

Monitoring is a standing practice that the one-time cleanup pays for. Once the backlog is gone, staying current costs a few corrections a week.

What the model settles and what still needs a person

The four moves do not carry the same amount of automation.

The model handles the cases it is sure about and hands you the rest. Audits and monitoring work the other way: they generate work for people. Surfacing an expired certification is one act. Chasing it down is another, and only the first one is automatic.

Run the audit first

The audit is the cheapest of the four moves and the other three depend on it. It turns “our data is a mess” into a list with names and record numbers on it, and a list can be assigned to somebody and finished. Everything the guide says about agents rests on that record being trustworthy: an agent working from incomplete or inaccurate data does not produce better outcomes, it produces poor outcomes faster.

If your workforce record already lives in 91¶¶Òõ, the audit starts as questions. Ask 91¶¶Òõ takes them in plain language, and the answers are the list. Give it to somebody, and give that person a Thursday.

The post Using AI to Clean Up Your Construction Workforce Data appeared first on 91¶¶Òõ.

Catching that does not take a monitoring platform. It takes a few things a contractor can check in fifteen minutes a week. The first is override rate: how often people accept the agent’s recommendation, and how often they quietly do the job themselves. The agents in 91¶¶Òõ AI propose and wait for a planner to confirm. Team Builder proposes a team and Assignment Finder proposes a role for someone coming free. That confirmation step produces the override number every week, at firms that already run it. Almost nobody reads it as a signal.

Why a staffing call is harder to check than a submittal

Construction supervises output by measuring things it can point at. A wall gets inspected. A quantity gets checked against the takeoff. A submittal gets reviewed. When the work is wrong, someone finds out fast: route a submittal to the wrong trade package and the person who opens it sees the mistake and sends it back. Document agents fit that habit.

A staffing recommendation is different. It picks one of four qualified names for a March start, and a slightly worse choice looks like a slightly different choice. There is no defect log for it. Nobody raises it. The planner changes the name by hand and gets on with the week. The system does not know it made a mistake, so the quiet fix does not improve anything.

Where drift enters the workforce planning week

Agents fail in two places, and only one of them has an alarm.

The first failure happens before launch, when nobody wrote down what a good output looks like. Those agents were never going to work, and firms find out within a few weeks. Most of what is written about why AI initiatives stall before they ship is about this failure.

The second failure happens to an agent that passed every check. Here is how it goes. The agent proposes a staffing plan for the weekly look-ahead, built from current project data and from its record of past runs. The planner confirms the recommendation or overrides it before the week is staffed. Reviewing each recommendation before you act on it is a control on one output at one moment. It stops a wrong answer from becoming a staffing decision. It says nothing about the trend. A firm can review every recommendation for six months, catch every bad one, and never notice that the share of bad ones has doubled.

An override also leaves no trace that the agent can read. The planner fixes the name, the week moves on, and the agent’s record shows no sign that anyone disagreed.

Drift is the word for what happens next. Nothing breaks. The agent still runs on schedule, still returns a recommendation, still produces output that looks the same as it did in the spring. It is getting worse at the judgment. 91¶¶Òõ’s names the other way in. Stale or inconsistent records get amplified when an agent acts on them, so an agent recommending a team from outdated availability data is working from a false picture, and nothing in its logs says so.

The weekly look-ahead is where drift shows first: more corrections, and people reading the recommendation less carefully. It is also the only place it shows.

Four practices for monitoring an AI agent after go-live

Start with override rate

Your review step already creates the data you need. Every time someone confirms or overrides a recommendation, that is a data point. Over time the data points form a pattern that tells you how well the agent is doing. Three months of confirmations is enough to see the direction.

Firms with no instrumentation at all do not get an alert when quality drops. They get a complaint, a billing oddity, or people quietly ignoring what the tool says. The people closest to the work lose confidence before any system reports a problem. A rising override rate is that loss of confidence, written down.

Read cost per run as an early tell

An agent checks its own work against its instructions and tries again when the work fails. So a struggling agent costs more than a healthy one doing the same job. Cost per run moves before the output looks obviously wrong.

One expensive month proves nothing on its own. Runs of the same agent on the same task can , and the study that measured it also found that spending more did not buy a better answer. There are innocent explanations too: more people are using it, the jobs got harder, somebody widened the data it reads. A cost line tells you when to go and look. It does not tell you what you will find.

Record a baseline at go-live and reread it weekly

Three things in the first month give you a baseline, and together they take an afternoon. Note what one run costs. Note how often people accept the recommendations while the agent is new and everyone is paying attention. Save eight or ten real staffing cases with the answers the agent gave, in a folder somebody will be able to find.

Then reread it. A baseline in a folder nobody opens is a baseline nobody has. Fifteen minutes on a Monday against those three numbers is the whole practice.

There is no correct override rate and no correct cost per run. The only thing that matters is the change from what this agent used to do, on this work, with this team. A firm that skips the baseline ends up arguing about impressions. Somebody thinks the recommendations got worse. Somebody else thinks the jobs got more complicated. No record settles it. Reconstructing six months of staffing decisions to find the week the quality slipped is not an afternoon’s work, and by then nobody can say what the agent used to do.

Start with one agent and one reviewer

One agent with a named reviewer beats five agents nobody owns. The reviewer’s job is the weekly read, and it gets easier the fewer agents it covers.

Hugh Seaton works with construction firms on AI adoption. He described the job on a : “[S]omeone has to keep an eye on how the agents are performing, and that’s a dashboard. It’s not technical, but nevertheless it has become more of a thing than it was before … almost like HR for agents.”

That job belongs with operations, not IT. Only someone who knows a good staffing call from a passable one can see the decline, and that judgment sits with operations and workforce directors, not with whoever administers the software. The work is closer to supervising a new hire than running a system. Check the early work closely, notice the month the quality slips, and have the conversation.

What to watch weekly and what to leave alone

The left column takes about fifteen minutes a week. The right column is real work for somebody with an engineering function, and a general contractor does not need it to catch an agent that has been getting worse since March.

Put a name against it this month

If an agent has been running since the spring and nobody has written down its override rate, start this month. Note the rate, note the cost per run, save ten cases, and give the weekly read to one person in operations. If none of that exists, the honest position is that nobody knows whether the agent is better or worse than it was, and nobody will until the numbers do.

The confirmation step is the instrument. 91¶¶Òõ’s agents propose and a planner confirms before anything is staffed, so the override number already exists every week. Reading it is the whole practice.

The post What to Watch After an AI Agent Goes Live appeared first on 91¶¶Òõ.

Try it on something real. One superintendent is assigned to two jobs in the same week. The inputs are two sets of dates. A good result is the overlap, flagged before anyone promises a client anything. That check is already running at firms that are still holding meetings about whether they are ready for AI.

Below, three common workforce planning decisions go through the test. They land in three different places.

Why a staffing decision is harder to hand off than a submittal

Most general contractors already use agents on documents. Something routes a submittal, flags an RFI, or reads a daily log and reports what changed. 91¶¶Òõ’s explainer on what separates an assistant from an agent covers that ground. Document work has one property that makes it easy to hand over: when it goes wrong, somebody notices right away. Route a submittal to the wrong trade package and the person who opens it sees the mistake and sends it back.

A staffing decision does not give you that signal. Pick one of four qualified people for an April start and a wrong pick looks like a reasonable pick. Nobody sends it back. The planner may frown at the name, change it by hand, and move on. The job runs and the work gets done. The cost of sending the second-best person shows up months later, when the client does not call for the next job.

That is why the second question in the test carries most of the weight in workforce planning and almost none in the document layer. Writing down what a correctly routed submittal looks like takes one sentence. Writing down what a good project team looks like at your firm means deciding what you value: client relationships, sector experience, who gets stretched. Most firms have never made those decisions explicitly.

Exposure is what makes operations leaders cautious about handing this over. Gaurav Singal of ConstructConnect put the plainly: “Am I going to be the person who trusted the AI and got burned on a bid?” On accountability, he added: “The smart ones know the accountability doesn’t transfer when the software is wrong.” Sorting your decisions before you delegate any of them limits that exposure. The cost is an afternoon on three recurring decisions. The alternative is losing a pursuit because nobody can explain how the team was picked.

The two-part test for AI workforce planning decisions

Hugh Seaton is Managing Director of AI Edge, an AI consultancy that works with contractors. On a he gave the rule his team uses before building anything: “if you could list all of the inputs, in other words it’s a finite number, and you could write down what good looks like, or give it an example of what good looks like, what finished looks like, that’s most of what you need to make an agent.”

You can answer both questions about one task in a meeting.

The first question is a completeness check. An agent that meets an input it has never seen does not stop and ask. It carries on with what it has and produces an answer anyway. So you need to be able to name every input, on a whiteboard, today.

The second question decides whether the agent can exist at all. An agent needs a way to check its own answer without handing the work back to you. That means somebody writes down the standard it checks against. Seaton listed what fails here: “things that require judgment, things that are open-ended, things that have lots and lots of different possible inputs are really hard to make an agent for.”

Writing in in January, Ethan Mollick said the people who thrive will “know what good looks like, and can explain it clearly enough that even an AI can deliver it.”

Most people say yes to the second question and find out otherwise when they try to write the standard down. Seaton, who has spent thirty years around process, says he has never had a standard operating procedure he followed perfectly, and that most teams cannot accurately describe their own steps. Answering honestly takes work. A later piece in this series covers what to do when your process only exists in people’s heads.

None of this depends on what the vendor calls the thing. Seaton, on the label: “I don’t think it matters if it’s an agent or something you know, or a ham sandwich. What matters is, is it reliably doing what you want and adding value to your team?” The test matters. The label does not.

Three workforce planning decisions, run through the test

The test gives one of three verdicts. “Not yet” is the useful one, because it names the specific piece of homework that is missing.

A scheduling conflict an agent can flag today

One person, two assignments, overlapping dates. Every input is a date already in your system. A good result is unambiguous: the overlap, surfaced before it becomes a promise. Nobody disagrees about the right answer.

This passes so cleanly that it has already shipped, and it is also the one most likely to be dismissed as too small to bother with. It is not small. A conflict caught on Tuesday is an email. The same conflict caught when a superintendent does not turn up is a schedule problem with a client attached. Start here.

A team shortlist that needs your definition of good first

Assembling a project team splits the test in half. The inputs can be listed, though the list is long: build type, market sector, availability, cost, who has worked with this client, who has worked with each other. The first question passes.

The second question is where most firms stop, and the reason is not technical. “Good” here means a strong team for this job, and that standard belongs to your firm. Three calls decide it:

• Does a repeat client relationship outrank sector experience? The PM the client already trusts, against the one who has built four of these.
• Do developing people go next to senior ones on purpose? That pairing costs something on this job and builds the bench for the next one.
• What do you give up when the ideal person is booked? Every shortlist reaches this question, and most firms answer it differently each time.

This does not have to be a single rule, Seaton says. An agent can hold several definitions of good and check itself against all of them. Somebody still has to write them down first.

The work this verdict names pays off whether or not you ever deploy an agent. The agents in 91¶¶Òõ AI include Team Builder, which proposes a team and waits for a planner to confirm it. What that proposal is worth depends on whether your firm has said what a strong team means. The software is available now. The definition it runs against is still yours to write.

A hiring decision that should stay with a person

Deciding which project manager to hire fails both questions, and it should. The inputs include who will work well with a difficult client, who is ready to be stretched, who is quietly looking elsewhere. None of that sits in a database, and some of it has never been written down anywhere. There is no evaluation you could hand a machine that would let it check its own answer.

A test that says yes to everything is not a test. The near-term value of agents in workforce planning sits where something proposes and a person confirms. 91¶¶Òõ’s sorts agent work into assistive, semi-autonomous and autonomous, and puts the near-term value for contractors in the first two. Anyone promising more is selling past what has shipped.

Where the decisions land

Each verdict tells you what to do next.

91¶¶Òõ’s explainer on agents ends by telling teams to decide where the line sits and write it down together. Run that exercise on one decision and you have a verdict by the end of the meeting.

The middle row asks for a definition of good. For a staffing decision, that means naming which experience actually matters: what someone has built, for which clients, in which sectors, and alongside whom. A firm that holds a real record of who has done what can write that definition in an afternoon. A firm whose experience data lives in a spreadsheet and three people’s memories cannot, and for that firm the agent question was never the real obstacle.

Run the test on one decision this week

Pick the staffing decision that comes around most often, put the two questions to it in a meeting, and write the verdict down. If it lands in the ready column, you have found your first agent. If it lands in not yet, you have found the afternoon of work that was actually in the way, and it was never a technology problem. Either way, keep watching once something is running, because an agent that was right in March can be worse by September while the logs still look normal.

If you want something concrete to run the test against, 91¶¶Òõ’s five agents are described one at a time, each with what it proposes and what it leaves to the planner. That is a reasonable place to see where your decisions land.

The post How to Tell Which Workforce Planning Decisions an AI Agent Can Handle appeared first on 91¶¶Òõ.

The Company

About Nox Group

Nox Group is a rapidly expanding construction and industrial firm that currently serves customers throughout the United States. Nox Group includes:

• Corbins, an industrial electrical contractor
• RMCI, an industrial general contractor
• Construction Labels, a total label and tagging fabricator
• Nox Group Innovations, which handles fabrication and virtual design

This unique structure lets Nox Group flex to serve each customer, whether they need self-perform electrical, general contracting, prefab, or a combination of all four. As Nox Group scaled over the past decade, the way they planned and deployed crews had to evolve to maximize flexibility and proactivity in resourcing across their projects.

The challenge 

Spreadsheets spread thin

Like many specialty contractors, Nox Group ran its manpower planning out of “a gross combination of Excel docs flying all over the enterprise,” as CIO Nate Unruh describes it. Support functions planned one way, field crews another, and none of it connected.

This approach held up while Nox Group was small, but broke down the moment they started winning bigger, more complex industrial work.

Excel docs work really well when you’re a small company. But the second you start getting hundreds of managers that need to identify needs, and those individuals are going over multiple geographies, it quickly becomes unscalable. We saw that as a big limiting factor.

Nate Unruh

Chief Information Officer

The solution 

A planning system built for the way trades work

Nox Group adopted 91¶¶Òõ in 2022 and experienced an early win by solving the exact problem spreadsheets couldn’t solve: getting assignments out of one superintendent’s head and into a system the whole team could see and act on.

Within eighteen months, Nox Group extended 91¶¶Òõ across the entire enterprise, using it to identify and fill every kind of role, from modelers to talent acquisition specialists. For the talent team, 91¶¶Òõ became the single pipeline they needed full visibility into at all times.

Crews built for large projects. With up to three hundred electricians on a single job, seeing them organized visually provides an important level of transparency. 91¶¶Òõ gives Nox Group a way to structure traveling crews, foreman-led crews, and site organization in one view.

Certification and license tracking. Manpower decisions at Nox Group aren’t just about availability; they’re about who’s qualified. Underground, low-voltage, and medium-voltage work each demands specific skill sets, and equipment operators are a small, critical subset of the team. Electrical licensing adds another layer, because requirements differ in every state.

“Licensing can get complicated across state lines, since electrical licensing is different for every state. 91¶¶Òõ helps the team identify those differences and still move people with confidence, without having to go into another system to look that information up.”

Bulk edits that keep up with ambiguity. As a trade contractor, Corbins (the industrial electrical contractor within Nox Group) lives with constant schedule changes driven by the GCs and partners it works alongside. Rather than plan too far out, the team keeps the next six weeks accurate and adjusts as new schedules arrive — usually by bulk-shifting dates across many roles at once. 91¶¶Òõ’s bulk-edit capabilities let the team absorb those changes quickly instead of reworking plans by hand.

The impact

Betting on better crew planning

For Nox Group, the payoff shows up in the ability to efficiently plan for massive, high-quality projects. 91¶¶Òõ gives Nox Group a shared system where field crews, project leadership, and support functions all plan together instead of depending on a single point of failure.

When you get to that level of scale, it can no longer be one person holding the whole ship together. It’s got to be a collaboration of people — and they need a system they can collaborate in. That’s how the team uses 91¶¶Òõ: it’s a collaboration manpower planning tool.

Staying ahead of labor challenges. Skilled electrical labor is hard to find, and Nox Group uses better planning to stay in front of it. Visibility into staffing gaps lets leadership flag understaffed jobs early and direct extra support where it’s needed. That same view feeds Nox Group’s talent development—keeping the bench full of future promotions so the company can grow its own leaders, not just hire them.

“Even just having visibility to a gap is a really powerful thing. Whenever we have more time, we’re able to be more successful. It’s important for us to fill those gaps with intentional talent acquisition—and talent development—efforts in our organization.”

Looking ahead

The next chapter: AI in specialty workforce planning

Nox Group is already pushing forward to what’s next. Using 91¶¶Òõ’s MCP connector, the team has begun querying 91¶¶Òõ data with its own internal AI models.

Our users are already able to ask natural language questions about the data in 91¶¶Òõ and get answers faster than actually going into the platform. That’s changed the game for our team. Individuals who are more consumers of that information can access it and ask questions much more easily.

For Nox Group, a well-built semantic model over the data is now part of how it evaluates technology partners, because it saves the team from building that intelligence themselves. Combined with features like AI-generated org charts, it’s the next step in a journey that started half a decade ago.

Asked whether he’d recommend 91¶¶Òõ to a peer, Unruh doesn’t hesitate:

“Absolutely. Our business could not have scaled without this tool. From a talent management and manpower standpoint, there is no better solution out there for visualizing and improving that discipline with your teams—for the current and the future.”

Our users are already able to ask natural language questions about the data in 91¶¶Òõ and get answers faster than actually going into the platform. That’s changed the game for our team. Individuals who are more consumers of that information can access it and ask questions much more easily.

Nate Unruh

Chief Information Officer

The post How Nox Group scaled specialty contracting with 91¶¶Òõ appeared first on 91¶¶Òõ.

91¶¶Òõ’s explainer on what MCP is covers the standard and what a connection looks like. This picks up from there and goes through what has actually been built.

An “official” MCP server is built and maintained by the platform vendor itself, the way Salesforce, HubSpot or 91¶¶Òõ build and support theirs. A “community” server is built by an independent developer, and it may or may not be maintained over time. Think of it as the difference between a manufacturer’s own accessory and an aftermarket part: both can do the job, and only one comes with somebody obliged to answer the phone.

Both are useful. You just judge them differently, and the section at the end covers how.

Where a vendor publishes its own documentation, the links below go there. Where a server exists only as a community project, the link goes to a registry listing, which is a place to start looking rather than a recommendation.

MCP servers for construction and design platforms

Autodesk publishes the most developed set of official servers in this category, though the coverage sits on the design side rather than the field side. Its is fully released and gives an assistant read-only access to documentation across more than 110 products, and a Fusion Data server covers Fusion’s backend project and folder data. Two more are earlier in the cycle: the is in tech preview and a Fusion Automation server is in private beta, so treat both as worth watching rather than worth building on this quarter. For teams working with Autodesk 91¶¶Òõ Services, Autodesk also publishes against its APIs, which is the realistic path if what you need is Autodesk Build or Construction Cloud data rather than model data.

Procore does not currently publish its own MCP server for project data, though it is building MCP support directly into the platform. Its now lets apps declare MCP servers and AI agents as components of a Procore app, with the stated aim of making every Marketplace app agent-ready. In the meantime several community servers exist against the Procore API, and Zapier offers a Procore connector. Anyone evaluating a community option should look closely at how it authenticates and what access it asks for, because Procore holds a great deal of commercially sensitive project information.

CMiC and Unanet have no official server and no established community server that we were able to verify, which leaves anyone on those platforms building against the API directly if they want a connection at all.

In practice that means a question like “what changed in the mechanical model since last week” is reachable today through Autodesk’s design-side servers, whereas a question like “which RFIs on this job are still open and who owns them” is not, because it lives in the project record rather than the model. That is the half nobody has shipped, and it is the half most field teams would actually use.

MCP servers for CRM and pursuit data

This is the most mature category in the list, and it matters more for construction than it first appears, because pursuit data is what turns workforce planning from reactive into forward-looking. Knowing a job sits at seventy percent probability three months before award is the difference between staffing it deliberately and scrambling for a superintendent the week it signs.

An assistant that can reach the pipeline answers questions that currently require somebody to pull a report and cross-reference it by hand, and those questions get asked far less than they should precisely because of how long they take to answer.

Salesforce supports MCP through Agentforce, with covering how resources, tools and prompts are exposed to an assistant. It works through your existing logins, so an assistant can only see what the person using it could already open.

HubSpot ships , one connecting any MCP-compatible assistant to your CRM for querying and writing records, and a second serving developers building on the HubSpot platform. Both connect through your existing HubSpot login, so access follows whatever that account can already reach.

Microsoft Dynamics 365 publishes official servers for and for Customer Service, the latter generally available since July 2026, with a Commerce server in preview. Supported clients include Copilot Studio alongside external ones such as Claude Code, ChatGPT and VS Code. For contractors already standardised on Microsoft, this arrives inside a governance model the IT team has almost certainly configured already.

Community and emerging servers

• Zoho Bigin. Simplified pipeline CRM with a community server via Smithery, relevant to smaller contractors already running the Zoho suite.
• Pipedrive. Deal-tracking CRM with a community server, common among regional contractors and specialty firms that never adopted an enterprise CRM.

MCP servers for HR and people data

This category is close to empty.

We could not verify an official MCP server for Workday, BambooHR, UKG, Oracle, ADP or Namely. Workday’s developer portal makes no mention of the protocol at all, and a URL that looks like a BambooHR MCP endpoint resolves to a login page rather than to documentation.

For workforce planning this is the most consequential absence on the list, because HR systems hold the roster, the certifications, the cost codes and the start dates that make a staffing answer trustworthy. Without a connection, an assistant works from whatever somebody last exported and uploaded, and the export is where this goes wrong. A roster pulled in March will answer a question about June with complete confidence and no indication that three people have left and two certifications have lapsed, which is a worse outcome than getting no answer at all.

Until those vendors ship, the practical route is a workforce platform that already syncs from your HRIS and exposes its own connection layer, so the assistant reads current state rather than a snapshot. That is the approach 91¶¶Òõ takes with its MCP connection to live workforce data.

MCP servers for spreadsheets, data and warehouses

Airtable publishes available on all plans, with access matching whatever the person connecting it can already see, which makes it useful for the trackers and light databases that accumulate around a construction operation.

Google BigQuery ships that interprets your schema and translates natural-language questions into SQL without moving data out of the warehouse, which is relevant to any contractor whose reporting layer already sits there.

Snowflake publishes MCP capability through its Cortex tooling, though the documentation has moved recently enough that it is worth navigating from the Snowflake docs homepage rather than trusting a link from an article, this one included. Warehouse connections tend to be the ones IT reviews most carefully, so budget time for that conversation.

MCP servers for construction document storage

Construction runs on documents more than it runs on anything else, and the file-storage category is comfortably the best covered on this list.

Dropbox offers connecting an assistant to your stored files, which is the simplest starting point on this whole list. Box publishes an official server aimed at enterprise content management, which matters for firms with retention and compliance requirements on project records. Microsoft publishes MCP references covering OneDrive and the wider Microsoft 365 surface, which is the relevant path for the large share of contractors running on SharePoint.

MCP servers for coordination and communication tools

Slack publishes covering channel and message access, useful mainly for reconstructing what was decided in a thread nobody minuted. Asana offers for task and project data, and monday.com publishes . Atlassian ships covering Jira and Confluence, which appears more in construction technology teams than in the field. Notion publishes for the teams keeping their standards and process documentation there.

None of these are construction tools, and every one of them is a place construction coordination actually happens.

Zapier publishes exposing thousands of connected applications through a single server. For a system with no MCP of its own but an existing Zapier integration, this is the pragmatic bridge, at the cost of an extra hop and a dependency on how well that Zapier integration was built.

Which MCP servers contractors should connect first

If you are starting from nothing, the order below gets you working connections without waiting on anybody’s roadmap.

Begin with file storage, whichever of SharePoint, Dropbox or Box holds your project documents. It is the highest-volume, lowest-risk connection available and it answers the largest share of everyday questions, which are mostly people trying to find what a document said.

Move next to the CRM, because pursuit data is the input that makes forward-looking staffing questions answerable at all, and because the servers in that category are the most mature on this list.

Add your data layer third, meaning Airtable, BigQuery or whatever holds the trackers and reports that accumulate around operations. This is where the questions that currently require somebody to build a pivot table start getting answered conversationally.

Leave communication tools until you have a specific reason, because connecting Slack sounds appealing and mostly produces summaries nobody asked for unless you already know the question you want it to answer.

Treat project management and HRIS as pending rather than absent, and ask the vendors directly rather than assuming. That conversation is worth having now even though today’s answer is mostly no.

How to evaluate an MCP server before connecting it

Four questions, ordered by how much trouble each one saves you later.

Who built it, and are they still maintaining it? Check the last commit or the last documentation update, because a community server nobody has touched in a year is a liability rather than a shortcut and the staleness is rarely advertised on the listing.

How much access does it ask for? A well-built server gives the assistant exactly the access the person using it already has, and nothing beyond that. If a server asks for more than that, sort it out before you install rather than after.

Is it read-only or can it write? Read access to a project record carries a very different risk profile from write access, and a surprising share of genuinely useful workflows need only the former, so start read-only wherever the option exists and add write access when something specific requires it.

Who owns it once it is connected? This one gets skipped. A connection nobody owns is a connection nobody reviews, and the review is what catches the access that made sense in March and does not now.

For discovery, the is the canonical index, and community marketplaces including Smithery, mcp.so, Glama and PulseMCP catalogue far more servers with varying quality signals. Listings on those marketplaces go stale, and a dead listing is common enough that it is worth verifying a server exists before planning around it.

What MCP adoption looks like for construction today

The connections available to a contractor today cluster around the business systems: your CRM, your file storage, your warehouse, the tools your office already runs on. Construction-specific servers are arriving as the industry adopts AI, and several are being built right now by vendors and by independent developers working against platform APIs.

So the practical move is to start where connections already exist and build the habit while the rest arrives. Working out who approves a connection, how much access it gets and who reviews it later takes an organisation longer than the technical setup does, and it is the same work whichever system you eventually point it at.

The post Top MCP servers for construction teams and what to connect first appeared first on 91¶¶Òõ.