If you’ve been watching the AI tooling space over the past year, you’ve probably noticed a lot of noise around MCP and what it means for how we work with tools like Revit. Community-built servers are popping up everywhere, and the enthusiasm is genuinely exciting. But one question keeps coming up: who do I trust?

That’s exactly the question we set out to answer with the Revit Public MCP Server.

A quick note before we dive in

This release is a Tech Preview, which means it’s available now for you to use and explore, but we’re actively developing it, gathering feedback, and iterating. It can be used in your workflow today, but you should expect things to evolve. We’d love to hear what’s working and what isn’t.

What Is MCP, Anyway?

MCP stands for Model Context Protocol, an open standard that lets AI assistants connect to external tools and data sources in a structured way. Think of it as a USB standard for AI: instead of every AI tool having to build its own custom integration with every application, MCP gives AI agents a common language to plug in and communicate. For Revit, that means an AI assistant like Claude can ask your model direct questions and get answers back, without you having to copy-paste data, export spreadsheets, or describe your model manually. The AI connects to Revit through the MCP server, and Revit responds.

What Is It, and Why Does It Matter?

The Revit Public MCP Server is Autodesk’s official, supported MCP server for Revit 2027. It gives AI assistants like Claude a direct and structured way to read and understand your Revit models. Think of it as a trusted bridge between your BIM data and the AI tools, you’re already starting to use day-to-day.

What are Autodesk MCP Servers? Autodesk MCP Servers are trusted tools made for agent-driven AI workflows in Design and Make. Built to Autodesk’s realiability standards, they act as safe bridges, letting AI assistants connect with Autodesk software, data, and tasks in a secure and dependable way.

What Is It, and Why Does It Matter?

The Revit Public MCP Server is Autodesk’s official, supported MCP server for Revit 2027. It gives AI assistants like Claude a direct and structured way to read and understand your Revit models. Think of it as a trusted bridge between your BIM data and the AI tools, you’re already starting to use day-to-day.

Getting Started

The Revit Public MCP Server ships as a separate addon for Revit 2027, and you’ll need Revit 2027 installed to use it. You can download it from accounts.autodesk.com under your Revit 2027 entitlements.

Once installed, Claude Desktop or Cursor is configured for you automatically! But for those technical folks, the configuration looks like this:

{

  “mcpServers”: {

    “revit”: {

      “command”: “C:\\Program Files\\Autodesk\\Revit 2027 MCP Server Technical Preview\\RevitMCPServer.exe”

    }

  }

}

The server communicates over stdio, which means it works with any LLM client that supports the MCP specification. Claude Desktop or Cursor is a great starting point, but the same configuration pattern applies to other MCP-compatible clients and tools.

What Can It Do Today?

The current release focuses on read-only access to your Revit model. That’s intentional. Before we open additional capabilities, we want to make sure the foundation is solid: queries are fast, results are accurate, and the experience is one you can trust.

Here’s exactly what’s in the box. Seven tools, each doing one thing well:

Get Running Revit Instances

The required first step in any session. This tool detects which Revit instances are currently running on your machine and returns the process ID and open document name for each.  Other tools take that process ID as its input,  but  the AI knows which model it’s talking to, even if you have multiple projects open at once.

Query Model

Query Model is the workhorse. This tool searches your model using multi-criteria filtering: category, family name, element name, level, bounding box, and parameter values with support for equals, contains, starts with, ends with, greater than, and less than comparisons. You can scope the search to the current view, a specific view, or the entire model. Results come back in two parts: a list of element IDs you can pass directly to other tools, and an analysis summary showing element counts broken down by category, level, and more. That analysis section is especially useful for narrowing down follow-up queries without having to pull full element data first.

Get Element Data

Once you have element IDs from a query, this tool retrieves the details. You control what comes back: basic info (name, category, family, type, level), element class, bounding box coordinates, key parameters, or the full set of all instance and type parameters. It’s how your AI assistant goes from “I found 47 structural columns” to telling you what each one is made of, where it sits, and what its parameters say.

Select Elements

Bridges AI analysis and your active Revit session. Pass it a list of element IDs and those elements become selected in Revit immediately, ready for you to inspect, tag, schedule, or modify. A direct handoff from AI output back to your hands.

Zoom to Elements

Takes things one step further than selecting. Rather than just selecting elements by ID, this tool zooms in and focuses the current view directly on them. When the AI has found something specific, this is how it brings you right to it on screen.

Open View

Activates a specific view in Revit by its ID. Useful when the AI needs to navigate you to the right floor plan, section, or 3D view as part of a larger workflow.

Export View

Exports views to image files (PNG, JPG, BMP, or TIFF), separate PDF files, or schedule data as CSV, with three export modes: a specific list of views by ID, the current active view, or the visible region as it appears on screen. Output goes to a path you specify, or defaults to your Documents folder. This is what enables AI-assisted documentation, rendering pipelines, and reporting — the AI can drive exports as one step in a larger task.

Together, these seven tools give your AI assistant a more complete picture of your model and a set of safe, read-only actions to work with, without ever touching your data in a destructive way.

The Strategy: A Base Layer You Can Build On

Here’s where it gets interesting for the AEC community. We see the Revit Public MCP Server as a foundation, not a ceiling.

Because it’s an official, tested server, it becomes a reliable base that you, your firm, or third-party developers can extend. You can run it alongside other Revit MCP servers, including community-built tools, firm-specific automation, and specialty plugins, and let each layer do what it does best. You’re not locked in, and developers don’t have to reinvent the wheel just to get reliable read access to a Revit model.

This is about choice and flexibility on the desktop. Your AI stack should work the way your practice works: mix-and-match, composable, and firmly in your control.

The Same Engine That Powers Autodesk Assistant

Around the same time as this Tech Preview, Autodesk is also launching the Autodesk Assistant Tech Preview, a new AI assistant built directly into Autodesk products. If you haven’t seen it yet, the Autodesk Assistant is designed to help you get answers, navigate tools, and work through tasks without leaving your application. It’s early days for the Assistant too, but the direction is clear: AI that understands your design context, not just generic prompts.

What the MCP server and the Assistant have in common is the underlying Revit model intelligence. The same technology that lets the Assistant understand your Revit context is what we’re exposing through the MCP server for use in your own AI desktop workflows.

The practical difference right now is that the Autodesk Assistant operates in a more controlled environment and can do more within that context out of the box. The MCP server gives you something different: the ability to bring that same intelligence into whichever AI client you choose, on your terms. They’re complementary.

What’s Next

We’re actively working on expanding these capabilities. Future tools, giving AI assistants the ability to create, modify, and manage Revit elements, are part of where we’re headed. We plan to release those through a dedicated write server, keeping read and write concerns cleanly separated so you can control what your AI assistant is allowed to do in your model.

The goal is straightforward: a trusted, official source of Revit MCP tools that users can operate for their workflows and that developers can build on and extend without starting from scratch every time.

We’ll have more to share as things mature. In the meantime, grab Revit 2027, our MCP server addon, set it up for your environment, and start asking your models better questions. 

Autodesk Revit: BIM software to design and make anything

Start a free trial

The post Introducing the Revit Public MCP Server: A Trusted Foundation for AI-Powered Workflows appeared first on AEC Tech Drop.

Revit 2027.1 continues the 2027 release focus on connected, higher-performance, and more predictable BIM workflows. For advanced users, the value of this release is in how these updates strengthen your everyday workflows: documenting design intent, coordinating cloud-connected models, validating analysis results, and preparing models for fabrication.

This point release introduces a pack of enhancements across architecture, structure, and MEP workflows, with a practical focus on reducing friction, improving control, and preserving model fidelity.

Architecture and Core Enhancements

Revit 2027.1 improves the day-to-day modeling and documentation experience with refinements that support visual fidelity, connected workflows, annotation quality, and AI-assisted productivity.

Autodesk Assistant for Revit continues to mature as a natural language interface inside the Revit environment. Supported assistant actions are more reliable across common model interaction and documentation tasks, including applying color overrides to elements, tagging elements without duplicates, and refining schedule data through filters.

Assistant activity is now fully traceable in Revit. Every MCP tool logs its execution in the Revit journal, including start time, completion status, and errors. Changes made through MCP tools are also labeled with an AI prefix in the Undo menu, making automated actions easier to identify and review.

Additional refinements include a Stop button and sorting capabilities in the Prompt Library. Together, these updates help BIM managers and project teams audit Assistant activity, troubleshoot issues, interrupt operations when needed, and reuse prompts more consistently across model interrogation and documentation workflows.

Accelerated Views support Gradient and Sky Background. The support of 3D View Backgrounds provides teams with greater consistency when using accelerated graphics for 3D navigation, design review, and coordination workflows, where both view fidelity and performance matter.

Forma Connected Clients support smoother Worksharing. Multiple users can now work with the same Revit cloud model and reload scenarios without requiring unnecessary permissions. This helps preserve connected context while reducing administrative friction during shared model work.

Rotate Fill Pattern Definitions. You can now rotate custom fill patterns in the Manage Fill Patterns dialog and save them as new rotated pattern types. For teams managing graphic standards through templates, this makes it easier to edit pattern definitions across documentation sets.

Structural Design, Analysis, and Fabrication Workflows

The structural enhancements focus on faster analytical model creation, clearer results review, improved reinforcement modeling, and more reliable steel fabrication workflows.

Create faster Analytical Elements at Grids. Model analytical columns at grid intersections, analytical walls along grids between intersections, and analytical beams along grids between columns. This aligns the creation of analytical models with the grid logic already used to model structural models. The result is faster setup, fewer repetitive placement steps, and better consistency.

Modernized Analysis Results Exploration Panel. The updated experience includes preset definitions for commonly used result sets, more convenient result type selection, display settings tailored to selected result types and objects, and quick insights into extreme result values. Together, these improvements make it easier to move from analysis output to model-based interpretation, helping engineers identify critical results faster and review structural behavior with greater clarity.

Place Standard Rebar Shapes in 3D Views. Apply shape-driven rebar directly in 3D views using familiar placement methods from 2D, including Expand to Host and By Two Points. Rebar placement responds to highlighted concrete host faces, placement plane options, cursor position, and view orientation. Users can place longitudinal bars, stirrups, and path shape distributions more intuitively in 3D. This is especially valuable for complex concrete conditions where rebar placement requires repeated validation in 3D.

Improved documentation for steel detailing.  New annotation enhancements help preserve the reliability of documentation through steel detailing and fabrication.

• Openings on steel columns are kept in place when applying steel connections.
• Hidden lines from member webs break correctly by Geometry or Steel Connection Cuts.
• Dimensions created in the Design phase are also preserved when applying Steel Connections.

The Steel Connections dialogs now support high-DPIimages.  The reference image in Steel Connections dialogs now scales properly on high-resolution displays, helping connection graphics remain legible across workstation setups.

Steel framing extensions controls. The Shape-handle extensions for steel framing elements now work when Steel Connections and shortened member ends are applied. This allows detailers to extend members beyond the steel modifier location, providing more direct control over the final geometry after connection logic has been applied.

MEP Design and Fabrication Workflows

For MEP detailers, Revit 2027.1 improves in-canvas modeling controls and adds more direct duct sizing support.

In-Canvas Connector Controls. This enhancement provides MEP detailers with clearer connector information during fabrication, part placement, and selection. Connector controls can now appear in-canvas and display connector Size, Type, and Number. Visibility can be toggled from the Analyze tab. This helps users understand connector behavior during modeling, reducing the need to inspect properties after placement and helping to avoid incorrect connection assumptions.

MEP Sizing Calculator. This release introduces a focused workflow for duct sizing that supports both design and fabrication workflows. Users can size ducts by Friction, Velocity, or both; apply tolerances with sliders; filter results by minimum and maximum sizes; review acceptable sizes in a table; and apply a selected size directly to the selected duct. This supports a more iterative and informed sizing workflow inside Revit, reducing reliance on disconnected checks or manual trial-and-error resizing. Note that pipe systems are not yet supported in the MEP Sizing Calculator.

A Practical Update for Advanced Users

Revit 2027.1 is a production-focused release, improving the details that matter in real projects: more controlled AI-assisted workflows, stronger graphics parity, smoother connected cloud models, faster structural analytical modeling, clearer analysis review, more intuitive rebar placement, better steel fabrication continuity, and more direct MEP connector and sizing workflows.

For full documentation on Revit 2027.1, refer to this link. To see what’s coming next, visit our Public Roadmap for upcoming feature plans.

Get started with Revit 2027.1 through the Autodesk Access application on your desktop. And if you’re not yet a subscriber, be sure to check out a free trial of Revit 2027.

Happy Revit-ing!

Autodesk Revit: BIM software to design and make anything

Start a free trial

The post What’s New in Revit 2027.1: More Control Across Design, Analysis, and Fabrication appeared first on AEC Tech Drop.

For two decades, the AECO industry has become exceptionally good at generating data. Models are richer. Collaboration is more connected. Common data environments are more mature. Yet at project handover, something predictable happens: most of that data fails to serve the people who need it for the next 30 to 70 years.

Design intelligence rarely becomes operational intelligence. Autodesk’s newest solution for managing handover data – the Asset Information Connector (AIC) – is built to change that dynamic.

The Real Cost of Handover

In our blog series on the evolution of CDEs, we highlighted a staggering statistic: 96% of engineering and construction data goes unused. [1] Some of that loss is cultural. Some is contractual. But much of it is technical. Data gets trapped in files, lost between project phases, and re-entered manually into systems that were never designed to speak to each other losing its connection to the original data source.

Nowhere is this more visible than at a project’s handover phase. After years of coordinated design and construction, owners often receive deliverables that are technically complete but operationally unusable. Equipment attributes are inconsistently named or populated. Specifications are incomplete. Warranty and commissioning information is disconnected from the assets it describes. Operations teams spend months re-keying data into CMMS platforms. Errors multiply. Trust erodes.

Owners are no longer willing to accept long handover cycles and reams of disconnected data. In today’s digital project delivery world, structured information deliverables are becoming operational requirements, not aspirational goals.

Autodesk Datum provides the enterprise framework to define and govern those requirements: class libraries, validation, change tracking, and progressive assurance across the asset lifecycle. But governance alone is not enough. The missing piece has been creating the right data correctly at the source.

That is where AIC comes in.

What the Asset Information Connector Does

AIC sits between model authoring tools and enterprise asset information systems like Autodesk Datum. It enables project teams to register design objects as operational assets, map authoring tool properties to downstream data schemas, validate asset data against structured information requirements, and resolve gaps during design rather than at closeout.

Consider a mechanical engineer placing an air handling unit in Autodesk Revit. That object carries geometry, performance data, and specification properties. But the Owner’s facilities team needs that same asset described in a completely different way. The Owner’s schema needs to be one aligned with the data standards they’ve defined in Datum, their CMMS, and their organizational requirements. Today, that translation typically happens manually and very late in the project lifecycle.

With AIC, mapping relationships between source properties and target attributes in Datum are configured once. Information requirements, drawn from Datum’s class libraries and validation rules, define what is expected for each asset class. Validation runs in real time. Instead of discovering missing data six months after handover, teams address gaps while the model is still active.

AIC and Autodesk Datum: Closing the Data Loop

In our post on Autodesk Datum, we said the industry needs to focus on making the “I” in BIM more robust. Datum addresses this at the enterprise level, governing class structures, validation rules, standards, and lifecycle tracking. It’s the engine that keeps asset data structured, validated, and trusted.

AIC operationalizes those standards inside the authoring environment.

For Datum customers, information requirements flow directly into AIC, allowing designers to work against owner-defined standards without leaving their native tools. A Revit user interacts with AIC as a natural extension of their design workflow. They register assets, populate properties against Datum’s standards, and resolve validation flags as they go.

Datum defines what good asset data looks like. AIC ensures that good data gets created at the source. Together, they close the loop between information requirements and information delivery.

This architecture is further supported by the AEC Data Model, which enables granular, object-level data access across Autodesk platforms. AIC participates in that broader ecosystem, with Datum at its core, contributing to a shift from file-based deliverables toward structured, interoperable asset data.

Configuration Over Integration

AIC is intentionally designed as a configurable connector, not a hardcoded point-to-point integration. Real-world portfolios are messy and varied, and the information requirements, target schemas, and systems of record vary enormously across segments, geographies, and organizational maturity levels.

For Datum customers, class libraries and requirements flow directly into AIC. But requirements can also come from other sources: Excel-defined data standards, bespoke organizational schemas, or third-party data platforms. Property mappings can target Datum’s schema or any other downstream system. As tools and systems evolve, AIC adapts through configuration rather than redevelopment.

From Event-Based Handover to Continuous Asset Identity

Traditional handover treats asset data as a packaged deliverable compiled at project close out. AIC reframes handover as a continuous process that can begin as soon as an asset is created.

Assets are registered early in design, establishing a persistent identity. As the project progresses, design properties are validated against Datum’s information requirements. Construction and installation data accumulate against that same identity. By the time handover occurs, asset information is already structured, validated against Datum’s standards, and governed. It’s not assembled from scratch.

The result is a continuous digital thread that supports operations from day one. Re-keying is reduced. CMMS onboarding accelerates. Trust in asset information increases over the lifecycle. This is a fundamental shift in how the industry thinks about asset data. Asset data stops being a deliverable and starts being a living record.

What’s Ahead

AIC is currently available in beta to Datum customers with desktop support in Revit. Development is underway for Civil 3D and Plant 3D connectors, with cloud-based workflows expanding support for asset data that originates beyond traditional authoring tools.

Integration with Autodesk Datum continues to deepen, with tighter alignment to Datum’s class libraries, validation engines, and change tracking so that AIC operates as a true extension of the Datum ecosystem within the authoring environment. For teams earlier in their data maturity journey, AIC provides a structured on-ramp to Datum’s enterprise capabilities.

The Inflection Point

The AECO industry is moving from file-based collaboration to granular, object-level data management. Asset information can no longer be treated as a byproduct of design. It must be treated as a lifecycle asset in its own right. AIC accelerates that transition so asset data created during design arrives at handover validated, structured, and operationally ready.

Better operational outcomes begin with better asset information. And better asset information starts where the data is created.

[1] FMI Corporation, Big Data = Big Questions for the Engineering and Construction Industry, 2018. Available at: https://fmicorp.com/uploads/media/FMI_BigDataReport.pdf

Connecting data across the asset lifecycle

Explore Autodesk Datum

The post Bridging the Gap Between Design Data and Asset Operations with Datum and the Asset Information Connector appeared first on AEC Tech Drop.

Uploading project files sounds simple. Open a folder, move the files, and you are done.

Civil infrastructure projects rarely work that way.

Most projects include XREFs, DREFs, XML files, templates, source drawings, and other linked data. If files are uploaded without those relationships, something important can break.

Autodesk Forma gives you a few different ways to upload project data. Each one works best in a specific situation. The key is knowing which method to use before you start.

1. Drag and drop for quick file uploads

If you just need to upload a single file, drag and drop is the fastest option.

Open Forma Data Management in the browser, then drag a file from Windows Explorer into the correct folder.

This works well for quick, one-off uploads. For example, sharing a file for review or adding a document to a project.

There are a few limits to keep in mind. This method works at the file level only. It does not bring reference files with it. Dragging a full folder into Forma would also result in an error. If you are looking to add folders and its contents you would want to use Desktop Connector.

If references are not part of the workflow, this method keeps things simple.If you just need to upload a single file, drag and drop is the fastest option.

Open Forma Data Management in the browser, then drag a file from Windows Explorer into the correct folder.

This works well for quick, one-off uploads. For example, sharing a file for review or adding a document to a project.

There are a few limits to keep in mind. This method works at the file level only. It does not bring reference files with it. Dragging a full folder into Forma would also result in an error. If you are looking to add folders and its contents you would want to use Desktop Connector.

If references are not part of the workflow, this method keeps things simple.

2. Use Desktop Connector when references matter

When you are working with actual project data, references usually matter.

Desktop Connector includes an Upload with References option. You select your local project folder, choose a destination in Forma, and let the tool scan the project before uploading.

That scan is where this workflow becomes useful. It highlights missing or broken references before anything is uploaded. You can then resolve those issues by pointing to the correct XREFs, DREFs, XML files, templates, or source drawings.

Once everything is resolved, the upload continues with those relationships intact.

This approach helps avoid a common problem where files upload successfully but do not behave correctly afterward.

It is also worth noting that naming standards set up in Forma Data Management are reflected in the local Forma Data Management drive through Desktop Connector. Files uploaded through either the browser or the local drive follow the naming rules for that folder.

While Desktop Connector is a good fit for active project work, it is not intended to handle large scale bulk migrations.

3. Bulk upload when references are not critical

If you need to upload a large number of files and references are not required, the Bulk Upload Tool may be a better fit.

Select Files without References, choose your local source folder and target Forma folder, run validation, and upload.

This method skips reference checking entirely. It simply moves files from one location to another.

Because of that, it can be faster, especially for larger uploads. It is a practical choice for standalone files or datasets that do not rely on linked content.

The Bulk Upload Tool is available through the Forma Data Management help page.

4. Bulk upload with references for full project moves

For larger uploads where references need to be preserved, there is one additional step.

You need a Reference Relationship JSON file.

You can create this file using the Drawing Integrity & Migration Tool for Forma Data Management. The tool scans your project, checks for missing references, and flags long path issues.

If missing references are found, you resolve them directly in the tool by selecting the correct folders. Long path issues are identified as informational items so you can review them as needed.

Once the project is cleaned up, export the Reference Relationship JSON file. A CSV report can also be exported if you need a record of the scan.

Next, open the Bulk Upload Tool and select Files with References. Import the JSON file, run validation, and upload.

The Bulk Upload Tool uses the JSON file to map local files to their destination in Forma and preserve reference relationships during upload.

While you can also upload directly from the Drawing Integrity & Migration Tool by selecting Upload, this option is better suited for smaller uploads. For large projects, we recommend using the Bulk Upload Tool because uploads from the Drawing Integrity & Migration Tool run through Desktop Connector, which is not intended for large migrations.

One important caution: do not upload the same files from the Drawing Integrity & Migration Tool and the Bulk Upload Tool at the same time. This can create overwrite conflicts.

Naming standards

Naming standards configured in Forma Data Management are applied automatically. Files uploaded through the browser or Desktop Connector follow the rules defined for that folder.

Use caution when turning on naming standards for folders that already contain referenced files, such as data shortcuts. The naming standards workflow does not exclude files that should not be renamed. If data shortcuts are automatically renamed, links could break.

If your workflows rely on data shortcuts, you will need Forma Design Collaboration. Forma Data Management alone does not include this capability.

Choosing the right method

Each method solves a different problem.

• Use drag and drop for quick, single file uploads
• Use Desktop Connector when references need to be maintained
• Use bulk upload without references for speed and simplicity
• Use bulk upload with a JSON file for larger, reference aware migrations

A small decision at the start can prevent a lot of clean up later.

Start with the reference question

Uploading files is more than a setup step. It determines whether your data stays connected and usable once it is in Forma.

Start by asking a simple question. Do the references need to stay intact?

If they do, choose a method that preserves them. If they do not, use the fastest path available.

That balance is what keeps projects moving without rework.

Plan your move to the cloud with more confidence

See how Autodesk experts walk through civil cloud workflows, including Desktop Connector, upload best practices, reference management, and troubleshooting tools that help maintain project health. Watch the webinar.

The post Four Ways to Upload Civil Project Files to Forma appeared first on AEC Tech Drop.

A wall is rarely just a wall. Walls define space, filter between inside and outside, provide structural support, and shape the composition and design of a building. In Revit, walls also manage enclosure, host openings, express material intent, and form the basis of construction documentation.

Our goal for Revit Architecture is to help architects design with less friction. And with wall workflows, we saw friction between intent and output, and an opportunity to make a meaningful improvement to architects’ everyday work.

For Revit 2027, that meant focusing on two connected needs: supporting multi-wall workflows and making wall joins accurate enough to document from directly.

Supporting multi-wall workflows

As projects grow more complex, many teams model wall layers as separate but coordinated elements. This better reflects how buildings are designed across disciplines and assembled on site. In user surveys, we’ve seen this approach to modelling increase steadily.

Architects do not think of walls as single objects. They think of them as systems: structure, substrate, air gap, finish, cladding, and everything in between. Revit 2027 is designed to support that layered way of working, helping separate wall elements behave more like coordinated parts of one assembly.

Accurate wall joins without manual intervention

In a multi-wall model, join behavior is critical. Finish layers need to stop, wrap, or continue predictably. When the model cannot resolve these conditions correctly, teams often turn to filled regions, manual overlays, or one-off fixes to communicate intent.

Those workarounds may solve the drawing in the moment, but they also create distance between the model and the documentation. Revit 2027 reduces that gap by making joins more accurate and consistent at scale, rather than manual corrections at each condition.

A more connected wall workflow

Revit 2027 builds on several recent wall enhancements to better support this layered way of working across a complete workflow: from setup, to creation, to coordination, to documentation.

1. Define how wall layers join

In earlier versions of Revit, every compound element required a Core layer. Because Core layers always took priority at joins, they could override the behavior teams wanted in layered wall assemblies.

Revit 2026 removed that requirement and expands layer priority controls, giving users more flexibility to decide which layers have priority join order. This creates cleaner automatic joins and less manual correction across the model.

2. Create walls faster

Once the wall assembly is defined, Revit 2026 also made it faster and easier to create walls.

With Place by Room, users can generate finish walls around rooms in a single click. When more precision is needed, Place by Segment lets users create finish walls only where specific conditions are required. They can select individual walls or columns, whether those elements are room-bounding or not, and whether they are in the host model or a linked model.

Users can also flip wall orientation during placement, helping ensure finishes face the correct direction from the start.

3. Keep finish walls coordinated as the design changes

Creating finish walls is only useful if they stay coordinated as the project evolves. New to Revit 2027, with Hosted Walls, walls can now be hosted to other walls. When the host wall moves, rotates, or changes cross-section, the hosted finish walls follow automatically. Instead of relying on locked constraints, which can introduce errors and limitations, Hosted Walls are designed specifically to keep related wall elements connected.

4. Check and document with confidence

Hosted walls also makes it easier for Teams also need to verify and document them. Hosted relationships are exposed through instance parameters, including Hosted and Offset from Host. This allows teams to use view filters to visually check which finish walls are hosted and whether offsets are applied correctly.Hosted walls also makes it easier for Teams also need to verify and document them. Hosted relationships are exposed through instance parameters, including Hosted and Offset from Host. This allows teams to use view filters to visually check which finish walls are hosted and whether offsets are applied correctly.

Hosted walls can also be scheduled, making it easier to review, manage, and document finish wall conditions across a project.

Small improvements, compounded across the project

When we prioritize development in Revit, we look for changes that have the greatest impact on everyday practice. Wall workflows are among the most-used in Revit: architects create, edit, join, coordinate, document, and revise walls throughout the life of a project. Improvements here multiply quickly.

Revit 2027 and recent releases move wall modeling closer to the way architects think about real buildings — not as isolated objects, but as layered systems that need to stay coordinated from model to documentation. Together, these improvements make one of Revit’s most fundamental building elements more predictable, more scalable, and more aligned with how architects actually work.

For architects, the outcome is straightforward: fewer manual fixes, fewer drafting workarounds, and more confidence that the model represents the building as intended.

Autodesk Revit: BIM software to design and make anything

Start a free trial

The post From Wall Objects to Wall Systems: Revit 2027 Supports the Way Architects Model Real Buildings appeared first on AEC Tech Drop.

Across every industry, we’re seeing a fundamental shift in how people work with AI. Users are moving from hands-on task execution to higher-level goal setting and decision-making. Instead of driving every command, they define intent, constraints, and desired outcomes. This means users no longer need to focus on “how”; they can focus on what matters most: “what”.

For AEC, this shift creates a powerful opportunity. It has the potential to expand what’s possible, freeing teams to increase capacity, think bigger, and push the boundaries of what our industry can achieve.

At Autodesk, we’re bringing this shift directly into your daily workflows.

Autodesk Assistant

Autodesk Assistant is the AI interface for Design and Make.  Whether you need quick answers, want to explore your work, or speed up repetitive tasks, it’s designed to help you work more efficiently while supporting your creative process.

It represents the next major step in Autodesk’s AI evolution, a conversational, generative AI experience that works within the tools you use every day. By bringing AI directly into your workflow, Assistant helps remove friction, simplify tedious tasks, and enables faster, more informed decisions. Think of it as an intuitive entry point into AI, one that enhances how you design, without changing how you think.

Autodesk Assistant in Revit – Available in Tech Preview

With Autodesk Assistant in Revit now available as a Tech Preview, AI is embedded directly into the design environment you use every day, providing early access to a defined set of supported workflows that will continue to improve over time.

Autodesk Assistant introduces a new, conversational way to interact with Revit. Instead of navigating menus or searching for documentation, you can:

• Ask questions about Revit features
• Query and explore your model
• Take action through natural language prompts such as “Create a door schedule sorted by level” or “Create a floor plan for the level L1 and name it “L1-AI”
• Receive personalized insights such as the new “Numbering” tool, based on your activities within the documentation workflow.

All through a simple chat interface embedded directly in Revit.

Get instant help from trusted sources

Autodesk Assistant provides contextual answers based on Autodesk’s official documentation, helping you quickly understand tools and workflows without leaving Revit. Whether you’re learning something new or just need a refresher, it gives you the confidence to keep moving. For example, you can ask, “Guide me through setting up sheets and views” and receive clear, step-by-step guidance, best practice and the source links.

Explore and understand your model

You can ask Autodesk Assistant about your current model, design, or project—and get answers right when you need them. Instead of manually searching or counting elements, let Assistant do the work for you. It can analyze your model and deliver context-aware answers, so you can stay focused on design.

Ask questions like:

• “How many structural columns have their Base Level set to L2?”
• “In the ‘L2’ view, count all door and window tags.”
• “Check whether all views on sheets A100–A106 have a view template assigned.”

Turn intent into action

Move beyond questions—turn intent into action.

From modifying elements to generating documentation, Autodesk Assistant helps translate what you want to do into real results.

In the example below, an AI-driven workflow generates a Level 2 floor plan, refines it with the appropriate view template, and automatically tags rooms. That setup is then reused to create equivalent plans for Levels 3 and 4, followed by automated sheet creation, naming, layout, and final PDF export.

Learn and improve with Insights

Autodesk Assistant doesn’t just respond—it helps you continuously improve how you work.

With My Insights, you’ll receive personalized, context-aware suggestions such as:

• Shortcuts to speed up repetitive and tedious tasks
• Features you might not know about
• Best practices based on your workflow

These insights are dynamically triggered based on your usage, helping you build better habits, discover new capabilities, and work more efficiently over time.

Built for real workflows with MCP

Under the hood, Autodesk Assistant is powered by Model Context Protocol (MCP)—enabling more reliable, contextual, and actionable responses.

With MCP, Autodesk Assistant understands your model more deeply and supports real-world workflows such as:

• Model Query—understanding and analyzing Revit model
• Export—project deliverable generation
• Sheet Management & Documentation—organizing project deliverables
• Room Management—architectural space planning and coordination
• Schedules & Data Management—project data organization and reporting
• Element Operations & Manipulation—direct element control and modification

Together, these workflows enable Autodesk Assistant to move beyond answering questions, becoming an active support in your design process.

Trust Principle in Autodesk Assistant

Autodesk is committed to responsible, ethical, and secure AI development, deployment, and use. We follow strict governance and “privacy by design” principles to protect customer data and intellectual property, ensuring data is used only for its intended purpose and shared in limited, approved ways.

Autodesk Assistant uses:

• Your conversation — The questions you ask during your session
• Autodesk product documentation — Official help content from help.autodesk.com
• Your work — In some products, context from your model or design when you ask questions about your work

Your Prompt Library and Chat History are stored in the cloud and linked to your Autodesk account. None of this data, nor any customer privacy data, is used to train LLM models.

 Assistant may connect to MCP servers to access additional tools and data sources. These servers are provided by Autodesk and operate according to Autodesk’s trust and privacy standards.

For more information, please refer to: https://help.autodesk.com/view/RVT/2027/ENU/?guid=AA_Trust_Privacy

Looking ahead

This is just the beginning.

AI in Revit isn’t only about solving pain points. It’s about creating new possibilities. It’s not just about the pain relievers, but the gain creators. AI has the potential to expand horizons in how you design and deliver projects.

Our goal is to enhance every part of your design and engineering workflows: the creative, complex work that represents the real value you bring to your projects.

As Autodesk Assistant continues to evolve, we’re focused on helping you do more of what matters most: designing better, moving faster, and pushing the boundaries of what’s possible.

The current tech preview of Autodesk Assistant in Revit is intentionally designed to support a focused set of workflows, rather than every Revit task. We’re using this early stage to gather feedback, learn from real-world use, and continuously improve the experience.

We invite you to join our community forum to explore what’s possible today, share your feedback, and partner with us as we shape the future of AI in Revit.

Autodesk Revit: BIM software to design and make anything

Start a free trial

The post Autodesk Assistant in Revit – Tech Preview: Your AI Support to Create More and Work Smarter appeared first on AEC Tech Drop.