Palantir Release Notes

CoProcess user-defined functions (UDFs) are now supported in Pipeline Builder. A keyed CoProcess UDF allows users to define custom stateful logic for processing events from two different streams and merging them into a single output stream.

A keyed CoProcess UDF takes a separate stream on each of its left and right inputs.

Rows can be processed and emitted from either stream, which allows sophisticated real-time pipelines that go beyond standard join patterns. As with any stateful UDF, keyed CoProcess UDFs can be imported into a pipeline and used like any other transform.

Configure a keyed CoProcess UDF by mapping the columns of each input to the UDF.

What's new

With keyed CoProcess UDFs, you can:

• Maintain custom state across both input streams. State is shared between the two inputs rather than scoped to a single stream.
• Emit output rows from either stream independently. Neither stream has to wait on the other to produce output.
• Implement complex matching logic that standard joins cannot express.

Example use cases

• Flight tracking: Join a stream of live aircraft positions with flight plan schedule updates to detect route deviations in real time.
• Supply chain: Join shipment tracking events with inventory updates to suggest restocking before a warehouse runs out.
• Wildfire alerting: Join satellite thermal detections with ground-level weather data to escalate alerts when hotspots coincide with high-risk conditions.

Share your feedback

As we continue to add features to Pipeline Builder, we want to hear about your experiences and welcome your feedback. Share your thoughts with Palantir Support channels or our Developer Community using the pipeline-builder tag.

Features

Ontology building / Workflow Lineage

Workflow Lineage now supports Vertex resources. Both Vertex graphs and Vertex graph templates appear as nodes on the graph and can be found using search. You can navigate to these resources directly from Workflow Lineage.

Enhancements

AI Platform (AIP) / AI FDE

AI FDE now includes a button in the chat outline header that opens resources from your current conversation in a Workflow Lineage graph. This provides quick access to Workflow Lineage directly from the outline panel without needing to use the keyboard shortcut.

Ontology building / Ontology Management

Ontology Manager now displays link type constraints on interface pages in a single-sided format, showing only the target entity rather than repeating the current interface name on every row. Target names are now clickable links that navigate directly to the corresponding interface or object type page. This applies to the

Links

tab, the interface overview links section, and the interface extension preview. Previously, both sides of the constraint were displayed on each row and neither was clickable, requiring users to search for the target entity by name.

Security & governance / Checkpoints

The checkpoint record review interface now includes an interaction RID filter in the filter bar. Users can paste an interaction RID to filter records directly, with options to remove individual filters or clear all at once. This filter was previously only accessible via URL parameter.

Security & governance / Sensitive Data Scanner

Sensitive Data Scanner now allows you to exclude a resource directly from a recurring scan's results page. Each result row includes an action to navigate to the scan configuration's resource selection step, where the resource is pre-staged for exclusion. The exclusion is not applied automatically — you must review and save the updated configuration before it takes effect.

Use case development / Workshop

Workshop now resolves object set parameters passed to bidirectional iframe widgets more quickly. Updates to an object set in Workshop reach the embedded iframe more promptly without any change in behavior.

Fixes

Ontology building / Ontology Management

Ontology Manager no longer incorrectly blocks moving ontology resources into projects that have no maximum classification constraint. Previously, migrating an entity into such a project could produce a false constraint violation, preventing the migration from proceeding. Projects with explicit classification constraints continue to block real violations as expected, and metadata or query failures remain safely blocked.

Summary metrics

The new object timeline feature provides observability into actions performed on an object. See edits performed by agents or by manual action along with full attribution for each one. Monitor token usage, runtime, and agentic coverage to find where to optimize. Trace any edit back to the execution that made it.

Object timeline showing edits to an object, with attribution, token usage, runtime, and change costs.

View a demonstration of object timeline on the Palantir Developers YouTube channel.

The object's summary metrics give you a starting point for optimization:

• Total token usage: The number of tokens consumed across all executions.
• Total runtime: The length of time from the first to the last execution.
• Waiting time: The amount of time spent waiting for human input, shown in the same cell as total runtime.
• Agentic coverage: How much of the object's history was driven by agents versus humans.

Explore the timeline

Each row represents an agent, human, or resource. Bars show each execution, and diamond markers show each edit made to the object in the ontology through an action. Together, the timeline shows how each has worked on the same object over time, including where activity overlapped or one picked up from another.

Select any bar or diamond to open a side panel with the metrics for that execution and the edits it made to the object.

Optimize your workflow

• Token usage per step lets you quickly identify which steps consume the most, so you know where to focus, whether to refine your prompt or switch models. Select any diamond on the timeline to view detailed metrics.
  • Easily spot that most of the token usage in this use case comes from the agent that creates a new campaign. At a glance, you can see where to prioritize optimization, whether that is refining the prompt, switching models, or reducing token usage another way.
• Time breakdown helps you spot where you are losing time in a run, so you can identify manual steps to automate and reduce overall workflow duration.

This notional example shows that 98 of the time is spent waiting on human input for the final review. Knowing this metric can help you understand where you can intervene to speed up the runtime.

The notional example above shows that 98% of the time is spent waiting on human input for the final review. Knowing this metric can help you understand where you can intervene to speed up the runtime.

Access object timeline from Autopilot or Object Explorer

You can access object timeline from Autopilot, as well as from Object Explorer if edit history is turned on.

Access the object timeline from Autopilot's graph view or from the More menu in Object Explorer.

Share your feedback

As we continue to add features to Autopilot, we want to hear about your experiences and welcome your feedback. Share your thoughts with Palantir Support channels or our Developer Community using the aip-autopilot tag.

Features

Data connectivity & integration / Build Schedules

Schedules now support overlapping runs. By default, a schedule does not start a new run while another run of the same schedule is in progress. Enable the Allow overlapping runs setting to allow runs to overlap. This can be used to reduce latency in a pipeline with a long sequence of jobs by allowing a new run to begin processing new input data before an earlier run finishes, or to use one schedule to keep multiple datasets up to date without requiring a separate schedule for each dataset.

Enhancements

Data connectivity & integration / Scheduler

Schedules now support overlapping runs. By default, a schedule does not start a new run while another run of the same schedule is in progress. Enable the Allow overlapping runs setting to allow runs to overlap. This can be used to reduce latency in a pipeline with a long sequence of jobs by allowing a new run to begin processing new input data before an earlier run finishes, or to use one schedule to keep multiple datasets up to date without requiring a separate schedule for each dataset.

Fixes

AI Platform (AIP) / AI FDE

AI FDE now correctly classifies terminal commands that include 2>/dev/null or 2>&1 stderr redirects. Previously, these common shell patterns caused commands to be rejected as unrecognized, requiring manual approval. Commands with these redirects are now classified and auto-approved according to their normal approval settings.

AI Platform (AIP) / AIP Analyst

AIP Analyst now accurately displays the pages that were actually returned when using the media read tool, rather than showing the originally requested page range. When a document read is truncated due to character limits, the tool card reflects only the pages that were successfully parsed and a warning indicator notifies users that some pages were not included. The model can then be prompted to read the remaining pages using the updated range.

Ontology building / Ontology Management

Ontology Manager now correctly allows changing the type of a mapped struct field (for example, from String to Timestamp) on object types backed by a direct datasource. Previously, a compatibility check incorrectly blocked valid type changes by validating against a synthesized schema field that did not exist in the datasource. The backing-field name now remains populated and the Confirm button is enabled as expected when making valid type changes.

Features

Ontology building / Workflow Lineage

You can now move multiple Compass resources to other projects or folders in bulk from Workflow Lineage. Before the move is executed, a preview displays a breakdown of which resources will be moved and which will be skipped, along with the reason each skipped resource cannot be moved.

Enhancements

Ontology building / Ontology Management

Ontology Manager now includes a
Remove unused parameters
button on the
Parameters
tab when defining rules. This button removes all parameters tagged as "Unused" in one click, including those inside sections. The button only appears when there are unused parameters available to remove.

Select models from DeepSeek, Z.ai, and Moonshot AI are now available in AIP through AWS Bedrock on non-georestricted, US, EU, UK, and JP commercial enrollments.

Model overviews

DeepSeek V3.2 is DeepSeek's mixture-of-experts reasoning model optimized for reasoning, coding, and instruction following. It supports client-side tool use and a 164,000-token context window with up to 8,000 output tokens.

GLM 5 is Z.ai's multimodal reasoning model, designed for coding, multilingual understanding, and agentic workflows. It supports text and image inputs, client-side tool use, and a 256,000-token context window with up to 16,000 output tokens.

Kimi 2.5 is Moonshot AI's frontier-class reasoning model, optimized for complex systems engineering and long-horizon agentic tasks. It supports advanced reasoning, mathematics, coding, and client-side tool use, with a 200,000-token context window and up to 128,000 output tokens.

Getting started

To use these models:

• Confirm that your enrollment administrator has enabled the relevant model family.
• Review token costs and pricing.
• See the complete list of models available in AIP.

Your feedback matters

We want to hear about your experiences using language models in the Palantir platform and welcome your feedback. Share your thoughts with Palantir Support channels or on our Developer Community using the language-model-service tag.

Iterate across the whole application locally

As of the week of August 3, SuperRepo is now available in beta, bringing a pro-code way to build complex full-stack applications anchored around the Ontology. A SuperRepo is a single monorepo that holds your Ontology definitions, your functions, and your React application together, so you can develop, build, and deploy them as one versioned artifact.

With SuperRepo, you ship a feature that spans the Ontology, a function, and a frontend from one repository, in a single edit-and-preview cycle.

The Foundry CLI runs your SuperRepo on your own machine so you can change the Ontology, your functions, and your application together:

• Ontology-as-code: Declare object types, links, interfaces, and actions in TypeScript. Your code definitions are the source of truth, and they materialize as real entities on your enrollment when your product is deployed.
• Embedded Ontology preview: Local servers reproduce the Ontology's behavior on your machine. Function-backed actions route through the embedded Ontology, and functions run in language-specific preview runtimes. Seed data files populate a fresh local database each time the server starts.
• Locally generated Ontology SDK: SDK bindings are generated from your Ontology-as-code definitions and regenerated automatically whenever those definitions change, then consumed directly by your functions and your Ontology SDK application. You can extend the Ontology and use the new types in a single loop, with no SDK republish in between.

Deploy programmatically to any enrollment

A SuperRepo compiles natively into a Marketplace product: a self-contained, reproducible, and cryptographically signed bundle you can install on one or more enrollments. Run foundry deploy configure once to map your deployment inputs into an env.yml file, commit it, and both deployment paths read the same configuration:

• From the Palantir platform: If your source is hosted in the platform, tag a version of your repository and Foundry CI builds and deploys the product for you.
• From your own CI system: If your source is hosted elsewhere, build and deploy from your terminal or from any CI provider, such as GitHub Actions or CircleCI, with the Foundry CLI.

Use the Ontology you already have

A SuperRepo does not require a separate Ontology. Entities that already exist on your enrollment, including those built in the Ontology Manager, can be imported into your SuperRepo instead of being redefined in code, and types created in code are visible in the UI. Applications are never siloed by how their Ontology types were created.

Getting started

Create a SuperRepo in whichever environment you prefer:

• In the platform, select New > Code repository, then Applications > SuperRepo, and select Open in VS Code to launch it in VS Code workspaces.
• Locally, install the Foundry CLI and run foundry create.

Then follow the end-to-end tutorial to import an object type, define a link type, add a TypeScript function, expose it as a function-backed action, and consume all of it from a React application without leaving your editor. When you are ready to install on an enrollment, review Prepare for your first deployment.

Learn more about SuperRepo in our documentation.

What is coming next

The following are in active development and not available yet:

• Python functions
• Agent engine and Agent SDK
• External sources
• Automate
• Data pipelines

Review Coming in the future and the FAQ for details.

We want to hear from you

We welcome your feedback on SuperRepo, and your posts help the team prioritize what to build next. Share your thoughts with Palantir Support channels or our Developer Community using the superrepo tag.

Enhancements

Data connectivity & integration / Data Lineage

Data Lineage now colors object types in the Permissions color mode when using the Resource Access setting, provided those object types are located in projects. This allows you to visually distinguish access levels for project-based object types directly on your lineage graph.

Data connectivity & integration / Job Tracker

Job Tracker now uses an updated object type selector for ontology filtering and RID search. The new selector provides an improved interface for selecting object types when filtering jobs by ontology.

Data connectivity & integration / Scheduler

Schedule search results in now open the metrics Overview page in the current tab instead of navigating to Data Lineage.

Claude Opus 5 is now available on non-georestricted enrollments from Anthropic, AWS Bedrock, Google Vertex, and Microsoft Azure. For US, EU, and non-georestricted enrollments, the model is available from AWS Bedrock and Google Vertex. For JP georestricted enrollments, the model is available from AWS Bedrock.

Model overview

Claude Opus 5 adds improvements in life sciences, task verification, and solving coding problems. For more information, review Anthropic's model documentation.

• Context window: 1,000,000 tokens
• Modalities: Text, image
• Capabilities: Extended thinking, function calling

Getting started

To use this model:

• Confirm your enrollment administrator has enabled the Anthropic, Azure, Bedrock, and Vertex model families.
• Review token costs and pricing.
• See the complete list of models available in AIP.

Your feedback matters

We want to hear about your experience using language models in the Palantir platform. Share your thoughts through Palantir Support channels or on our Developer Community using the language-model-service tag.

Gemini 3.6 Flash is now available for commercial enrollments with VertexAI enabled in the US, EU, and non-georestricted regions. Additionally, Gemini 3.5 Flash Lite is now available for commercial enrollments with VertexAI enabled in the US, EU, and non-georestricted regions as well as for IL2 and IL4 enrollments.

Model overviews

Gemini 3.6 Flash is Google's latest Flash model, optimized for multi-step orchestration, full-stack code refactoring, and general reasoning. It is ideal for quickly executing agentic tasks. For more information, review Google's model documentation.

Gemini 3.5 Flash Lite is Google's fastest and lowest cost model in the Gemini 3.5 model family best used for latency-sensitive tasks where striking a balance between model performance and cost is important. For more information, review Google's model documentation.

Getting started

To use these models:

• Confirm your enrollment administrator has enabled the relevant model family.
• Review token costs and pricing.
• See the complete list of all the models available in AIP.

Your feedback matters

We want to hear about your experiences using language models in the Palantir platform and welcome your feedback. Share your thoughts with Palantir Support channels or on our Developer Community using the language-model-service tag.