Skip to main content
​
New releasesImprovementsFixes
This release moves the Claude engine to bring-your-own models: Claude-engine steps now run on the Anthropic or AWS Bedrock models you configure, with a workspace default and per-sub-agent model selection.

​
Claude engine models

  • Claude-engine steps now use the models you configure in the workspace, each with its own credentials, instead of a single workspace-wide Claude API key. Anthropic and AWS Bedrock models are supported. See Claude Agent SDK.
  • Set a workspace Default Claude Engine Model in Workspace Settings > AI. A step resolves its model in order: the explicit step or agent choice, then the workflow default, then the workspace Claude default, then the main workspace default.
  • Pin a different model per sub-agent on the Claude engine. Pinning changes only which model answers: credentials, billing, region, and gateway always come from the session’s coordinator model, so a sub-agent model must be from the same provider as the session.
  • Anthropic models accept a Base URL, so the Claude engine can route through a gateway that serves the Anthropic wire format (/v1/messages).
  • Existing workspaces were migrated automatically: the legacy workspace “Claude API key” secret became a “Claude (migrated)” Anthropic model, set as the workspace Claude default. No action is needed. The Workspace Secrets tab was removed along with the legacy secret.
  • Misconfigured models fail at dispatch with a message naming the model and the cause. There is no silent fallback to another key or model.

​
AWS Bedrock

  • Bedrock models can now authenticate with a Bedrock API key as an alternative to an IAM access key pair. When both are set, the API key is used. See LLM models.
  • Prompt caching now applies to Claude models routed through OpenRouter and AWS Bedrock, cutting token usage and latency on repeated context.
  • Bedrock cache tokens are now counted in LLM usage.

​
Triggers

  • Messaging trigger conditions now expose the full message context in the workflow builder’s condition selector: channel ID, channel name, channel provider and privacy, workspace ID, message text, and message and thread timestamps. Build conditions such as context.channel.id alongside the existing actor fields.

​
Orchestrations

  • Human replies and decisions now resume an orchestration reliably: transient failures are retried automatically, and an instance that cannot recover is shown as stalled instead of failing silently.

​
Workflow builder and runs

  • Run details and logs now show step names instead of step IDs, using the names from the run’s workflow snapshot even after the workflow changes.
  • Model errors during runs are now classified and reported with distinct messages instead of all surfacing as model unavailable.
  • Fixed parallel tool calls from OpenAI models being misrouted.
  • Fixed workflow builder steps rendering stacked on top of each other.
  • Fixed the Space key not registering in instruction editors inside the workflow builder.

​
Integrations

  • Agents can now read ticket comments on Linear and ClickUp.

​
On-prem deployments

  • All services now honor HTTP_PROXY, HTTPS_PROXY, and NO_PROXY, including spawned agent containers, so Overcut can run behind an egress proxy.

​
Other fixes

  • Removed team members no longer appear in the team member list.
​
New releasesImprovementsFixes
This release introduces Orchestrations, a new module for running multi-workflow processes with agents deciding the path and humans deciding at the gates.

​
Orchestrations

A workflow automates a single job. An orchestration runs the whole process: it carries a work item (a ticket, a task, or an external resource delivered by a custom event) from intake to completion, across as many workflows as the process takes.Real processes rarely follow one path. Instead of authoring every branch up front, you define the outcome and the boundaries: the goal, the workflows the orchestration may use, and the points where a human must decide. Within those bounds, agents choose the next step at runtime based on how the work actually unfolds, so the same orchestration handles the straightforward case and the exceptional one.
  • Bounded autonomy: agents pick the path, but only from the workflows you allowed, within the limits you set, and never past a gate without a human decision.
  • Human judgment where it matters: gates pause the process for approval, and you can discuss a pending decision with the orchestration in chat before you decide.
  • Supervised to completion: a supervisor keeps each instance moving, detects stalls, and judges the result against the goal, not just whether the steps ran.
  • Accountable by default: every routing decision is recorded, and the conversation stays connected to the work item. Comments on the original issue or pull request flow into the process, and replies go back to it.
  • Visible in operation: every in-flight item is tracked in one place, from intake to resolution, and any instance can be inspected or cancelled at any point.
Orchestrations are built on a visual canvas and start from the same triggers workflows already use.

​
Machine sizes for workflow runs

  • Choose the machine size a workflow runs on with the new Machine Size setting in workflow settings: standard (default, 1 credit per run), large (2 credits), or xlarge (4 credits). Larger sizes provide more CPU and memory for workspace commands such as builds and tests.
  • The size is frozen when the run starts and shown on run views, and the run log records the machine size used.

​
Slack thread reply trigger

  • Workflows can now trigger on thread_reply: when someone replies in a watched Slack thread, the workflow fires with the reply as context. Configure it like any other trigger in the workflow builder.

​
File attachments

  • Attached DOCX, XLSX, and PDF files are now parsed and their content made available to agents. PDFs are passed natively to Anthropic models.
  • Fixed attachments with non-ASCII filenames (for example Hebrew) arriving garbled.

​
Models

  • The GPT-5.6 family is available as system models: gpt-5.6-sol (flagship), gpt-5.6-terra (mid), and gpt-5.6-luna (small), all with vision enabled.
  • Seven legacy system models were retired: o3, o3-mini, gpt-4.1, gpt-4.1-mini, gpt-4o-mini, gpt-5-codex, and gpt-5.2-codex.

​
Assistant and chat

  • The workflow builder assistant now suggests a publish message when you publish workflow changes.
  • The chat input suggests your next message as ghost text; press Tab to accept.

​
Azure DevOps

  • The agent’s completion message is no longer overwritten by later status comments on pull requests.
  • Fixed list_tickets keyword search failing due to invalid WIQL syntax.

​
Reliability & fixes

  • Agent start failures (for example an image that cannot be pulled) now surface a clear error and fail fast instead of hanging.
​
New releasesImprovementsFixes

​
Run Script workflow action

  • New script.run action runs an inline bash script as a deterministic workflow step, with no AI agent or model tokens involved.
  • Scripts receive trigger data and previous step outputs through environment variables, and can return structured JSON to later steps by writing to $OC_OUTPUT_FILE.
  • Secret values are redacted from script results, and a configurable timeout stops the script and every process it spawned.
  • The script field uses a code editor with syntax highlighting, and the workflow builder assistant can add and configure the step for you.
  • Read the docs

​
Run Context panel

  • Workflow run details now include a Run Context panel: select Context to see the actual trigger data and outputs JSON available to the run’s steps and templates. Step outputs update while the run executes, so you can verify what template expressions like {{outputs.<stepId>.<field>}} resolve to.

​
LLM gateway support

  • Custom LLM models on OpenAI, OpenRouter, and Azure OpenAI (Responses API) can now route through a proxy or API gateway: override the base URL, choose how the credential is sent (bearer Authorization, api-key header, or a custom header name), and add static extra headers for gateway routing. Standard Azure OpenAI also supports extra static headers. Existing models keep their current behavior.
  • Fixed deactivated models becoming unrecoverable: inactive models stay visible on the LLM Models page, where you can review, edit, or reactivate them, while model pickers only offer active models.
  • Read the docs

​
Azure DevOps

  • Code review results are now submitted as reviewer votes with comment threads on Azure DevOps pull requests, and retries no longer create duplicate threads.
  • Fixed automated replies from the integration’s service account re-triggering workflows.

​
Skills

  • Add multiple skills at once from the Add Skill page.

​
Slack

  • Channel pickers load faster: channel lists are cached server-side with debounced search, and repeated scans no longer trip Slack rate limits.

​
UI refresh

  • Workflow builder nodes use a new tab-card style with a floating action toolbar on the canvas.
  • Fixed text overflow on agent cards.

​
Reliability & fixes

  • Fixed agent connections dropping mid-run due to premature socket closes and connection registration races.
  • Fixed several tool-call handling errors that could stall LLM conversations or break retries.
  • Agent status reporting now times out safely during transient outages instead of crashing the run.
  • Repository connections no longer show duplicates across providers, and abandoned connection drafts are cleaned up automatically.
  • Repository identification tolerates extra text around JSON output instead of failing the workflow.
  • Fixed ClickUp requests failing on some content-type headers.
  • The universal dev container image (version 6) now ships Node 22.
​
New releasesImprovementsFixes

​
Token usage analytics

  • New token usage analytics on the dashboard, with charts and metrics that break down LLM consumption over time and per workflow, so you can see where tokens are going.
  • Workflow run consumption can be filtered at the workspace level, and workflow names in the usage charts link straight to their runs.
  • Cached input tokens are now tracked and reported as part of usage.

​
Audit trail

  • Full audit trail across every workspace-scoped resource, recording who changed what for security review, compliance, and incident investigation.
  • Browse and filter the audit log in the UI, defaulting to the last 7 days, with field-level diffs of each change.
  • Read the docs

​
Models

  • Added support for GPT-5.5 and GPT-5.4-mini.

​
Prompt caching

  • Anthropic prompt caching is now applied to the system prompt, reducing cost and latency on repeated runs.
  • Prompt-cache tokens are reported consistently across the Anthropic and OpenAI Responses API paths.

​
Dev containers

  • Added a new universal image (version 6) and a .NET 10 variant.
  • Agent image resolution now spans multiple repositories, with precedence and clear reporting when images conflict.

​
Preparation steps

  • Workflow run details now show preparation steps, such as setting up the workspace and provisioning the environment, as their own distinct steps. You can follow each one as it runs and see exactly where time is spent before your workflow begins.

​
Reliability & fixes

  • Chat sessions are more stable and stay connected through infrastructure disruptions instead of hanging.
  • Fixed LLM retries failing because trailing system messages violated Anthropic’s message ordering requirements.
  • Custom model configuration errors are now surfaced, and stale configuration no longer lingers after editing a model.
  • Fixed API tokens expiring prematurely instead of honoring the rolling inactivity window.
  • Workflow failures now surface git token errors in the run status instead of failing silently.
​
ImprovementsFixes

​
Triggers

  • Issue triggers now expose classification fields - priority, severity, components, areaPath, and iterationPath - across Jira, Azure DevOps, and Linear, so you can filter and branch workflows on them.
  • Issue triggers now provide granular labelsAdded and labelsRemoved arrays, so you can react to exactly which labels changed rather than the full label set.
  • Linear issues with no priority now map to an undefined priority instead of a “No priority” label, so priority filters behave consistently.

​
Azure DevOps

  • Connecting an Azure DevOps organization now uses a guided, multi-step OAuth flow.
  • Added support for legacy visualstudio.com URL formats.
  • Azure DevOps comments are now fully converted from HTML to plain text, so comment content reads cleanly in workflow runs.
  • Clearer error handling when prefetching Azure DevOps data fails during setup.

​
Repository connections

  • Connecting a repository now surfaces webhook creation errors immediately, instead of silently leaving the repository connected with no webhook.
  • Unhealthy repositories now show their state with a retry option in the integrations UI.
  • Soft-deleted repositories are excluded from project lookups, preventing stale settings validation errors.

​
Reliability & fixes

  • Fixed agent log scrolling so a tall message no longer hijacks the page scroll until it is focused.
  • Fixed dropped tool responses when several tool calls run in one batch. Synthetic attachment messages are now deferred until all sibling tool calls complete.
  • Fixed orphaned tool calls by limiting internal agent delegation to one per turn.
​
New releases

​
Custom Events

Overcut already comes with built-in integrations for systems like GitHub, Jira, Linear, and GitLab. But every organization has additional systems that matter to their workflow, whether internal platforms, custom services, enterprise tooling, or external vendor systems. With Custom Events, any system that can send an HTTP request can now trigger an Overcut workflow.What this unlocks for your team
  • Incident response automation across your full stack - connect Datadog, Grafana, PagerDuty, internal alerting systems, or custom observability pipelines directly into remediation workflows.
  • Deployment and CI orchestration beyond built-in integrations - Jenkins, Buildkite, internal deployment tooling, release scripts, or platform APIs can trigger workflows directly.
  • Enterprise-wide workflow automation - connect internal portals, security systems, vendor platforms, legacy infrastructure, or any custom service into your SDLC automation layer.
  • Unified orchestration across all systems - the entire operational ecosystem around your engineering organization, not just the tools Overcut ships with out of the box.
Built for production
  • Flexible authentication (bearer token, custom header, or URL-only) to support different sender capabilities.
  • Token and secret rotation without downtime.
  • Concurrency control via lockKey, allowing workflows that touch the same resource to execute safely and sequentially.
  • Project-level scoping to control which teams can consume specific event types.
  • Structured payload fields that keep workflow runs readable in the UI while remaining fully filterable in workflow logic.
Overcut can now orchestrate workflows across the full surface area of your organization, not just predefined integrations.Read the docs
​
New releasesImprovementsFixes

​
Meet your new Overcut assistant

We’ve reimagined the assistant as a first-class workspace citizen.
  • A new home screen welcomes you with a focused chat experience. Start a workflow, ask a question, or kick off a task from a single input.
  • Persistent header chat stays with you across the app, expanding and collapsing as you work.
  • Conversation history with renaming, deletion, and auto-generated titles, so you can pick up exactly where you left off.
  • Real-time updates across the UI. When the assistant creates or edits something like a workflow, permission, or trigger, the UI updates instantly without a refresh.
  • Smarter and more capable. The assistant can now perform almost anything available in the UI. Ask it to connect an MCP server, inspect logs, manage integrations, or execute workflows.

​
Multi-project workspaces

Workspaces now support multiple projects with proper isolation and scoping throughout the platform.
  • Global project picker in the workspace header for fast switching.
  • Per-project repository access controls. Choose whether a project can access all connected repositories or only a selected subset.
  • Project-level permissions with team and role assignment for finer-grained access control.
  • Project colors for quick visual identification.
  • Project-scoped runs, dashboards, and consumption summaries that automatically respect the active project.
  • Restructured sidebar with workspace ↔ project mode switching and nested settings.

​
Slack integration

  • Connect Slack to your workspace, manage channels, and send messages directly from workflows and the assistant.
  • Channel message triggers that kick off workflows when Slack messages arrive, with filtering by channel, user, and message content.
  • Expanded OAuth scopes for message history and reactions support.

​
Workflow builder & orchestration

  • Syntax-highlighted instruction editor with live preview in a full code editing experience.
  • New agent tools for linking and unlinking tickets across Jira, Linear, and other ticketing systems, including support for relationship types.

​
UI polish

  • Brand-new icon system for crisper and more consistent visuals across the platform.
  • Restyled sidebar, menus, and profile areas with refined design tokens.
  • Centralized breadcrumbs for clearer navigation context across every page.
  • Automatic selection of your latest execution or default repository when opening the playground.
  • Smarter workflow run defaults that jump directly to the most relevant log step based on run status.

​
Reliability & fixes

  • Improved handling for large agent outputs with automatic management of oversized tool results.
  • Cleaner branch checkouts. Cached working trees now discard stray uncommitted changes before switching branches.
  • Fixed an issue where deleting a comment containing a slash command could accidentally retrigger it.
  • Fixed PR approvals via submit_review failing with “no pending review”.
​
New releasesImprovements
This release is focused on giving teams better visibility, more control, and faster ways to scale agent-driven workflows across the organization.

​
Orchestration Map

Get a clear, real-time view of how your entire system operates.Instead of managing workflows, agents, and integrations in isolation, you can now see how everything connects in one place. This makes it easier to understand dependencies, debug issues faster, and confidently evolve your setup without breaking things.

​
Skills

Turn your existing knowledge and tools into reusable capabilities for agents.Overcut now lets agents use the same skills your developers already rely on, including skills from repositories and marketplaces. You don’t need to rebuild anything, you can plug into what already exists and bring it into your workflows with full control.
  • Reuse skills from your existing ecosystem and marketplaces.
  • Apply the same governance and management layer across all skills.
  • Control which agents can use which skills to keep execution focused and avoid prompt bloat.
  • Ensure consistency while still allowing flexibility at runtime.
The result is a more scalable way to distribute expertise across teams, without losing control.

​
Playbook Catalog

Make it easier for teams to get started and reuse proven workflows. The new catalog helps teams discover, adopt, and standardize workflows across projects, reducing setup time and ensuring best practices are consistently applied.

​
Workflow Visibility

Understanding what happened during a workflow run is now much simpler with a redesign of the execution details and logs. Teams can quickly scan executions, identify issues, and drill into details, reducing time spent debugging and improving overall reliability.

​
Change Accountability

Every workflow version change is now clearly tied to a person, with full visibility on the history page. This improves traceability, governance, and collaboration, especially in larger teams where multiple people are evolving workflows.
​
New releasesImprovements
This release focuses on self-improvement, memory management, and better visibility into agent behavior.

​
Automatic Workflow Self-Improvement

Workflows are now self-improving through an automated reflection process. After a configurable number of executions (default: 10), Overcut analyzes a sampled set of recent runs and feeds insights back into the workflow. Auto-improvement is enabled by default for all workspaces.How it worksEach retrospective runs a multi-step pipeline:
  • Investigate - analyzes logs, tool usage, and outcomes across sampled runs. Identifies errors, inefficiencies, and recurring patterns, including whether existing memories helped or hurt.
  • Process tentative memories - validates previously tentative memories. Repeated patterns are promoted to active; contradictions are removed.
  • Create memories - generates new memories from cross-run patterns. Patterns seen in 2 or more runs become active; strong single-run signals stay tentative.
  • Update weights - adjusts memory relevance (0.0-1.0) based on impact. Helpful memories are strengthened; ineffective ones decay. Memories below 0.05 are archived.
  • Summarize - produces a structured report with findings, memory updates, and recommendations.
Manual mode is also available - run retrospectives on demand with an optional focus question. Manual runs skip weight updates and tentative memory processing to avoid bias.New configuration options
  • Run threshold - number of runs before triggering a retrospective.
  • Sample size - percentage of runs analyzed.
Read the docs

​
Agent Tool Visibility

You can now see exactly which tools each agent has access to during a workflow run.
  • New “Tools Available” message in each agent thread.
  • Captured for both main agents and sub-agents.
  • Included in thread summaries for quick reference.
  • Infrastructure logs excluded from step counts to keep things clean.
This makes it much easier to understand why an agent did or didn’t use a specific tool.

​
Cancel Queued Workflow Runs

Runs in On Hold status can now be cancelled directly from the UI.
  • Cancel button with confirmation dialog.
  • Transitions the run to Failed with a clear status message.

​
GPT-5.3 Codex as Default Model

The default agent model is now GPT-5.3 Codex, improving code generation and reasoning out of the box. Workspaces with an existing default model are not affected.

​
Workflow Version Tracking

Each run now includes the system-managed version of the workflow at dispatch time. This makes it easier to track how changes impact results over time.
​
New releasesImprovements
This update introduces deeper integrations, smarter agents, and better visibility into how your workflows run and improve over time.

​
ClickUp Integration

Overcut now supports full integration with ClickUp. You can connect your workspace and have workflows automatically sync with your tasks:
  • Create comments.
  • Update statuses.
  • Track attachments.
Everything is powered by real-time webhook events, and supports ClickUp markdown formatting for clean, readable updates directly in your tasks.

​
Agent Memory

Agents can now learn across workflow runs. They build memory of patterns, decisions, and context from your codebase, making workflows more consistent over time.Key capabilities:
  • Dedicated UI to view, edit, and manage memory.
  • Memory scoped per workflow step for precision.
  • Full visibility into which memories are used during execution.
  • Tentative memory system where agents suggest new memories for approval.
This is a big step toward adaptive, improving workflows.

​
Retrospective Workflows

You can now run retrospectives on past workflow executions. Select previous runs and trigger a retrospective to:
  • Analyze agent logs and tool usage.
  • Evaluate outcomes.
  • Generate a consolidated summary with actionable insights.
This lays the groundwork for automatic workflow self-improvement.

​
Workflow Dashboard

Each workflow now has a dedicated dashboard with:
  • Recent runs.
  • Average duration.
  • Quick access to run details.
This gives you a clear view of performance over time without digging into logs.

​
GPT-5.4 Model Support

Overcut now supports GPT-5.4 as the default model for agent and chat workflows. You get access to improved reasoning and performance out of the box.

​
Custom Agents

You can now define custom agent types tailored to your workflows. This allows you to go beyond built-in agents and create specialized automation aligned with your development processes.Read the docs

​
Additional Improvements

  • Use case organization - cleaner tab-based navigation.
  • Workflow output display - properly formatted single-message outputs.
  • Scrollable chat - improved experience for long agent conversations.
​
New releasesImprovements

​
MCP Catalog & One-Click Installation

Finding and installing MCP servers is now much easier. You can browse a curated MCP catalog directly in the app, search by name, filter by category, and see which servers are already installed.When installing a server, a guided setup flow walks you through everything from a single page:
  • Configuring required secrets.
  • Selecting which tools to expose.
  • Previewing the final configuration.
  • Creating the server.
You can still create custom MCP servers for any service in your ecosystem.Read the docs

​
MCP Server Secrets

MCP servers can now have project secrets attached directly to them. Secrets can be created, updated, or removed from the MCP server settings page and are securely resolved at runtime when agents execute.Read the docs

​
Scratchpad Tools for Multi-Agent Workflows

Agents now have built-in scratchpad tools designed for multi-step workflows. These allow agents to pass structured data between steps and agents, replacing file-based scratchpads that sometimes caused path confusion or accidental overwrites.All scratchpad tools are already available to agents in the playbooks repository, so you can start using them immediately in your workflows.Read the docs

​
GPT-5.3-Codex Model Support

GPT-5.3-Codex is now available as a model option. Vision support is enabled out of the box, and vision has also been enabled for existing Codex models. Across most playbooks we are seeing major improvements in quality, accuracy, and execution speed.

​
New Code Review Playbook + Major Improvements

We released a new code review playbook built with:
  • The new scratchpad tools.
  • Improved reasoning flow.
  • Parallel execution.
Combined with GPT-5.3-Codex, we are now seeing average review times of ~4 minutes for mid-to-large PRs, with improved accuracy and more consistent feedback.View the playbook on GitHub
​
New releases

​
Context Map

A new way to manage multiple code and ticket repositories across your workspace.What it isA visual, graph-based view of all your repos across GitHub, GitLab, Bitbucket, Jira, Azure DevOps, and Linear, showing how ticket systems connect to code repos.What you can do with it
  • Visually connect ticket repos to code repos with simple drag and drop.
  • Instantly see which features are enabled per repo (caching, indexing, hints, custom instructions).
  • Filter by org or configuration.
  • Focus on a specific repo and highlight only its related connections.
  • Edit repo configuration inline from the same screen.
Why this mattersAgents need to understand which code repos correspond to which ticket systems. Without clear correlations, scoping gets messy. Context Map becomes the central place to manage that relationship across your entire workspace.
​
New releases
Two new capabilities bring your CI pipelines into Overcut workflows.

​
CI Triggers & Tools

Workflows can now react to CI pipeline events - failed builds, completed runs, timed-out jobs, and more. Six new trigger events (ci_workflow_failed, ci_workflow_completed, and others) let you kick off workflows automatically when something happens in your pipeline. Agents also get five new CI/CD tools to inspect runs, read logs, and retry workflows, all without leaving the Overcut environment.

​
Fix CI Playbook

Our first CI-powered playbook is live. Fix CI automatically detects when a CI run fails on a PR, reads the logs to figure out what went wrong, applies a code fix, validates it locally by re-running the failed command, and pushes the fix, all hands-free.It won’t take shortcuts either: no ts-ignore, no deleting tests, no commenting out code. If the fix requires a bigger change, it leaves a detailed comment for the developer instead.Trigger it automatically on any CI failure, or manually with /fix-ci on any PR.

​
Build Your Own CI Workflows

We also enriched our playbook repo with knowledge about CI events and context, so you can use it to build your own custom CI workflows tailored to your team’s needs.

​
A note on rollout

CI-triggered workflows are a new feature, so we recommend monitoring them for the first few runs before enabling fully autonomous operation. Start with manual triggers (/fix-ci), review the fixes they propose, and enable the automatic trigger once you are confident in the results.
​
New releasesImprovements

​
Vault

You can now securely store secrets and access tokens inside Overcut. Go to Settings -> Agents -> Vault to get started.Secrets stored there are injected into the agent execution sandbox as environment variables at runtime. This allows you to:
  • Store API keys and credentials securely.
  • Control which secrets are available per use case or per agent.
  • Ask the agent to execute commands that reference secrets via environment variables.
No more exposing credentials inside prompts.

​
MCP Support (Beta - Controlled Rollout)

We’ve added support for MCP integrations, allowing you to connect external systems and capabilities directly to specific agents. When combined with Vault, you can provide MCP credentials securely at runtime without exposing them in prompts.MCP is currently in controlled beta rollout and is enabled per workspace on request.

​
Persistent Agent Memory

Agents now retain persistent memory across runs. They carry forward context about your codebase, structure, and project patterns. This reduces repeated exploration and makes execution smarter over time, especially in long-running or iterative workflows.This works automatically. You don’t need to configure or enable anything; the agent manages this behavior internally.

​
Dedicated Explore Agent

We introduced a dedicated Explore Agent for deep codebase understanding. It knows when to explore, when to act, and handles large or unfamiliar repositories much more reliably. This significantly improves accuracy and overall run stability.It is used automatically by other agents when needed. If you want to explicitly instruct an agent to leverage it at a specific step, you can simply say something like “use the explore agent to analyze the repository structure before making changes”.

​
Parallel Multi-Agent Execution

You can now delegate multiple tasks in the same turn within a multi-agent session. For example, you can instruct the system to assign multiple review tasks to different agents simultaneously, enabling true parallel execution instead of sequential work. This reduces total runtime and improves throughput for complex workflows.The coordinator will attempt to parallelize work automatically when it makes sense. If you know that tasks can safely run in parallel and want to improve runtime, you can also instruct it explicitly, for example “run in parallel”, “delegate all tasks at the same time”, or “execute simultaneously”.

​
New Skills in overcut-playbooks

We’ve added new skills to the overcut-playbooks repository to help you create higher-quality Overcut use cases. To use them:
  • Pull the latest version of the repository.
  • Use your preferred local agent.
  • Leverage the new skills to generate or refine structured playbooks.
These updates should make it easier to build reliable, production-ready workflows.
​
New releases

​
Workflow Versioning

Workflow versioning is now live. This gives you full control over workflow changes with a git-inspired approach, without risking production.What’s new
  • Draft vs Published - edits are saved as drafts. Only published versions run, so you can safely work without affecting live workflows.
  • Publish with messages - when you publish, add a short message describing what changed, just like a commit.
  • Full history - see every version of a workflow, who published it, and when.
  • Safe rollbacks - restore any previous version with one click.
  • Unpublished changes view - a new page shows all workflows with pending changes across the project, including visual diffs.
  • Discard changes - reset your draft back to the last published version.
How it works
  • Edit your workflow as usual; it auto-saves as a draft.
  • When ready, click Publish and add a message.
  • View history anytime from the workflow page.