Tag: AI Tools

Claude Cowork shipped more meaningful features in Q1 2026 than in any prior quarter. This is the complete log of what changed, what shipped, and what stayed broken — documented for teams managing Cowork deployments who need to know what actually changed and when.

January 2026: Foundation Stability

January was primarily infrastructure hardening. The Cowork runner environment received reliability improvements addressing the most common mid-task failures — streams aborting on slow API responses, sub-agent MCP tool inheritance failures, and session cleanup bugs that left stale working directories. No major feature launches, but the stability improvements reduced the frequency of mid-run failures that had characterized late 2025 Cowork usage.

Claude Code received the iOS app in October 2025 and the web version — both of which fed into Cowork’s remote dispatch capabilities in Q1. By January, the ability to assign Cowork tasks from a phone was stable enough for regular use.

February 2026: Model Upgrades Change Everything

February 5: Claude Opus 4.6 launched. February 17: Claude Sonnet 4.6 launched. Both significantly improved Cowork task quality — particularly for long-horizon agentic sessions where the original 4.0 models would lose coherence mid-task. Sonnet 4.6’s dramatically improved computer use capability (scoring 72.7% on OSWorld) made computer-use Cowork tasks reliable for the first time. Tasks that previously required constant human intervention to stay on track became genuinely autonomous.

The 1M token context window entered beta on both models in February, enabling Cowork tasks to hold significantly more context across long sessions — particularly valuable for content pipelines processing large document sets or cross-database synthesis tasks in Notion.

March 2026: Computer Use Reaches Cowork

March brought the integration of computer use into Cowork for Pro and Max plan users. Claude gained the ability to open files, navigate browsers, click through interfaces, and operate software within Cowork sessions — no additional setup required for Pro/Max subscribers. This was the most significant capability expansion of the quarter: Cowork tasks could now interact with software that doesn’t have an API, including legacy desktop applications and web interfaces without structured data access.

Dispatch — Cowork’s task queue feature — was extended to support computer use actions, allowing scheduled tasks to include browser automation and desktop interaction steps alongside the existing MCP tool calls and bash operations.

The Cowork VM disk-full bug (GitHub issue #30751) was acknowledged by Anthropic during March but not resolved. Power users with many skills installed continued to hit the useradd: cannot create directory error every 40-50 sessions. The documented workaround — moving sessiondata.img to reset the VM — remained the only fix. See the full fix guide.

April 2026: General Availability

Cowork reached general availability on macOS and Windows via Claude Desktop in April, removing the “research preview” label it had carried since launch. The GA release added enterprise features that had been absent from the preview: usage analytics, OpenTelemetry support for monitoring Cowork activity, and role-based access controls for Enterprise plans allowing admins to define which capabilities each team group can access.

A plugin marketplace launched for Team and Enterprise plans with admin controls. Admins can now approve, restrict, or block specific plugins org-wide. The Customize section in Claude Desktop was reorganized to group skills, plugins, and connectors in one place.

Scheduled and recurring task creation was formalized in the UI — previously requiring config file editing, now accessible from within the app. This was the feature most requested by Cowork power users throughout Q1.

What Remained Broken Through Q1

The sessiondata.img disk-full bug was the most significant ongoing issue. It affected every power user with a substantial skill library and required periodic manual intervention. No automatic session cleanup shipped in Q1. The manual workaround is documented at Claude Cowork useradd Failed Error Fix.

Machine-sleep task skipping also remained unresolved — scheduled tasks that fire when a machine is asleep are silently skipped with no retry. Teams running reliable scheduled automation continued to need an always-on machine or a cloud-side solution.

Q2 2026 Outlook

The disk-full bug fix and automatic session cleanup are the most anticipated Q2 items. Agent teams (available on Max plans) are expected to expand with better orchestration tooling. Claude 5, expected Q2-Q3, will bring model quality improvements that should further improve long-horizon Cowork task reliability.

Related: How Claude Cowork Can Actually Train Your Staff to Think Better — a 7-part series on using Cowork as a training tool across industries.

WordPress has a fully functional REST API built in. Most people never use it because they don’t know it’s there. For publishers, content operations teams, and anyone running Claude-powered content workflows, the REST API is the infrastructure that eliminates manual publishing and enables automation at scale. Here’s how it works and how to wire Claude to it.

What the WordPress REST API Can Do

The REST API exposes every major WordPress function over HTTP: create posts, update posts, get posts, manage categories and tags, upload media, manage users. Every action you can take in the WordPress admin can be done via API call. No plugin required — it’s built into WordPress core since version 4.7.

Authentication: Application Passwords

The simplest authentication method for Claude-to-WordPress connections is WordPress Application Passwords — a built-in feature (WordPress 5.6+) that generates a dedicated password for API access without exposing your main login credentials.

To generate one: WP Admin → Users → Your Profile → Application Passwords → enter a name → click Add New. Copy the generated password immediately — it’s only shown once. The format it gives you has spaces; remove them before using in API calls.

Authenticate using HTTP Basic Auth:

Publishing a Post via API

A complete post publish call:

The response returns the new post ID and URL. Log these — you need the post ID for any subsequent updates.

Wiring Claude Into the Pipeline

The standard Claude-to-WordPress pipeline: Claude generates the article content (with SEO optimization, schema markup, and FAQ sections baked in), a Python or Node.js script assembles the API payload, the payload POSTs to the WordPress REST endpoint, and the response confirms publication. For Cowork tasks, this runs on a schedule without human intervention.

The critical rule: Notion first, WordPress second. Every article goes to a Notion page before publishing to WordPress. Notion is the storage and version control layer; WordPress is the distribution layer. If you ever need to republish, update, or audit, you have a source of truth that isn’t locked inside the WordPress database.

Handling WAF Blocks

Many managed WordPress hosts (WP Engine, SiteGround) run Web Application Firewalls that block API calls from cloud IP addresses. Symptoms: 403 Forbidden errors on POST requests, even with correct credentials. Two solutions: route API calls through a Cloud Run proxy service that presents a different IP profile, or whitelist your specific GCP IP range in the hosting provider’s WAF settings. For SiteGround specifically, direct whitelisting is the most reliable path — the proxy approach has mixed results due to SiteGround’s aggressive WAF configuration.

Schema and SEO Metadata

The WordPress REST API supports all Yoast SEO and Rank Math meta fields as post meta. To set SEO title, meta description, and schema markup programmatically, include the relevant meta fields in your POST payload. For Yoast: _yoast_wpseo_title and _yoast_wpseo_metadesc. For Rank Math: rank_math_title and rank_math_description. Inject JSON-LD schema directly into the post content as a <script type="application/ld+json"> block — it renders correctly on the front end and passes Google’s rich results validator.

Running Claude through Vertex AI on GCP is straightforward to set up for a solo developer. For a team deploying Claude in production, three infrastructure decisions matter significantly: project structure for billing, IAM configuration for access control, and quota management to avoid rate-limit failures. Here’s the setup that scales cleanly.

Project Structure: One Project for Claude

Create a dedicated GCP project for Claude workloads — separate from your main application project, your data pipeline project, and your development sandbox. This separation is the single most important decision for operational clarity. With a dedicated project you get: Claude API costs isolated on their own billing line, IAM permissions that only affect Claude access (not your entire infrastructure), quota limits and alerts scoped to Claude usage, and audit logs that only contain Claude-related activity.

Naming convention: company-claude-prod for production, company-claude-dev for development. Keep them separate — dev workloads shouldn’t share quotas with production.

IAM Configuration: Minimum Necessary Permissions

The role that grants Claude API access through Vertex AI is roles/aiplatform.user. That’s the only role needed for model invocation and token counting. Don’t assign broader roles like roles/aiplatform.admin or roles/editor to service accounts that only need to call Claude.

For team deployments, create one service account per application or environment — not one shared service account for everything. Example structure:

If a service account is compromised, you rotate one key without affecting other applications. If a developer leaves, you disable their specific account without touching production credentials.

Quota Management: Request Increases Before You Need Them

Vertex AI Claude quotas are set conservatively by default. The default quota for most regions is enough for development and testing, but production workloads — especially automated pipelines running multiple requests per minute — will hit limits. The 429 error (Resource exhausted) at peak load is one of the most common production failure modes.

Request quota increases before launch, not during an incident. Go to Cloud Console → IAM & Admin → Quotas, filter by “anthropic,” and request increases for the Claude models you’re deploying. Approval is typically same-day for standard business accounts. For the global endpoint, a good starting quota for a production team is 60 requests per minute for Sonnet 4.6 and 20 requests per minute for Opus 4.6.

Budget Alerts: Know Before It’s a Problem

Set a budget alert on your Claude GCP project before anything runs in production. Go to Billing → Budgets & Alerts, create a budget for the project, and set email alerts at 50%, 80%, and 100% of your expected monthly spend. Add a Pub/Sub notification if you want to automatically throttle or pause workloads when budget thresholds are hit.

A Claude content pipeline running at unexpected volume can burn through budget quickly — especially with Opus 4.6 at $25/million output tokens. Budget alerts are the safety net that turns a potential billing surprise into a manageable alert.

Cloud Logging: Keep the Audit Trail

Vertex AI API calls are logged to Cloud Logging by default. For regulated industries, explicitly configure log retention to match your compliance requirements — the default 30-day retention may not be sufficient. For SOC 2 or HIPAA environments, export logs to Cloud Storage for long-term archival. The log entries include model called, project, timestamp, and token counts — enough for a complete audit trail without exposing prompt content.

Claude Cowork’s value multiplies significantly when it’s connected to the services where your work actually lives. A Cowork task with no MCP connections can only work with files on your local machine. A task connected to Notion, Gmail, and Google Calendar can read your priorities, check your schedule, triage your inbox, and write outputs back to your workspace — automatically. Here’s how to wire the connections.

Where MCP Configuration Lives

All MCP servers are configured in a single file: claude_desktop_config.json. On Windows, this is at %APPDATA%\Claude\claude_desktop_config.json. On macOS, it’s at ~/Library/Application Support/Claude/claude_desktop_config.json. Open it in any text editor. If it doesn’t exist yet, create it. Claude Desktop reads this file at launch — any changes require a restart.

Connecting Notion

Notion MCP gives Cowork tasks read and write access to your Notion workspace — fetch pages, create pages, query databases, and update records.

Get your Notion API token from notion.so/my-integrations. Create an internal integration, copy the token, and add it to the config. Then share each Notion database or page you want Claude to access with that integration — Notion doesn’t give blanket workspace access, you grant it page by page.

Connecting Gmail

Gmail MCP lets Cowork tasks search threads, read emails, and create drafts. Setup requires a Google Cloud project with the Gmail API enabled and OAuth credentials configured.

First-run requires completing OAuth in a browser window. After that, the token refreshes automatically. Gmail MCP is read-heavy in most Cowork workflows — used primarily for triage and summary, not bulk sending.

Connecting Google Calendar

Calendar MCP provides today’s events, upcoming meetings, and schedule context for briefing and planning tasks.

If you’ve already set up Gmail MCP with Google OAuth credentials, Calendar MCP can reuse the same credentials file.

Verifying Your Connections

After updating the config and restarting Claude Desktop, open a new chat and ask: “What MCP servers do you have access to?” Claude will list the active connections. If a connection doesn’t appear, check the config file for JSON syntax errors — a single missing comma or bracket breaks the entire config. Use a JSON validator before restarting.

For Cowork specifically: start a task session and ask Claude to fetch a specific Notion page or list today’s calendar events. A successful response confirms the MCP connection is working for scheduled tasks, not just interactive chat.

Common Issues

MCP server not showing up: JSON syntax error in config, or the npx package failed to install. Run the npx command manually in a terminal to check for errors.

Notion pages returning empty: The integration hasn’t been granted access to that specific page. Go to the page in Notion, click the three-dot menu, and share it with your integration.

Gmail authentication loop: The OAuth token expired or the credentials file path is wrong. Delete the token file and re-authenticate.

Related: How Claude Cowork Can Actually Train Your Staff to Think Better — a 7-part series on using Cowork as a training tool across industries.

One of the most practical Cowork automation setups is a daily briefing task — a scheduled agent run that assembles your morning context before you start work. Here’s exactly how to build it.

Daily Briefing Prompt Patterns by Use Case

What the Briefing Covers

A well-designed daily briefing task pulls from 3-5 sources and returns a single structured summary. Typical sections: today’s calendar events (from Google Calendar MCP), open priority tasks (from Notion MCP), any overnight emails that need a response (from Gmail MCP), one or two metrics worth knowing (from whatever dashboard you track), and a suggested priority order for the day. The whole thing arrives as a Notion page or appears in a Cowork run log by the time you open your laptop.

Step 1: Set Up Your MCP Connections

The briefing task needs read access to the services it pulls from. In Claude Desktop settings, confirm you have active MCP connections for the services you want to include. At minimum: Notion (for tasks and project status) and Google Calendar (for today’s schedule). Gmail is optional but adds significant value if you get time-sensitive emails. Configure these in claude_desktop_config.json before building the task.

Step 2: Write the Task Prompt

The prompt is the core of the task. It needs to be specific about what to pull, how to structure the output, and where to write it. A working prompt structure:

Step 3: Create and Schedule the Task

In Claude Desktop, open Cowork and create a new task. Paste your prompt. Set the schedule to daily at a time before you start work — 6:00 AM or 7:00 AM typically. Make sure Claude Desktop is configured to launch at startup on your machine so it’s running when the task fires. If your machine is off or sleeping when the task fires, it will be skipped — there’s no catch-up mechanism.

Step 4: Test It Manually First

Before relying on the scheduled run, trigger the task manually once. Verify it’s pulling from the right Notion database, writing to the correct parent page, and that the calendar and email integrations are connecting. Most first-run failures are MCP authentication issues — the MCP server needs to be authenticated with each service before the task can use it.

Iteration: Making It Better Over Time

The first briefing will be useful but imperfect. After a week of runs, refine the prompt based on what’s missing or what’s noise. Common refinements: add a “what’s overdue” check from Notion, filter email to only flag certain senders or subjects, add a weather check for field-based work, or include a one-line summary of the prior day’s Cowork run logs. Each iteration takes 5 minutes to update the prompt; the task runs better every week.

Related: How Claude Cowork Can Actually Train Your Staff to Think Better — a 7-part series on using Cowork as a training tool across industries.