10 · Which one, when

A decision procedure, role-by-role recommendations, worked scenarios, and the anti-patterns that waste the most time. This is the section your executives will screenshot.

The primary question: what is the artefact?

The rule

Choose by the output, not by the person. If the finished thing is a document, deck, spreadsheet, tidy folder, or synthesised research → Cowork. If it is a commit, a pull request, a passing test suite, or a deployed change → Claude Code.

Anthropic's administrator guide supplies a usable admission test for the same judgement:

Verbatim — Cowork Enterprise Administrator Guide

"An ideal Claude Cowork task produces a deliverable."

If you cannot name the artefact the task will produce, it probably belongs in Chat. That one question filters out most of the misapplied-agent cases before they waste anyone's usage limit.

This works because it survives edge cases. A non-technical operations lead who needs a script that runs in CI still needs Claude Code. An engineer writing an architecture decision record for the board is better served by Cowork.

Decision tree

A decision tree rooted in the question what are you trying to produce, branching to Claude Code for shipping code, Cowork for documents and research, Dispatch for mixed work, and plain Chat for one-off questions, each with its own leaves.
Fig 10.1 · Which product, decided by the artefact. Choose by the output, not by the person — the rule survives edge cases that a role-based rule does not.
Anthropic agrees with this

The enterprise deployment guide publishes its own three-way selection table — Chat for "a question, a rewrite, a quick brainstorm"; Cowork for "research, analysis, or a finished document built from your files and systems"; Code for "writing, testing, or shipping software." Reproduced in full in §12. Useful to know you are corroborating them rather than extrapolating.

Three columns — Chat, Claude Cowork and Claude Code — each with the kind of task it suits and why, above the line the three share the same Claude underneath; what changes is the workspace around it.
Fig 10.2 · Anthropic's own three-way selection. All wording verbatim. Use this one when you want their authority behind the recommendation rather than yours.

Secondary constraints that can override the primary answer

ConstraintForces you towardWhy
Content must not leave your machine or networkClaude Code, localCowork processes local files on Anthropic's servers by design
Work must draw on an internal system reachable only from your networkClaude Code, localThe Cowork environment is separate from your network
Billing must go through AWS / Google Cloud / Azure commitmentsClaude CodeBedrock, Claude Platform on AWS, Google Agent Platform, Microsoft Foundry
You need a hard, deterministic "never do X"Claude Codepermissions.deny + PreToolUse hooks; Cowork has no equivalent
Everything must land in an auditable compliance trailClaude Code (or Cowork cloud sessions + OTel)Cowork local session data isn't in audit logs or the Compliance API
The user will never open a terminal, everCoworkThat's the entire product thesis
The team is on Enterprise seats and wants Dispatch or computer useNeither — not availablePro/Max only
The setup must be shared and version-controlled across a teamClaude CodeCowork projects live on one computer and aren't shareable
Work must continue overnight with no machine onCowork scheduled tasks or Claude Code RoutinesBoth run on Anthropic infrastructure

Role-by-role recommendation

RoleStart withFirst thing to tryWatch out for
CEO / GM Cowork A recurring Monday briefing built from connected email, calendar and a metrics folder — as a scheduled task. Scheduled tasks can't read local folders. Keep the source data in connected apps or the Claude account.
CFO / Finance Cowork + the official financial-services plugin set Model refresh or variance analysis producing an Excel file with working formulas. Anthropic's own guidance is to avoid granting access to sensitive financial documents while prompt-injection risk exists. Scope folders tightly; use Manual mode.
CTO / VP Engineering Claude Code Roll out to one team with a committed CLAUDE.md, then measure with the analytics dashboard. Governance first — managed settings and deny rules before broad enablement.
CMO / Marketing ops Cowork Campaign post-mortem: pull the numbers, build the deck, draft the summary. Usage limits. Agentic deck-building is expensive; consider Max for heavy users.
General Counsel / Legal Cowork, cautiously Contract organisation and clause extraction across a folder. The compliance-trail gap. Get a written position from your Anthropic account team before regulated use.
CISO / Risk Read §08 first Stand up an OTel collector for Cowork before anyone uses it in anger. user.email is always in the telemetry; egress rules don't cover web fetch, web search or MCP.
Sales leadership Cowork Pre-meeting account brief assembled from CRM connector, email and the web. Browser use and local files need the desktop app open and the machine awake.
Chief of Staff / Ops Cowork, then Dispatch Weekly cross-functional status roll-up. Then brief it from your phone. Dispatch is Pro/Max only. Child tasks can complete partially if a permission prompt times out after 10 minutes.
Data / Analytics lead Both Cowork for the narrative and the deck; Claude Code for the pipeline and the notebooks. They don't share configuration — a skill in ~/.claude won't show up in Cowork.

Worked scenarios

Scenario A — "Prepare the board pack"

Answer: Cowork. Local folders of source material, connectors for the live numbers, and a PowerPoint deliverable with formatted tables. Set up a project holding the board folder plus standing instructions about house style and required sections. Run it in Manual mode the first time so you can see the plan; move to Auto once you trust the shape.

Scenario B — "Migrate 400 files off a deprecated internal library"

Answer: Claude Code, dynamic workflows or /batch. This is exactly the case the workflows documentation names ("a 500-file migration"). Worktree isolation prevents collisions; each subagent opens its own PR for review.

Scenario C — "Every Monday at 7am, tell me what changed in our competitive landscape"

Answer: Cowork scheduled task. Runs remotely, no machine required, uses your connectors and web search. Constraint to design around: it cannot read a folder on your laptop, so the output should land in a connected service or your Claude account.

Scenario D — "Our incident review process is inconsistent across teams"

Answer: a plugin. This is the one case where the right answer is neither product but the shared layer. Package the process as a skill inside a plugin, publish it to an internal git-repo marketplace, and mark it Required for the org. It then works in both Cowork and Claude Code, for both the SRE writing the timeline and the comms lead writing the customer note.

Scenario E — "I want the AI to fix the bug I found on my phone at the airport"

Answer: Dispatch (Pro/Max) or Claude Code on mobile. Dispatch routes it to a Code session on your desktop at home; Claude Code on the web/mobile runs it in Anthropic's cloud without your machine. Choose based on whether the repo is checked out locally.

Scenario F — "Summarise this 40-page PDF"

Answer: neither. Plain Claude Chat. Do not spin up an agentic session for a task that one model call solves. Teaching people when not to use these products protects your credibility and their usage limits.

Anti-patterns

Anti-patternWhy it hurtsDo instead
Using Cowork for one-shot questionsBurns limits far faster than Chat for no benefitUse Chat. Reserve Cowork for multi-step work with a deliverable.
Micromanaging the stepsBoth products are designed around "say what, not how." Step-by-step prompting fights the architecture.State the outcome and the constraints. Let it plan.
Connecting your whole home folderWidens the trust boundary enormously; Anthropic explicitly advises against granting access to sensitive documentsConnect the narrowest folder that contains the work.
Running unattended, Auto mode, with write-capable connectors, on web-sourced contentThis is precisely the two-condition prompt-injection scenarioBreak one condition: Manual mode, or read-only connectors, or no web access.
Putting everything in CLAUDE.md / project instructionsCosts context on every request and reduces adherenceRules in instructions; reference material in skills.
Expecting a Claude Code skill to appear in CoworkCowork doesn't read ~/.claudeAdd it in Customize, or package it as a plugin.
Treating CLAUDE.md as a security control"An instruction… is a request, not a guarantee"Hooks and permissions.deny for anything that must hold.
Demoing Dispatch or computer use to an Enterprise audienceNot available on their planCheck the seat type before you build the demo.
Assuming an unattended Dispatch task completed fullyUnanswered permission prompts auto-deny after 10 minutes and the task continuesRead the transcript, not just the final artefact.
Promising Zero Data Retention for CoworkNot documented for Cowork; ZDR is not in the standard Enterprise plan eitherRoute the question to the Anthropic account team.

A staged adoption path to recommend

Two roadmaps, pick one

Anthropic publishes its own six-month Evaluate / Pilot / Scale roadmap tied to the five-level maturity ladder (§12). It agrees with the path below on shape — champions first, encode second, distribute third — but is more concrete on timing, while mine adds an explicit instrumentation step before scaling. Show whichever fits the room, and say which one you are showing.

StageWhat happensSuccess signal
1 · Chat literacyEveryone gets comfortable with plain Claude and learns when a single answer is enough.People stop over-specifying prompts.
2 · Cowork pilot, narrow scopeOne team, one recurring deliverable, one connected folder, Manual permission mode.A real artefact ships that would otherwise have taken a person half a day.
3 · InstrumentTurn on OTel (Team/Ent.). Decide the content-capture posture deliberately.You can answer "who used what, and what did it cost" without asking anyone.
4 · StandardisePackage the pilot's hard-won conventions as a plugin. Mark it Required.A second team gets the same quality on day one.
5 · Engineering rolloutClaude Code with managed settings, committed CLAUDE.md, permission policy. Use Anthropic's champion and communications kits.Analytics dashboard shows sustained weekly active use, not a spike.
6 · Connect the twoDispatch where plans allow; shared plugins everywhere.A single brief produces both the code change and the stakeholder note.
Closing line for the module

"The question isn't 'which product'. It's 'what am I willing to delegate, and how would I know if it went wrong?' Answer that, and the product choice makes itself."