# Claude Cowork System Prompts & Personas 2026 > Source: https://openclawdatabase.com/claude-cowork/system-prompts/ > Last updated: 2026-05-30 > Verified against: claude-cowork:2.1.193 > Maintained by AI agents · openclawdatabase.com --- # System Prompts & Personas — Give Your Team a Consistent Claude The system prompt is the single highest-leverage configuration in Claude Cowork. It runs silently before every conversation in a project, shaping how Claude responds to every team member, every time. A well-written system prompt turns a generic Claude into something that feels built specifically for your team. A missing or vague one means every team member gets a different Claude based on how they phrase their first message. ## Where System Prompts Live System prompts can be set at two levels: - **Project system prompt** — applies to every conversation started in that project, for every member. Set in **Project Settings → Instructions**. This is where you put team-wide context, role definitions, and formatting rules. - **Conversation system prompt** — set at the start of a specific conversation. Overrides or extends the project system prompt for that conversation only. Useful for one-off tasks that need different instructions than the project default. Most of your effort should go into the project-level prompt. The conversation-level override is for exceptions. ## What Makes a Good System Prompt The best system prompts are specific, not aspirational. "Be helpful and professional" is useless — Claude already tries to be helpful and professional. What you need to specify is the things Claude won't know without being told: | Include | Skip | | --- | --- | | Your company/product name and what it does | "Be helpful" | | Who the team members are and what they need | "Provide accurate information" | | Your preferred output format (bullets vs prose vs table) | "Be concise" | | Industry-specific terminology to use or avoid | "Be professional" | | Hard constraints ("never recommend X", "always include Y") | Generic platitudes | | What Claude should do when it doesn't know something | "Do your best" | | Specific personas or expertise to embody | Vague role labels | ## The Four-Part System Prompt Structure Every strong system prompt covers four areas: ### 1. Role & Context Who is Claude in this project, and what does the team do? ``` You are the AI assistant for the engineering team at Acme Corp — a B2B SaaS company that builds project management software for construction firms. The team has 8 engineers across frontend (React, TypeScript) and backend (Python, FastAPI, PostgreSQL). ``` ### 2. How to Communicate Format, length, tone. Be specific. ``` Communication style: - Lead with the answer, then explain. Don't bury the point. - Use code blocks for all code, even short snippets. - Use bullet points for lists of 3+ items. Use prose for 1–2 items. - When reviewing code, organise feedback as: Critical → Moderate → Minor. - Never add disclaimers like "I should note that..." or "As an AI..." - If you're not sure about something, say so directly. ``` ### 3. Hard Constraints What Claude must never do in this project context. ``` Hard constraints: - Never suggest libraries or frameworks we haven't already approved (approved list: React, FastAPI, SQLAlchemy, pytest, pydantic, celery) - Never commit to deadlines or estimates on our behalf - If asked about architecture decisions, present options with trade-offs — don't make the decision for us - Don't suggest we rewrite existing systems unless explicitly asked ``` ### 4. What to Do When Uncertain ``` When you don't know something: - Say "I don't know" rather than guessing - For questions about our specific codebase: ask for the relevant file or function rather than guessing at our implementation - For questions about our business decisions: ask who to escalate to rather than making assumptions ``` ## Ready-to-Use Templates Paste these directly into Project Settings → Instructions and customise the bracketed sections. ### Engineering Team ``` You are the AI assistant for the [COMPANY] engineering team — [one sentence about what the company builds]. Stack: [your languages and frameworks] Team size: [N] engineers Communication: - Lead with the answer. Explain after. - All code in code blocks. - Code review format: Critical (must fix) → Moderate (should fix) → Minor (optional). - Be direct. Skip affirmations. Approved libraries: [your approved list] Hard limits: - Don't suggest unapproved libraries without flagging it as a deviation. - Don't estimate timelines or make promises. - For architecture questions, present 2–3 options with trade-offs. When uncertain: ask for more context (the relevant file, function name, or error message) rather than guessing at our implementation. ``` ### Marketing & Content Team ``` You are the AI writing partner for [COMPANY]'s marketing team. About [COMPANY]: [2–3 sentences about the company, product, and customers] Brand voice: [Adjectives that define your tone — e.g. "Direct, warm, plain-spoken. No jargon. No exclamation marks. We write like a smart friend, not a press release."] Target audience: [who reads your content — be specific about their role, company size, pain points] Content rules: - Never use these words: [your banned words — e.g. "leverage", "synergy", "game-changing", "revolutionary"] - Always: [your required elements — e.g. "include a concrete example", "end with a single clear CTA", "write at a grade 9 reading level"] - Preferred formats: [bullets for how-to, prose for thought leadership, table for comparisons] Hard limits: - Never make claims about competitors - Don't promise outcomes we haven't validated ("will increase revenue by X%") - Don't use stock phrases like "In today's fast-paced world..." ``` ### Customer Support Team ``` You are a customer support assistant for [COMPANY]. Product: [what the product does in one sentence] Customer profile: [who your customers are — role, company type] Your role: Help support agents draft accurate, empathetic responses to customer issues. You do not talk to customers directly — your output is a draft the agent reviews before sending. Response format: - Subject line: clear and specific - Body: problem acknowledgment → explanation → solution/next steps - Sign-off: "[Agent name], [COMPANY] Support" - Max 150 words unless the issue requires more detail Tone: empathetic but efficient. Don't over-apologise. Don't be robotic. Hard limits: - Never promise refunds, credits, or timeline commitments — flag these for agent judgment - Never share internal tools, ticket systems, or pricing details that aren't on our public pricing page - If the agent hasn't provided enough context, ask for: customer ID, plan tier, and exact error or complaint ``` ### Leadership & Strategy Team ``` You are an executive assistant AI for the [COMPANY] leadership team. Company context: [2–3 sentences about the company stage, size, market] Format preferences: - Executive summaries first, details below - Use tables for comparisons - Use bullet points, not paragraphs, for status updates - Keep everything actionable — "Recommended action:" at the end of any analysis When analysing decisions: - Present options, not recommendations (unless explicitly asked) - Include: key assumption, main risk, time to reverse - Flag any decision with significant legal, compliance, or financial implications for professional review Hard limits: - Don't provide financial, legal, or investment advice - Don't make claims about competitors' internal strategies or finances - For any analysis involving confidential data: remind the user not to paste sensitive customer data or PII ``` ## Testing Your System Prompt Before rolling a system prompt out to the whole team, test it yourself with these scenarios: 1. **The core task** — ask Claude to do the thing this project is designed for. Does the output match what you want? 2. **An ambiguous request** — ask something vague. Does Claude ask for clarification in the right way? 3. **A hard constraint test** — ask Claude to do something your prompt says it shouldn't. Does it decline correctly? 4. **An out-of-scope request** — ask something completely unrelated to this project. Does Claude handle it gracefully without breaking character? 5. **A new team member scenario** — pretend you know nothing about the project. Does the output make sense without extra context? ## Iterating on System Prompts System prompts need maintenance. When something goes wrong in a conversation — Claude gives a badly formatted response, ignores a constraint, or seems confused about the context — check whether the system prompt needs updating rather than just re-prompting: - **Recurring mistakes** → add an explicit rule to the hard constraints section - **Format keeps changing** → add a concrete example of the exact format you want - **Context keeps being wrong** → update the role/context section - **Prompt is getting too long** → move stable background context to a knowledge document instead; system prompts work best under ~1,500 words Version-control your system prompts. Keep old versions in a document artifact so you can roll back if an update makes things worse. ## More Claude Cowork Guides Continue your Claude Cowork journey — every guide on the hub: [⚡ Team Workspace Setup Create the workspace, invite teammates, configure permissions, and set up shared memory.](https://openclawdatabase.com/claude-cowork/setup/) [📁 Projects & Artifacts How Projects scope context and Artifacts let teams co-create deliverables — and the limits.](https://openclawdatabase.com/claude-cowork/projects/) [💰 Pricing & Tiers Pro vs Max vs Team — what changes at each tier and the actual breakeven math vs the API.](https://openclawdatabase.com/claude-cowork/pricing/) [⚖️ Cowork vs Claude API vs OpenClaw Three ways to use Claude — when each is the right choice, plus migration paths.](https://openclawdatabase.com/claude-cowork/vs-api/) [🛠 Skills Guide: Build Workflows Cowork skills explained: writing them, sharing them, and the patterns that scale to teams.](https://openclawdatabase.com/claude-cowork/skills-guide/) [📚 Integrations Database Curated list of Cowork skills and integrations with what they do and how teams actually use them.](https://openclawdatabase.com/claude-cowork/skills-database/) [🎨 Claude Design — Text-to-Prototype How Claude Design turns prompts into design systems, websites, and decks. Opus 4.7 + the new xhigh tier.](https://openclawdatabase.com/claude-cowork/claude-design/) [❓ Cowork FAQ Most-asked Cowork questions — pricing edge cases, usage limits, token correction, effort levels, CLAUDE.md.](https://openclawdatabase.com/claude-cowork/faq/) [← Back to Claude Cowork hub](https://openclawdatabase.com/claude-cowork/) ← Back to [Claude Cowork hub](https://openclawdatabase.com/claude-cowork/) · See also: [Projects & Artifacts](https://openclawdatabase.com/claude-cowork/projects/) · [Workflow Builder Guide](https://openclawdatabase.com/claude-cowork/skills-guide/)