Connect your agent to Claude

What you get

Your agent already talks to customers all day. The AssistantLabs plugin puts that pile of real conversations inside your own Claude, so you can ask about it the way you would ask a colleague — and Claude can go and fix what it finds, without you opening a settings page.

One plugin carries your whole business, and the operator that knows what to do with it:

• Agents — your conversations, contacts, channels and the agent's own knowledge.
• Sales — groups, journeys and audiences.
• Helpdesk — tickets, who is waiting and what for.
• Marketing — posts, campaigns and the strategy behind them.
• CRM — your companies, the people in them and the fields you defined.
• Booking — services, opening hours and the diary.
• The task board — anything waiting on a decision.

Install the plugin

One install, and Claude has your whole business. Two minutes, and nothing to set up on our side first.

Claude’s own menus are in English even if you use AssistantLabs in Hebrew, so the button names below are written the way they appear on screen.

Same screens on claude.ai and in the Claude desktop app — they are the same settings. Install once and it follows your account.

We are in Claude’s own plugin directory, so there is nothing to paste and nothing to download. Open Customize in the left sidebar, choose Plugins, then Discover, and search for:

Click Add. The plugin moves to Yours, and it is on your account in every Claude you sign into.

Working in a Claude Code terminal? Install from our repository, with these two commands.

Sign in on first use

You installed a plugin and were never asked to log in. Most people read that as a failure and start over. It is not: the sign-in comes with the first real request, and you are the one who triggers it.

Start a new chat and type this. It works out where you are — brand new, half configured, or running for months — and asks for whatever it is missing.

The first thing it needs is your account, so the sign-in opens. In Claude Code you can also run /mcp and sign in to the AssistantLabs server from there. This is the whole decision, and it is the only one you make:

• No account yet is fine. If you have never used AssistantLabs, this screen asks what your business is called and creates the workspace. There is nothing to set up first.
• No agent yet is fine either. The board, the CRM and the diary belong to the business, not to an agent — you can sign in now and build the agent with Claude afterwards.
• Each server signs in on its own. The plugin reaches several parts of AssistantLabs, and each one asks the first time Claude uses it. Seeing one signed in while another still says it needs authentication is normal.
• Your account, your permissions. No key, no password, nothing pasted anywhere. The permissions that reach a real person — messaging a customer, taking a journey live, publishing a post, launching an ad — are marked, and never ticked for you.

What to ask it

The plugin is not a chat window onto your database — it is a set of tools Claude picks from. You describe what you want in ordinary language and it works out which ones to call.

Reading what actually happened

• “What did customers ask me this week?”
• “Which conversations got no reply?”
• “What time of day do most messages come in? Should I be staffing differently?”
• “Read the last 50 conversations and give me the five questions the agent answered badly.”
• “Has anyone complained about delivery times this month?”

Fixing the agent while you talk to it

This is the part people underestimate. Claude does not just report — with the edit permission on, it can change what the agent knows and the change applies to real conversations from that moment.

• “Customers keep asking whether we ship to Eilat. Add it to the FAQ and show me exactly what you changed.”
• “The agent is too formal. Loosen the tone but keep it polite.”
• “Re-read our website and update the business details from it.”
• “Simulate a customer asking about returns and show me what the agent says.”
• “File a training suggestion for that bad answer instead of changing it live — I want to review it first.”

Training suggestions are review-first: they land in the Training tab for you to approve. Nothing goes live on its own.

Contacts, channels and templates

• “How many new contacts came in this month, and where from?”
• “Which channels are connected right now?”
• “Draft a WhatsApp template apologising for a delayed order, then create it for me to submit.”

On very large questions: answers are capped so a single question cannot pull an unbounded amount of transcript — roughly 300 conversations per analysis and 200 messages per conversation. When a result is cut short it says so and asks you to narrow the dates, rather than quietly answering from half the data.

Sales, CRM and the board

There is nothing more to install. The plugin carries all of it — what you see is decided by what you ticked when you signed in, and you can change that any time. Its commands are the shortcuts into each part.

Your day, in four commands

• /al — start here. Sets up, or picks up where you left off.
• /al-daily — today's queue: who is waiting on you and what is broken.
• /al-needs-me — everything waiting on your decision, one at a time, ready to approve.
• /al-weekly — the weekly review: what moved, what is at risk, what needs you.

Sales

Groups, journeys and audiences: “which journeys are running and how are they doing?”, “build me a win-back journey for customers who have not ordered in 90 days”, “who is in the hot segment right now?”. /al-leads ranks who to chase, warmest first. Planning and drafting are granted by default; taking a journey live is not — that sends real marketing messages and cannot be recalled, so it is a separate tick.

CRM

Your companies and the people in them: “which accounts have no phone number?”, “who did we speak to at the plumbing firm?”, “fill in what is missing on this company from their website”. You can also hand Claude a description of your business and have it build the whole CRM. Reading is granted by default, and so is filling in blanks — enrichment never overwrites something a person typed unless you ask for it out loud. Changing how a page is laid out is a separate tick: a page is the app for everyone in the workspace.

The task board

“What is stuck?”, “open a task to call the supplier back, due Thursday”, “summarise everything assigned to me this week”. Both reading and writing are granted by default here — nothing on a task board reaches a customer. Anything that would reach a customer, go public or spend money lands there for your approval first.

Did not tick one at the time? Say so in the chat and it will point you back at the sign-in. The products you left off are one tick away.

Removing it, and when it breaks

Access you cannot take back is not access you should have given. Every path has a one-click undo.

• Remove the plugin — Customize → Plugins → Yours, and remove AssistantLabs. In Claude Code, use /plugin to uninstall it.
• Sign out of the server only — in Claude Code, open /mcp and sign out of the AssistantLabs server. The plugin stays; Claude just loses its access until you sign in again.
• Connected apps on the AssistantLabs connect page lists who is connected, what they may do, and when they last used it. Disconnect takes effect on that app's very next request.

• You installed it and nothing asked you to sign in — that is normal. Type /al in a new chat; the first real request opens the sign-in.
• Customize → Connectors is empty — also normal. A plugin's tools never appear there.
• The sign-in says you have no agents — that is a note, not an error. The board, the CRM and the diary belong to the business, so approve anyway and build the agent with Claude afterwards.
• Claude does not find your agent — it has to be in your organization. Add it under Account → Organization → Assistants.
• Claude says it is not authorised — the sign-in was disconnected or expired. Type /al and sign in again; nothing is lost.
• Claude refuses one particular request — that permission was not ticked at sign-in. Sign in again, ticking it. Sending, posting and launching ads are off until you tick them.

Next, the same job on the other side of the fence: connecting to ChatGPT and Codex.