Connect your Assistant Labs account to ChatGPT once. Then just ask — what came in this week, who is still waiting, why the agent got an answer wrong. It reads your real conversations and fixes the agent while you talk to it. In Codex, the same account runs the day for you and brings you the decisions.
Connects in about five minuteslist_conversationsFour people are still waiting. The longest has been 19 hours:
Yael — asked whether you deliver to Eilat. The agent never answered.
Dana — asked for a quote on 40 units.
patch_agent_moduleWhat actually changes
Not a chatbot with tools bolted on. The difference is who does the work and who makes the call.
One connector
One address covers all of it. You choose which parts to switch on when you sign in, and you can add the rest later without connecting anything again.
Conversations, customers and the agent itself
Every conversation your agent has had, the contacts behind them, and the settings that decide how it answers.
https://mcp.assistantlabs.io/mcpJourneys, audiences and outbound
The journeys that follow up on carts, orders and quiet customers — and how they are performing.
https://mcp.assistantlabs.io/mcpThe record of who you deal with
Your customers and companies with their whole history — in the fields your business actually uses.
https://mcp.assistantlabs.io/mcpThe work your business owes people
What is open, what is blocked, and what someone promised a customer — kept in one place instead of in your head.
https://mcp.assistantlabs.io/mcpThe connector is a read of your live account — nothing is copied, exported or stored on ChatGPT’s side.
It reads the real thing
ChatGPT reads the transcripts your customers actually sent: the questions, the follow-ups, and the moments the agent lost them. Ask in plain language and it finds the pattern across hundreds of chats.
list_conversationssearch_conversationsconversation_statsget_conversationIt can act, not just report
Finding a bad answer and fixing it are usually two different tools and two different days. Here they are one sentence. ChatGPT edits the agent’s knowledge, and you can have it rehearse the new answer before anything goes live.
patch_agent_moduleset_extra_instructionsscan_websitesimulate_conversationIt reaches your customers
The same conversation that surfaces a segment can write to it. ChatGPT pulls the contacts, drafts the message in your voice, and sends it through the channels you have already connected.
list_contactslist_segmentscreate_whatsapp_templatesend_whatsapp_templateThings to ask it
These are ordinary sentences, typed into ChatGPT. It works out which part of your account to read and answers from your real data.
How many conversations came in this week, and what did people ask about most?
Show me every chat where someone asked about delivery and didn’t get a straight answer.
Which customers are still waiting for a reply?
What are people complaining about lately?
The agent keeps saying we’re open on Saturday. We’re not — fix it.
Add a returns policy to the FAQ, in Hebrew.
Re-scan our website; we changed our prices.
Before you save that — show me how the agent would answer.
Who bought from us twice but hasn’t been back in three months?
Draft a WhatsApp update for everyone labelled VIP.
Reply to Dana and tell her the quote is on the way.
In Codex the operator installs as skills. Ask in your own words, or name the one you want — these are the ones you will want most days.
startBegin here. It works out where you are and takes you one step forward.briefWhat is happening right now — who is waiting, what is at risk, today’s three things.needs-meEverything waiting on your decision, one at a time, ready to approve.waitingEvery customer who has not been answered — with the replies already drafted.leadsWho to chase, warmest first, with what to say to each.moneyWhat is owed, what is at risk, what is coming in.agent-reviewWhere your agent answered badly this week — and the fix.autopilotA full unattended pass. Does everything. Sends nothing.The deal
The whole thing rests on this. It is not a setting you tune — it is the contract.
Everything reversible that nobody outside the business ever sees.
It acts, keeps the receipt, and mentions it once.
Every time. An approval yesterday is not an approval today.
It will never send a message because nobody was around to say no. An owner who is away is not a quiet yes — the decision waits for them, with the finished text attached.
When you are not at a screen
From your own business number — the one your customers already message and you already have saved. Not a second sender to learn to trust.
Not "shall I draft something for Dana?" — the exact message she would receive, word for word, so there is nothing left to do but decide.
Approve, No, or just write back — "yes", "not yet", "send it". It understands Hebrew and English, and it never reads a "don’t" as a yes.
Not "approved" — the actual outcome. If a send failed you hear that instead, because being told it went out when it did not is the one thing this design exists to prevent.
Replying never talks to your bot. Your own agent never answers you, never files you as a lead in your own customer list, and never sees the conversation.
It learns your business
A generic assistant is worthless. What makes it yours is a set of pages it keeps in your workspace and reads before it acts.
Not "friendly and professional" — actual sentences your people sent to actual customers. Drafts come back sounding like the business.
Tell it once that you do not deliver on Saturdays and it lands in the right place with the date, and fixes your agent if that was wrong too.
If Dana handles invoices and decides refunds up to ₪500, a ₪380 refund is Dana’s call and never reaches you at all.
Kept with your account rather than on one computer — so it still knows you from a new laptop, and when it works overnight with nobody there.
Security
A connector is a door into your business, so it is built to be narrow, inspectable and easy to shut.
The consent screen lists exactly what ChatGPT is asking for — reading conversations, editing the agent, sending messages. Untick anything you would rather keep to yourself.
Tools are built from the permissions you actually granted. A read-only connection is never even shown a tool that could change or send something.
The connector holds no copy of your data and no credentials of its own. Every question becomes one live request to your account, answered and forgotten.
You connect with your Assistant Labs login, so no key ever lands in a URL, a screenshot or a chat log. Access is bound to that one connector and expires on its own.
A connection reaches only the organization you signed in to, and only the agents inside it. If you run several, you pick which one it may see.
Disconnect it in ChatGPT, or cut it off from your Assistant Labs settings. Access stops immediately — there is nothing left behind to clean up.
Your permissions are enforced by the server, not asked of the model — a connection that cannot send is never handed a tool that sends.
Setup
Connect it to ChatGPT and you can ask your business anything. Install the operator in Codex and it runs the day for you. Most people start with ChatGPT and add Codex later.
Custom connectors live in ChatGPT’s developer mode. Nothing is downloaded and nothing runs on your computer — you paste one address and sign in.
In ChatGPT, open Settings → Apps & Connectors → Advanced and switch on developer mode. On a Business, Enterprise or Edu workspace an admin has to allow it first.
Choose Create, paste the connector address from Assistant Labs, and let ChatGPT scan the tools. Sign in with your Assistant Labs account and approve what it may do.
A new app starts as a draft — publish it to your own workspace, open a chat and ask it about your week.
The same account, one level up: it runs the day unattended and brings you the decisions. Codex reads one config file and a folder of skills — no marketplace, no developer mode. Run these from inside plugins/assistantlabs-codex.
One public repository, both builds. The Codex one is in plugins/assistantlabs-codex.
git clone https://github.com/Assistant-Labs/claude-pluginAppends the four Assistant Labs servers to your Codex config. Once per computer.
cat config.toml.example >> ~/.codex/config.tomlSigns you in the same way ChatGPT does, in your own account. Each connector is its own decision.
codex mcp login assistantlabsThe skills that make Codex run the business rather than just read it.
cp -R skills/* ~/.codex/skills/Say "brief me", or "who is waiting". Codex loads the matching skill on its own — there is nothing to memorise.
Questions
Still unsure about something? Message us and we’ll answer properly.
Ask us on WhatsAppConnect Assistant Labs to ChatGPT, find out what your customers have been asking while you were busy — and let Codex start handing you the decisions instead of the work.