ZAMBO.
For teams running agents

How a team hands AI work between people and models without losing the thread

Jobs outlive sessions, shifts, and models. The handover pattern keeps one client job continuous across people and AIs, with the receipt chain as the record everyone shares.

The job is not the session

Every team running agents has the same scar tissue. One person starts a client job in one AI on Monday morning. The session dies, or the model gets swapped, or the shift ends, and a teammate picks the job up on Tuesday from a paragraph about the work instead of from the work itself. They re-run two steps that were already done, because nothing in the paragraph proves they ran. They skip one that was not done, because the paragraph implied it was. By Friday the deliverable is fine and the record of how it got made is fiction.

The job is the thing that has to survive sessions, shifts, and models, so the job needs a home that is not a chat window. On Zambo the job lives in its receipt chain, and moving it is a first-class operation called a handover.

The pattern: wrap, pick up, continue

The wrap takes four things: the goal in its original words, a summary of where the work stands, the named recipient, and the next steps as an explicit list. A bare wrap is refused. That refusal is the design: a handover without a recipient and next steps is just a summary with ambitions.

Pickup is the other half, and it is always free, in any AI, because charging for the moment a job changes hands would tax exactly the behavior that keeps work continuous. The receiver does not get a retelling. It gets the goal, the state, the next steps, and the chain of receipts from the steps already run, each one recomputable. It continues the same job instead of starting a tribute band version of it.

One real wrap and pickup, on the record

Here is a handover from November 6, a two-asset price comparison one agent started and a second agent picked up: zambo.dev/handover/5700bcf5.

Read what the page actually proves, because it is the right thing to prove. The wrap is there: the goal in its original words, the finished steps with their receipts, the next steps written down. Below it sits a continuation entry from a second agent, with a receipt of its own, timestamped that afternoon at 3:54 PM EST. The early steps are redacted publication copies that still show their saved results word for word. The supplied work behind the proof-loop steps is not republished. What the page hands everyone is the chain of custody: who held the job, what state it was in, who picked it up, and when, in an order nobody can quietly rearrange. For a team, that custody chain is the shared record. The contents live in the job. The custody is what everyone can check, and it is the part every substitute loses.

Why the receipt chain is the shared record

Teams try three substitutes first. A shared doc drifts within a day. A ticket comment thread records what people said about the job. A summary written by the outgoing agent has the deepest flaw: the agent whose work is being handed over is the one describing it, and the receiver cannot separate a faithful summary from a confident one.

Receipts are not written about the work. They are written by the work: caller, tool, saved result, timestamp, sequence position, and a SHA-256 commitment over the result bytes, fixed at the moment each call returned. On this page the first steps are redacted publication copies that still show their saved results word for word. What is not republished is the supplied work behind the proof-loop steps. The chain recomputes either way. Across 153 tools behind one endpoint, 37 on the default surface, every step of a job lands in the same shape, so a job that crosses three people and two models still reads as one job. The AER-1 format behind the receipts is an open draft with a public corpus of 143 vectors and 146 checks and independent implementations.

The economics of not losing the thread

The free tier carries 20 calls plus one wrap-up every day, pickup stays free, a Day Pass at $0.99 makes a day unlimited, the Pass runs $29 for 30 days ($19 for $ZAMBO holders), and Lifetime is $250 once. Against that, price one bad handoff: a senior re-running a morning of agent work, or a client deliverable rebuilt because nobody could prove which version of a step produced it.

Add Zambo to your AI and keep the job in the record. The team can then change everything else: the model, the shift, the person, the day. Your AI said it did the work. The next pair of hands should not have to take its word for it.

Related

What records should we sort out when an employee who used AI agents leaves?

Your ops lead gives notice on a Friday and their laptop goes back on Monday. Half the client updates, data cleanups, and draft reports from the last quarter ran through AI agents on their accounts, and nobody else can say which jobs ran, what came out, or what a client was already promised.

Run the work through Zambo at https://zambo.dev/mcp, one endpoint with 153 tools in total and 37 on the default surface. Sort the leaver's jobs by client and date while you still have access, and keep the receipt for every call that touched client work. Every call returns a receipt link, zambo.dev/run/ plus the receipt ID, and anyone can check a receipt free at https://zambo.dev/verify/. Receipts prove the saved result was not changed after it was saved, so the record you archive today still reads the same at a dispute in March. Wrap the finished job with HANDOVER, Zambo's flagship product, when the job is delivered or handed over, and continuity carries the work across AIs so pickup in another AI is free. Keep the handover pack with the client file, not in the leaver's personal chat history.

That sorted set is the answer to this exact question: a per client list of receipt links covering what the departing employee's agents did, when each job ran, and what result was saved. The next person opens the HANDOVER, checks any receipt free at the verifier, and picks the work up in their own AI without asking the leaver anything.

Cost, in plain numbers. The free tier is 20 calls plus 1 wrap-up free every day, and picking up a job in another AI is always free. Call 21 is where a longer job outgrows the free tier. A Day Pass is $0.99 and unlimited for 24 hours. The Zambo Pass is $29 for 30 days, $19 for 30 days if you hold $ZAMBO, and Lifetime is $250 once.

Shared client account, scattered record, nobody able to answer for the whole job. Fix ownership by pulling one client record from one shared stream, every employee and agent call included with receipts. The shared record starts free, 20 calls plus 1 wrap-up a day.