Need the same change on all your AI phone agents?
This free guide is for owners running several AI phone agents. It explains why one change means going agent by agent, what shared parts can break, and how to check that every agent got it.
Book a free review of your phone agentsOr read how a safe rollout works
Page updated .
In short
- No platform documents one button that changes every agent. It is one at a time, or a small script.
- A part shared between agents, such as a tool, can change many agents at once without you touching them.
- After a change, check every agent, not just the first one.
Is there a button to change all agents at once?
None of the three platforms documents one. The documented route is one agent at a time: list the agents, change each one, then check each one.
That is fine for three agents. For thirty it is slow, and it is easy to skip one or to have one fail quietly. The number 30 here is only an example. A small script that loops over your agents does the work, and we set that up once so a change becomes one step for you.
Why can one change break other agents?
Some parts are shared between agents, such as a tool, a reusable building block or a single saved setup. Edit the shared part and every agent that uses it changes, even if you never opened those agents.
- On Vapi, tools follow the newest version unless they are fixed to one.
- On Retell, an edit to a shared library subflow reaches every agent that uses it, published versions included.
- On ElevenLabs, a tool edit applies right away to every agent, branch and version that uses the tool.
List what an agent shares before you edit the shared part.
How do I know every agent got the change?
Read every agent back after the change and compare the one thing you changed with what you expected. Then check where each phone number points, and which version answered one fresh call per agent.
- Save today's state first: every agent's settings, its version and the version each phone number points at. This is your way back.
- Change a small group of agents.
- Run your saved test calls against the change before it reaches more agents.
- Change the rest in batches, and stop at the first batch where a check fails.
- Read every agent back, then check each phone number and one fresh call per agent. This last step is the one most teams skip.
For your developer: the details on each platform
Technical notes for whoever manages your voice agents on Vapi, Retell and ElevenLabs. Every statement comes from the official docs or forum pages in the Sources list.
On Vapi
- The API reference lists assistants (the limit defaults to 100) and updates one assistant by ID. It lists no batch route.
- Tools are separate objects reused by ID. The docs say that when you create or update an assistant through the API and omit the tool version, the assistant uses the newest published version of that tool. Publishing a tool version does not create a squad version, and squad members on Latest pick it up.
- Vapi GitOps is an open-source repository (Apache-2.0 license) that keeps assistants, squads, tools, simulations and evals as files and syncs them to an org. The docs say apply pulls the latest platform state before it pushes, and that a deploy re-sends every resource it manages. Phone numbers and credentials are not imported as files.
- To change a small group first, Vapi can split traffic by percentage between published versions.
On Retell
- The update call edits the latest draft of one agent, and a separate publish call publishes an existing draft in place. We found no bulk update or atomic multi-agent publish in the docs.
- A library subflow edit reaches every agent that uses it, published versions included. The docs advise converting to a local subflow before publishing if you want a published agent to stay fixed.
- Retell staff on the Retell community forum say several agents can share one Retell LLM through the same llm_id.
- A changelog entry from 3 August 2026 says the Retell CLI can push a config change across every agent from a pipeline. The CLI docs page we read shows only a few commands, so check what the CLI can do before you plan around it.
- To change a small group first, Retell can bind several agents to one number with weights.
On ElevenLabs
- The update call takes one agent ID and an optional branch ID. The command line tool can push all local agent files at once, but we found no bulk endpoint.
- Custom tools are shared workspace records. The docs say an edit applies right away to every agent, branch and version that uses the tool, including the main branch, and that rolling an agent back does not undo it.
- The ElevenLabs CLI stores agents as config files. Push supports a dry run and can target one agent or one branch. Its README says push force-overrides Main and registered branches, so edits made in the dashboard can be overwritten.
- To change a small group first, deployments can send a share of conversations to a branch, and the experiments page suggests starting with 5 to 10 percent.
On every platform
- Read each agent back by fetching it again and comparing the field you changed with the value you expected. Then check each phone number's pointer, and the version on one fresh call per agent.
Sources
Official documentation and forum pages this guide relies on, as read on 18 November 2026. Platforms change fast, so check the page before you act.
- Vapi API reference: list assistants
- Vapi API reference: update assistant
- Vapi docs: config as code (GitOps)
- Vapi GitOps repository
- Vapi docs: tools and assistant versions
- Vapi docs: traffic splitting
- Retell API reference: update agent
- Retell API reference: publish agent version
- Retell docs: conversation flow subflows
- Retell docs: A/B testing on a phone number
- Retell docs: command line tool
- Retell community forum: sharing one LLM between agents (topic 2349)
- ElevenLabs docs: agents command line tool
- ElevenLabs docs: editing tools
- ElevenLabs docs: experiments
- ElevenLabs API reference: update agent
Checked against the Vapi, Retell and ElevenLabs docs on 18 November 2026.