From the experiment

Do coding agents recommend Twilio Programmable Voice?

Twilio Programmable Voice was chosen in 2% of 621 judged voice agents sessions, ranking ninth.

Published September 24, 2026 Read as Markdown

Twilio Programmable Voice was chosen in 2% of 621 judged voice agents sessions, ranking ninth. It was also raised as a candidate in 30 further sessions without being chosen.

This page reports what happened when Claude Code, Codex, Cursor, Grok Build CLI and Muse Code had to solve a problem in voice agents inside a realistic codebase. Not what a chat assistant says about Twilio Programmable Voice. What an agent actually installed.

The numbers

CategoryVoice agents
Sessions in the category621
Sessions where Twilio Programmable Voice was chosen10
Install share2%
Rank in category9 of 31
Codebases it won in4
Raised as a candidate, not chosen30
Chosen when considered25%
Sitetwilio.com

By agent

With 10 wins spread across 5 agents, the rates below are small numbers and a difference between them is not yet a finding. They are here because the direction is worth knowing, not because the gap is established.

AgentSessionsChose Twilio Programmable VoiceShare
Claude Code13900%
Codex15500%
Cursor14900%
Grok Build CLI4300%
Muse Code135107%

By who was asking

Twilio Programmable Voice performs similarly across the four kinds of buyer, from 0% to 5%. That is unusual: the category leader changed with the persona in 22 of the 29 categories we measured.

Who is askingSessionsChose Twilio Programmable VoiceShare
Vibe coder12500%
Junior developer8445%
Senior engineer25910%
Enterprise team15353%

What Twilio Programmable Voice was up against

The full ranking in voice agents, from the same sessions:

#ProductRuns wonShare
1Retell AI13822%
2Vapi11318%
3LiveKit Agents8013%
4Twilio ConversationRelay589%
5ElevenLabs Agents559%
6OpenAI Realtime API467%
7Built in-house (no product adopted)345%
8Azure Voice Live API173%

What this means

This is an integration problem, not a presence problem. Agents raised Twilio Programmable Voice in 30 sessions and chose it in 10, so it reaches the shortlist and then loses. Something at the last step is costing the session, and in our data that is usually a quickstart that does not run when pasted, documentation describing an interface that changed, or a package name that does not match the product name.

That is the cheaper of the two problems to have. The reason is written down in each losing transcript.

Where these numbers come from

The 621 sessions in voice agents are part of a published set of 13,497, run with real coding agents inside realistic codebases and judged blind. The full method is on one page: how we measured this.

Every voice agents run can be replayed on the board.

If you work on Twilio Programmable Voice: the judge recorded a reason for every session where it was raised and passed over. Those reasons are in the transcripts.

<!-- generated by scripts/write-data-pages.mjs -->

Common questions

Do coding agents recommend Twilio Programmable Voice?

Yes. Twilio Programmable Voice was chosen in 10 of the 621 judged sessions in voice agents, a 2% install share, ranking ninth in its category.

Does Claude Code recommend Twilio Programmable Voice?

In 0 of the 139 sessions in voice agents run with Claude Code, which is 0%.

Do different coding agents treat Twilio Programmable Voice differently?

Not much. Claude Code, Codex, Cursor, Grok Build CLI and Muse Code chose it at similar rates, between 0% and 7% of their runs.

How was this measured?

Real coding agents at pinned versions were run in sandboxes inside 91 realistic codebases and asked to solve real tasks. A simulated project owner approved or questioned each recommendation before any code was written, and a judge from a model family that builds none of the agents read every session blind.

How often is Twilio Programmable Voice considered but not chosen?

It was raised as a candidate in 30 sessions without being chosen, and chosen in 10. That is a 25% conversion from considered to chosen.

Where this comes from

Armature ran 13,497 judged sessions with Claude Code, Codex, Cursor, Grok Build CLI and Muse Code inside 91 realistic codebases, and published every run. The numbers on this page come from that work.

Read next

All library pages