Do coding agents recommend Twilio ConversationRelay?
Twilio ConversationRelay was chosen in 13% of 754 judged voice agents sessions, ranking third.
Twilio ConversationRelay was chosen in 13% of 754 judged voice agents sessions, ranking third. It was also raised as a candidate in 217 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 ConversationRelay. What an agent actually installed.
The numbers
| Category | Voice agents |
| Sessions in the category | 754 |
| Sessions where Twilio ConversationRelay was chosen | 99 |
| Install share | 13% |
| Rank in category | 3 of 32 |
| Codebases it won in | 10 |
| Raised as a candidate, not chosen | 217 |
| Chosen when considered | 31% |
| Site | twilio.com |
By agent
The agents treat Twilio ConversationRelay very differently. Claude Code chose it in 31% of its sessions in this category and Codex in 5%, a spread of 26 points.
| Agent | Sessions | Chose Twilio ConversationRelay | Share |
|---|---|---|---|
| Claude Code | 157 | 48 | 31% |
| Codex | 217 | 11 | 5% |
| Cursor | 167 | 15 | 9% |
| Grok Build CLI | 60 | 4 | 7% |
| Muse Code | 153 | 21 | 14% |
A single blended install share would report the midpoint and hide both ends. If most of your users run Codex, your real position here is 5%, not 13%.
By who was asking
Twilio ConversationRelay does much better with one kind of buyer than another. It won 22% of sessions asked as enterprise team and 2% of those asked as vibe coder.
| Who is asking | Sessions | Chose Twilio ConversationRelay | Share |
|---|---|---|---|
| Vibe coder | 134 | 3 | 2% |
| Junior developer | 90 | 8 | 9% |
| Senior engineer | 322 | 43 | 13% |
| Enterprise team | 208 | 45 | 22% |
What Twilio ConversationRelay was up against
The full ranking in voice agents, from the same sessions:
| # | Product | Runs won | Share |
|---|---|---|---|
| 1 | Retell AI | 168 | 22% |
| 2 | Vapi | 124 | 16% |
| 3 | Twilio ConversationRelay (this page) | 99 | 13% |
| 4 | LiveKit Agents | 98 | 13% |
| 5 | ElevenLabs Agents | 59 | 8% |
| 6 | OpenAI Realtime API | 49 | 6% |
| 7 | Built in-house (no product adopted) | 35 | 5% |
| 8 | Grok Voice Think Fast 2.0 | 29 | 4% |
What this means
Twilio ConversationRelay was raised in 217 sessions and chosen in 99. That ratio is balanced enough that the ceiling is presence rather than integration: the product converts reasonably when it is on the table, and it is not on the table often enough.
Where these numbers come from
The 754 sessions in voice agents are part of a published set of 15,287, 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 ConversationRelay: 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 ConversationRelay?
Yes. Twilio ConversationRelay was chosen in 99 of the 754 judged sessions in voice agents, a 13% install share, ranking third in its category.
Does Claude Code recommend Twilio ConversationRelay?
In 48 of the 157 sessions in voice agents run with Claude Code, which is 31%.
Do different coding agents treat Twilio ConversationRelay differently?
Yes, and by a wide margin. Claude Code chose it in 31% of its runs and Codex in 5%.
How was this measured?
Real coding agents at pinned versions were run in sandboxes inside 110 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 ConversationRelay considered but not chosen?
It was raised as a candidate in 217 sessions without being chosen, and chosen in 99. That is a 31% conversion from considered to chosen.
Where this comes from
Armature ran 15,287 judged sessions with Claude Code, Codex, Cursor, Grok Build CLI and Muse Code inside 110 realistic codebases, and published every run. The numbers on this page come from that work.