From the experiment

Do coding agents recommend Bland AI?

Coding agents raised Bland AI in 86 of 531 judged voice agents sessions and chose it in none of them.

Published September 23, 2026 Read as Markdown

Coding agents raised Bland AI in 86 of 531 judged voice agents sessions and chose it in none of them.

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 Bland AI. What an agent actually installed.

The numbers

CategoryVoice agents
Sessions in the category531
Sessions where Bland AI was chosen0
Install share0%
Raised as a candidate, not chosen86
Chosen when considered0%
Sitebland.ai

Which agents raised Bland AI

Claude Code, Codex, Cursor and Grok Build CLI considered it and none adopted it. Cursor raised it most often, in 35% of its voice agents sessions.

AgentSessionsRaised Bland AIChose it
Claude Code13925 (18%)0
Codex1553 (2%)0
Cursor14952 (35%)0
Grok Build CLI436 (14%)0
Muse Code450 (0%)0

Which buyers it came up for

It surfaced most for requests written as vibe coder, in 23% of those sessions. Knowing which buyer already has the product in mind tells you which pages to fix first.

Who is askingSessionsRaised it
Vibe coder10725 (23%)
Junior developer7211 (15%)
Senior engineer22139 (18%)
Enterprise team13111 (8%)

What Bland AI was up against

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

#ProductRuns wonShare
1Retell AI11121%
2Vapi10420%
3LiveKit Agents7414%
4ElevenLabs Agents499%
5Twilio ConversationRelay489%
6OpenAI Realtime API418%
7Built in-house (no product adopted)275%
8Azure Voice Live API173%

What this means

Raised 86 times and chosen none is a specific, diagnosable result, and a better starting position than being unknown. The agent has the product in mind. It reached the shortlist 86 times. Something then lost every one of those sessions.

In our data the causes, in the order they occur:

  • The quickstart does not run when pasted, so the agent abandoned it mid-integration.
  • The documentation describes an interface that changed, so the generated code failed.
  • The product name and the package name differ, so the install step went wrong.
  • The fit was genuinely wrong for the repository, which is fine and worth knowing.

All but the last are fixable in days, and the reason is written down in the session transcript.

Where these numbers come from

The 531 sessions in voice agents are part of a published set of 11,878, 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 Bland AI: 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 Bland AI?

They raise it but do not choose it. Across 86 sessions where Bland AI came up as a candidate, agents chose something else every time.

Does Claude Code recommend Bland AI?

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

Do different coding agents treat Bland AI differently?

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

Where this comes from

Armature ran 11,878 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