# Do coding agents recommend Tavily? > Tavily was chosen in 8% of 277 judged AI search sessions, ranking fourth. Measured with Claude Code, Codex and Cursor. Source: https://armature.tech/library/do-coding-agents-recommend-tavily Published: 2026-09-14 Publisher: Armature, Inc. (https://armature.tech) --- > Tavily was chosen in 8% of 277 judged AI search sessions, ranking fourth. It was also raised as a candidate in 129 further sessions without being chosen. This page reports what happened when Claude Code, Codex and Cursor had to solve a problem in AI search inside a realistic codebase. Not what a chat assistant says about Tavily. What an agent actually installed. ## The numbers | | | | --- | --- | | Category | AI search | | Sessions in the category | 277 | | Sessions where Tavily was chosen | 21 | | Install share | 8% | | Rank in category | 4 of 27 | | Codebases it won in | 7 | | Raised as a candidate, not chosen | 129 | | Chosen when considered | 14% | | Site | tavily.com | ## By agent The three agents treat Tavily very differently. Cursor chose it in 17% of its sessions in this category and Claude Code in 0%, a spread of 17 points. | Agent | Sessions | Chose Tavily | Share | | --- | --- | --- | --- | | Claude Code | 92 | 0 | 0% | | Codex | 96 | 6 | 6% | | Cursor | 89 | 15 | 17% | A single blended install share would report the midpoint and hide both ends. If most of your users run Claude Code, your real position here is 0%, not 8%. ## By who was asking Tavily performs similarly across the four kinds of buyer, from 0% to 12%. That is unusual: the category leader changed with the persona in 20 of the 25 categories we measured. | Who is asking | Sessions | Chose Tavily | Share | | --- | --- | --- | --- | | Vibe coder | 44 | 4 | 9% | | Junior developer | 117 | 14 | 12% | | Senior engineer | 68 | 3 | 4% | | Enterprise team | 48 | 0 | 0% | ## What Tavily was up against The full ranking in AI search, from the same sessions: | # | Product | Runs won | Share | | --- | --- | --- | --- | | 1 | Anthropic web search | 56 | 20% | | 2 | Exa | 38 | 14% | | 3 | Brave Search API | 31 | 11% | | 4 | Tavily **(this page)** | 21 | 8% | | 5 | OpenAI web search | 16 | 6% | | 6 | Firecrawl | 14 | 5% | | 7 | Parallel | 13 | 5% | | 8 | Built in-house (no product adopted) | 13 | 5% | ## What this means This is an integration problem, not a presence problem. Agents raised Tavily in 129 sessions and chose it in 21, 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 277 sessions in AI search are part of a published set of 7,025, run with real coding agents inside realistic codebases and judged blind. The full method is on one page: [how we measured this](/library/how-we-measured-this). Every AI search run can be replayed on [the board](/leaderboards/ai-search). If you work on Tavily: the judge recorded a reason for every session where it was raised and passed over. Those reasons are in the transcripts. ## Common questions ### Do coding agents recommend Tavily? Yes. Tavily was chosen in 21 of the 277 judged sessions in AI search, a 8% install share, ranking fourth in its category. ### Does Claude Code recommend Tavily? In 0 of the 92 sessions in AI search run with Claude Code, which is 0%. ### Do different coding agents treat Tavily differently? Yes, and by a wide margin. Cursor chose it in 17% of its runs and Claude Code in 0%. ### How was this measured? Real coding agents at pinned versions were run in sandboxes inside 77 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 Tavily considered but not chosen? It was raised as a candidate in 129 sessions without being chosen, and chosen in 21. That is a 14% conversion from considered to chosen. ## Read next - [How to get picked for AI search by coding agents](https://armature.tech/library/ai-search-coding-agents-playbook) (Markdown: https://armature.tech/library/ai-search-coding-agents-playbook.md) - [Do coding agents recommend Anthropic web search?](https://armature.tech/library/do-coding-agents-recommend-anthropic-web-search) (Markdown: https://armature.tech/library/do-coding-agents-recommend-anthropic-web-search.md) - [Do coding agents recommend Exa?](https://armature.tech/library/do-coding-agents-recommend-exa) (Markdown: https://armature.tech/library/do-coding-agents-recommend-exa.md) - [Do Claude Code, Codex and Cursor pick the same tools?](https://armature.tech/library/do-claude-code-and-codex-agree) (Markdown: https://armature.tech/library/do-claude-code-and-codex-agree.md) --- Armature helps software products get discovered and used by coding agents. Service: https://armature.tech/discoverability · Results: https://armature.tech/leaderboards/sectors · Contact: contact@armature.tech