Merge builds product and business tools with OpenAI technology
- ID
- 43596
- Status
- summarized
- Published
- 05 Nov 2026, 4:00 PM
- Fetched
- 06 Nov 2026, 7:33 AM
- Provider
- OpenAI News
- Category
- ai-labs
- Original URL
- https://openai.com/index/merge-builds-with-openai
- Source URL
- https://openai.com/news/rss.xml
Summary
- Score
- 3.0
- Created
- 06 Nov 2026, 7:34 AM
- Tags
- Audience
- ai_agent_usersai_ml_learnerssaas_founders
What happened
OpenAI published a customer story (dated 5 Nov 2026) on Merge, a North America startup whose products cover customer-data integrations (Merge Unified), secure tool access for AI agents (Merge Agent Handler), and model routing/cost controls (Merge Gateway). CEO and co-founder Shensi Ding is quoted using Codex to review product code — including a new provisioning tab in Merge for Workforce — while colleagues use GPT-6 Astra for product testing and marketing. The one hard number in the piece is a vendor claim: Merge says tool calls through its connector product succeed 99.9% of the time, versus roughly 60% for public MCP servers.
Why it matters
This is OpenAI marketing a customer, not independent testing, so treat the 99.9%-vs-60% MCP reliability figure as an unverified claim from the vendor selling the alternative. If you are wiring agents to third-party tools, the actionable step is to instrument your own per-tool success and retry rates before deciding whether a managed connector layer like Merge Agent Handler is worth paying for — the article gives you no methodology, sample size, or definition of 'success' to reproduce that comparison. Nothing here changes what you build this week.
Discussion angle
The 99.9% vs ~60% MCP tool-call success claim has no stated methodology — what would you actually measure (per-tool error rate, retry count, schema-validation failures) to test that on your own agent stack, and at what failure rate would you stop self-hosting MCP servers?