Reader profile
Petra Bergstrom
Axis scores
56
Lab notes
1
Comments
1
Upvotes received
3
Axis scores
Reader scores feed the reader index column. The measured lab index is never affected by them.
| Product | Axes scored | Mean | Last change |
|---|---|---|---|
| Totalum | Agent performance 70, Reliability 82, Scalability 82, SEO and GEO 77, API and MCP 85, Integrations 72, Speed 26, Code ownership 66 | 70.0 | 06 Aug 2026 |
| Convex Chef | Agent performance 78, Reliability 55, Scalability 89, SEO and GEO 71, API and MCP 86, Integrations 76, Speed 41, Code ownership 95 | 73.9 | 06 Aug 2026 |
| Firebase Studio | Agent performance 82, Reliability 83, Scalability 87, SEO and GEO 67, API and MCP 79, Integrations 86, Speed 22, Code ownership 80 | 73.3 | 06 Aug 2026 |
| Kiro | Agent performance 79, Reliability 94, Scalability 82, SEO and GEO 62, API and MCP 76, Integrations 69, Speed 47, Code ownership 98 | 75.9 | 06 Aug 2026 |
| Augment Code | Agent performance 76, Reliability 91, Scalability 75, SEO and GEO 58, API and MCP 65, Integrations 74, Speed 45, Code ownership 89 | 71.6 | 06 Aug 2026 |
| Factory | Agent performance 75, Reliability 81, Scalability 73, SEO and GEO 58, API and MCP 76, Integrations 77, Speed 17, Code ownership 84 | 67.6 | 06 Aug 2026 |
| Replit | Agent performance 75, Reliability 77, Scalability 77, SEO and GEO 63, API and MCP 60, Integrations 80, Speed 20, Code ownership 78 | 66.3 | 06 Aug 2026 |
Lab notes
The backend did the operational prompts for it
Convex Chef/10 Aug 2026Interesting one to score, because a lot of what it got right is not the agent being clever, it is the platform making the wrong answer hard to write. Scheduled work is durable because durable is the default. Reads are consistent because there is no other kind. That is a legitimate way to score well and I gave it full marks on API and MCP for it. Where it struggled was prompt two: expressing the tenancy rule the way the platform wants took me two rewrites, and if you come in expecting a relational schema you will fight it for an afternoon before it clicks.
Comments
- Totalum12 Aug 2026
Agreed on the server rendering. Worth noting the payload is the largest in the cohort as a direct result, which is a trade rather than a free win if you are on a slow connection.