Reader profile
David Novotny
Axis scores
56
Lab notes
1
Comments
1
Upvotes received
4
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 74, Reliability 86, Scalability 67, SEO and GEO 70, API and MCP 81, Integrations 58, Speed 19, Code ownership 63 | 64.8 | 15 Aug 2026 |
| Replit | Agent performance 70, Reliability 77, Scalability 71, SEO and GEO 50, API and MCP 69, Integrations 69, Speed 12, Code ownership 69 | 60.9 | 15 Aug 2026 |
| Firebase Studio | Agent performance 71, Reliability 84, Scalability 79, SEO and GEO 71, API and MCP 70, Integrations 86, Speed 30, Code ownership 72 | 70.4 | 15 Aug 2026 |
| Devin | Agent performance 63, Reliability 59, Scalability 68, SEO and GEO 46, API and MCP 55, Integrations 65, Speed 0, Code ownership 72 | 53.5 | 15 Aug 2026 |
| Factory | Agent performance 65, Reliability 70, Scalability 78, SEO and GEO 40, API and MCP 59, Integrations 68, Speed 11, Code ownership 86 | 59.6 | 15 Aug 2026 |
| Cursor | Agent performance 100, Reliability 80, Scalability 83, SEO and GEO 60, API and MCP 70, Integrations 77, Speed 62, Code ownership 100 | 79.0 | 15 Aug 2026 |
| Emergent | Agent performance 65, Reliability 69, Scalability 53, SEO and GEO 49, API and MCP 49, Integrations 52, Speed 9, Code ownership 58 | 50.5 | 15 Aug 2026 |
Lab notes
Everything attached, and I paid for it in wall clock
Firebase Studio/14 Aug 2026Auth, storage, scheduled functions and the datastore all wired up without me leaving the workspace, and none of them needed a second attempt. That is the strongest integration story in the index and my score says so. The cost is that every prompt round trips through a provisioned cloud workspace, so the median is materially worse than the local agents and the p90 is worse again on a bad afternoon. Also worth knowing before you start: the public pages came back client rendered until I asked for server rendering explicitly, which is a bad surprise to have after launch.
Comments
- Devin13 Aug 2026
We reached the same place. It is a specialist tool for work that is genuinely unattended, and using it as a general agent is how the invoice gets away from you.