Average Ratings 0 Ratings
Average Ratings 1 Rating
Description
Cognigram is an online platform designed to automatically analyze data and produce reports that summarize the outcomes of cognitive tests. Typically, completing the Cognigram assessment requires around 10 to 15 minutes. This tool is aimed at supporting healthcare professionals by providing an objective evaluation of cognitive function for individuals ranging from 6 to 99 years of age. The resulting reports are user-friendly for clinicians and include comparisons to normative data from healthy, age-matched individuals. The assessment process, which takes roughly 15 minutes, evaluates four distinct cognitive domains. Results are computed automatically, ensuring efficiency. The assessment consists of four tests that utilize playing cards to pose straightforward "yes" or "no" questions, with instructions and practice sessions provided for clarity. Furthermore, the Cognigram system can be utilized not only for a one-time assessment but also for monitoring cognitive changes across multiple evaluations, making it a versatile tool in cognitive assessment.
Description
SWE-2 is a software engineering model from Cognition built for agentic coding tasks that require strong performance at lower computational and monetary cost. It is post-trained from the Kimi K3 base model and extends Cognition’s earlier SWE-1.7 training approach with a new reinforcement learning method for jointly optimizing multiple reasoning-effort settings. Medium, high, and maximum effort modes provide different tradeoffs between speed, cost, exploration, and verification depending on task complexity. The model is trained to inspect only the parts of a codebase that are likely to matter, helping it reach implementation faster and reduce unnecessary exploration. SWE-2 can generate and modify code, run tests, analyze repositories, work through terminal tasks, and verify whether implementations satisfy user requirements. Cognition also reports improvements in end-to-end test creation, regression detection, instruction following, and re-deriving conclusions when challenged. Its training process incorporates cost-aware rewards, length-weighted reward baselines, expanded reinforcement learning environments, and hardened verifiers intended to improve both efficiency and reliability. SWE-2 is positioned as a cost-efficient alternative to larger frontier coding models while remaining competitive on software engineering benchmarks such as FrontierCode, DeepSWE, and Terminal-Bench. The model is available in Devin Desktop and Devin CLI and is being introduced to additional Cognition products including Devin Web and Fusion.
API Access
Has API
API Access
Has API
Integrations
C
C++
CSS
Cerebras
Devin
Devin Desktop
JSON
Kotlin
Kubernetes
Lua
Integrations
C
C++
CSS
Cerebras
Devin
Devin Desktop
JSON
Kotlin
Kubernetes
Lua
Pricing Details
No price information available.
Free Trial
Free Version
Pricing Details
$20/month
Free Trial
Free Version
Deployment
Web-Based
On-Premises
iPhone App
iPad App
Android App
Windows
Mac
Linux
Chromebook
Deployment
Web-Based
On-Premises
iPhone App
iPad App
Android App
Windows
Mac
Linux
Chromebook
Customer Support
Business Hours
Live Rep (24/7)
Online Support
Customer Support
Business Hours
Live Rep (24/7)
Online Support
Types of Training
Training Docs
Webinars
Live Training (Online)
In Person
Types of Training
Training Docs
Webinars
Live Training (Online)
In Person
Vendor Details
Company Name
Cognigram
Country
United States
Website
www.cognigram.us/cognigram/about
Vendor Details
Company Name
Cognition
Founded
2023
Country
United States
Website
cognition.com