Blog

Training an Agentic Router for Optimal Cost-Performance on SWE Tasks

Nic Becker, Rhythm Garg

Bringing Capabilities in Distribution via Relevance-Masked Self-Distillation

Raymond Feng, Pranav Vaid

Unlocking Real-Time Bug Detection at Cognition

How Applied Compute post-trained a specialized model that enabled 10x faster bug detection.

Memory in the wild: how we use Context Engine on our own code

Sam Denton, Dylan Yu, Raymond Feng

Remember, Refine, Retrieve: A Context Engine for Enterprise Agents

Sam Denton, Ben Scharfstein, Vinjai Vale

Benchmarking Inference Engines on Agentic Workloads

Oam Patel, Linden Li

Unlocking the AI Overhang

The case for forward deployment

Bryan Lee

The Advantage You Own

Applied Compute Raises $80M to Help Enterprises Advance from Generalized to Specific Intelligence

Yash, Rhythm, Linden

Speeding up RL with high-leverage samples

Agastya Goel, Linden Li

Building State-of-the-Art Agents with Mercor

How Applied Compute's long-horizon RL stack turned Mercor's expert data into a top ranked agent at a fraction of the cost

Automating Merchant Onboarding at DoorDash

How DoorDash trained a proprietary agent using internal experts and delivered a 30% relative reduction in critical menu errors

It's time to get specific

Yash, Rhythm, Linden