Harness Engineering: Building the Production Cage for Powerful Domain Agents — Mike Chambers, AWS
Summary
The presentation introduces 'Harness Engineering,' a critical concept for building production-grade AI agents at scale. Mike Chambers distinguishes between agents that are used (e.g., coding assistants) and agents that are built. For built agents, the harness encompasses all non-model components—such as memory, skills, tools, identity, and context management—that must scale independently. The core principle is that scaling these components separately, rather than deploying them in a single container, is essential for handling thousands of users and maintaining reliability.
Key takeaways
-
Two Types of Agents
4:05
Agents are categorized into 'agents we use' (productivity tools, coding assistants) and 'agents we build' (production-scale systems). The approach for built agents requires careful architectural planning.
-
Defining the Harness
7:04
A harness is defined by subtraction: take an agent and remove the model component; everything left over is the harness. This includes the infrastructure, skills, and tools.
-
Scaling Built Agents
10:57
For production agents, the harness must manage complex concerns like loop management, scaling, payments, identity, runtime, context management, and observability. Attempting to containerize everything together is incorrect for high scale.
-
Avoiding 'Slop Ops'
10:07
Build engineers must avoid 'slop ops' (clicking around a console to deploy resources). Instead, agents must build infrastructure using Infrastructure as Code (IaC) to maintain ownership and control over cloud deployments.
Technical details
-
Agent Architecture and Scaling
838s
To achieve scalability for thousands of users, components like memory and loop management must be deployed as separate, managed infrastructures, allowing them to scale independently from the core agent logic.
-
AWS Agent Core Deployment
1016s
The process utilizes the `agentcore` command line tool to deploy agents. This tool facilitates the deployment of multiple components (e.g., memory, agent runtime) as separate, scalable cloud infrastructure, enabling multi-tenant isolation.
-
Memory Management
1016s
The system can be configured to deploy both long-term and short-term memory as managed cloud infrastructure, ensuring state persistence and retrieval across asynchronous agent invocations.
-
Minimalist Agent Definition
A highly simplified agent can be deployed using only a JSON configuration file specifying a model and a system prompt, demonstrating that much of the agentic functionality can be managed by the core infrastructure.
Mentioned resources
- AWS Agent Toolkit
- Amazon Bedrock Agent Core
- Strands agents SDK
Channel & topics
Watch on YouTube · Back to latest
This independent, AI-assisted summary is provided for commentary and informational purposes. It may contain errors or omit important context. Please watch the original video for the creator's complete presentation. Video, thumbnail, and related copyrights belong to their respective owners.