Channel
Digests from AI Engineer
Automattic shares its strategy for building AI fluency in a fully remote company. They advocate for two-week immersive programs, focusing on real project work and advanced topics like autonomous agents and MCPs.
Read article
Running AI agents in production requires separating the 'brain' (LLM planning) from the 'hands' (deterministic harness). This approach treats agent harnesses as late-bound sagas, ensuring reliability and durability for complex, long-running workflows.
Read article
Learn how Postman mapped 115 microservices into an API context graph to enable coding agents to function across complex, distributed systems. Discover how to improve API discovery and impact assessment.
Read article
Bigger context windows won't save your AI agents. Learn why models lose information in the middle and master the four strategies of Context Engineering: Externalize, Select, Compress, and Isolate.
Read article
AI attackers are faster than traditional pen tests. To keep up with the volume of insecure code generated by LLMs, security must shift to continuous, multi-agent offensive security running on every PR.
Read article
The Software Factory proposes an autonomous system of agents that converts input signals (like bug reports) into production code. The focus shifts from coding to governing agents, emphasizing model-agnostic principles and measuring outcomes like signal-to-production time.
Read article
Connecting agents is a distributed systems problem requiring solutions for ordered transport, persistence, and runtime binding. BAND introduces an interaction layer to solve the single-agent bottleneck.
Read article
The Gemini Interactions API handles server-side state and long-running background jobs, replacing user/model turns with a structured timeline of steps. Agents run in a managed cloud sandbox, allowing them to execute code and share persistent environments.
Read article
Scaling AI agents requires more than just tools. Success demands redesigning the entire workflow, remodeling roles, and building trust incrementally through automated code review and merging.
Read article
Learn how to build a self-improving company by turning agent failures into reusable skills. We discuss using MCP as the distribution layer and creating an organizational flywheel that captures hard-won knowledge.
Read article
For enterprise data, simple file traversal fails. We need an agentic 'harness' that combines hybrid search, metadata filtering, and specialized parsing (LlamaParse) to ground answers from massive, multimodal corporate documents.
Read article
AI companies are accidentally building banks. Scaling AI requires moving beyond simple usage billing to complex financial infrastructure that checks entitlements synchronously before consumption.
Read article
AI struggles with production because it spans code, infrastructure, and telemetry. To fix this, a robust agentic harness requires six pillars: Model Orchestration, Causal Reasoning, Context Engineering, and more.
Read article
Learn how to scale databases for the AI era. Ben Dicken covers essential principles like sharding, back pressure, and decoupling, and shows how AI agents can safely manage infrastructure using VSchema and Traffic Control.
Read article
Building agent quality platforms is a complex systems challenge. Learn why simple spreadsheets fail and how to build the continuous improvement loop using advanced tracing and observability.
Read article
Marc Klingen details the self-improving OSS agent stack, showing how AI can automate the loop between online tracing, offline datasets, and evaluations, moving teams from manual to automated agent refinement.
Read article
Codex is demonstrated as an advanced AI agent capable of automating complex, multi-stage development workflows. Learn how to use Goals, Subagents, and the App Server to build 'software factories' and manage entire CI/CD pipelines.
Read article
Discover how merchants can accept payments initiated by AI agents using protocols like ACP and UCP. Learn about MCP apps, tokenization, and the trade-offs between embedded and external checkout flows.
Read article
This workshop details how to master AI Observability by building a continuous agent improvement flywheel. Using Braintrust, engineers can derive signal from production traces via custom scoring and Topics, automating the process of identifying failures and proposing code changes.
Read article
To ensure AI safety, agents must run in sandboxes that are modeled after the task's intent. Safety comes from limiting tools and context, not from the harness itself.
Read article