Topic
All digests tagged CI/CD
Suggested route
Move from earlier context through the available material to the newest signals. This route is a reading aid, not a difficulty ranking.
AI agents are solving the coding problem, but verification is the new bottleneck. Learn how Anthropic scaled to 30,000 merged changes daily and why multi-layered, zero-trust verification is mandatory for modern software factories.
Read article
Harness engineering is the infrastructure around LLMs, encompassing tools, context, guardrails, and telemetry. While LLMs introduce non-determinism, core software principles like CI/CD, security, and observability remain essential for building robust agents.
Read article
Stop guessing your LLM configs! Learn how to use data-driven benchmarking with BenchPod, a vLLM dashboard, to optimize parameters like max batch tokens and ensure reliable, production-ready AI deployments.
Read article
Learn how to build a fully autonomous 'Software Factory' using agent loops and feedback loops. Discover how to achieve 75% PR merge rates without human intervention, while maintaining cost control and model agnosticism.
Read article
Fuad Ali details the self-improvement loop for AI agents: trace failures, use Signal to detect issues, create living regression datasets, and run experiments to prove fixes. This automates reliability.
Read article
Harbor is an open-source framework for evaluating AI agents on real tasks using isolated sandboxes. It allows engineers to test agent changes by measuring side effects and optimizing metrics like tool call count, moving from 'vibes' to 'evidence.'
Read article
Managed Deep Agents streamlines the journey from local agent prototype to production. It couples the agent harness with LangSmith infrastructure, simplifying complex tasks like durable execution, multi-tenancy, and context governance.
Read article
The next leap in agentic engineering is moving from Human In the Loop to Out the Loop. This requires building durable, proactive agents in isolated sandboxes, mastering the Core Four (Context, Model, Prompt, Tools), and building the system that builds the system.
Read article
Agentic Engineering is the future of software development. Learn the five core concepts—Prompt, Context, Harness, Loop, and Graph Engineering—that power autonomous AI agents and automate the entire SDLC.
Read article
To ensure AI agent reliability, the speaker details a five-step regression loop. This process uses production traces as the source of truth, employing LLMs as judges to quantify subjective metrics and integrating automated gates into CI/CD.
Read article
Agentic coding is moving fast, creating massive efficiency but also unprecedented security risks. Experts discuss securing the 'software factory' and the need for new controls like identity and intent analysis.
Read article
Building rigorous evaluation systems for AI coding agents is complex. The talk details why public benchmarks fail and how to balance measurable vs. representative tasks, emphasizing observability and trace analysis.
Read article
Learn how to build reliable AI agents for high-stakes environments. We cover the AI Engineering Loop: tracing, dataset curation, and integrating automated evaluation (Evals) into your CI/CD pipeline to prevent regressions.
Read article
Anthropic introduces Flows in Claude Managed Agents, a multi-agent orchestration engine that allows a single goal to be executed by up to 1,000 collaborating agents. This solves the scaling problem of single agents and enables complex, verifiable AI workflows.
Read article
Transitioning AI agents to production requires a governed framework. Learn how to implement centralized MCP Gateways, LangGraph workflows, and robust CI/CD pipelines for secure, scalable, and observable enterprise AI.
Read article
Learn how to build a 'software factory' using agent feedback loops. We cover inner, middle, and outer loops, and why clear intent is crucial for self-healing codebases.
Read article
Learn how to manage Claude Managed Agents in CI/CD using Ancho CLI and YAML. We cover multi-tenancy, the coordinator pattern, and scaling with self-hosted sandboxes.
Read article
Discover how to improve browser agents without changing model weights using the AutoBrowse loop. This system pairs a Doer agent with a Teacher agent to generate reusable 'skill' files, dramatically increasing reliability and reducing operational costs on complex websites.
Read article
Learn how to build reproducible AI agent evaluation pipelines using WolfBench. Discover why single scores are insufficient and how to track consistency, cost, and capability across six critical pipeline layers.
Read article
Discover how to build ultra-fast AI agents and MCP servers using WebAssembly, Spin, and Akamai Functions. Learn how to achieve global distribution with zero cold starts.
Read article