Notes from the foundry
Engineering essays on generative AI, retrieval systems, and what it takes to ship intelligent software to production.
Teaching an Agent Our Client Reporting Playbook with Vercel AI SDK v7 Skills
Our monthly client reports followed a 40-line prompt nobody dared touch. I moved the whole playbook into an uploaded skill using the new uploadSkill API in Vercel AI SDK v7.
AI Agent Development vs Chatbot Development: What You Need to Know
Confused about AI agent development vs chatbot development? Discover the key differences, explore AI agent implementation services, and find the best platform for AI agent development.
Hiring an AI Automation Agency vs. Building an In-House AI Team
Deciding between an AI automation agency and an in-house team? Explore the pros, cons, costs, and risks associated with each approach for your next AI project.
Antigravity IDE: The Next Evolution of Autonomous Coding
Explore how Antigravity IDE and the Antigravity CLI are reshaping software engineering with persistent, autonomous agent workspaces.
How Financial Services Firms Are Using Autonomous Agents
Explore how the finance sector is leveraging custom AI agents for quantitative analysis, automated reporting, and secure data processing.
Building AI Agents with the Grok xAI API
Build agents on xAI's Grok models: function calling, Grok Build, streaming, and an honest look at where Grok fits against other providers.
Claude Code CLI Hacks: Pro Tips for Agentic Development
Master the Claude Code CLI with these pro hacks, tips, and tricks. Learn how to manage context, build custom skills, and speed up your agentic workflow.
How Much Does It Cost to Build a Custom AI Agent in 2026?
A comprehensive breakdown of the costs involved in building a custom AI agent. Learn about build costs, inference fees, maintenance, and how to budget for your next AI project.
Cursor AI vs GitHub Copilot: The Ultimate Guide for Agentic Coding
Comparing Cursor AI and GitHub Copilot for agentic development. Learn which AI coding assistant offers the best context management, codebase indexing, and autonomous editing.
Custom AI Development vs. Buying Off-The-Shelf SaaS Platforms
Choosing between a custom AI agent and an off-the-shelf SaaS product? Learn when to buy, when to build, and how to evaluate your business's unique needs.
Escaping LLM Vendor Lock-in: Migrating to Open-Source Models
Learn how to architect your AI applications to avoid LLM vendor lock-in. Discover strategies for migrating from OpenAI to self-hosted models like Llama 3.
The Hidden Costs of AI Implementation (And How to Avoid Them)
Discover the hidden pitfalls and unexpected costs of enterprise AI implementation, from token bloat to maintenance overhead, and how to mitigate them.
Building HIPAA-Compliant AI Agents for Healthcare Workflows
A technical guide to building secure, HIPAA-compliant AI agents in healthcare. Learn about self-hosted models, zero-retention policies, and sandboxing PHI.
Hire AI Agent Developers: A Guide for Enterprise CTOs
Looking to hire AI agent developers? Learn how to find an enterprise AI agent development partner that can deliver custom, production-ready autonomous systems.
Why Your RAG Pipeline is Failing (And How to Fix It)
Struggling with a poorly performing RAG pipeline? Learn advanced techniques like semantic routing, query expansion, and hybrid search to fix your AI architecture.
Grok 4.5 vs Muse Spark 1.1: An Independent Comparison After Ten Days in Production
Grok 4.5 and Muse Spark 1.1 launched a day apart at similar prices. An independent head-to-head from a team running both in production: token efficiency, tool use, orchestration, and which one belongs in your stack.
Building a Durable AIOps On-Call Agent with Eve.dev
Build an AIOps on-call agent with Eve.dev that triages alerts, runs diagnostics, and gates risky remediation behind human approval, surviving restarts.
Multi-Agent Orchestration in Eve.dev: An Autonomous Accounts-Payable Pipeline
Use Eve.dev's multi-agent orchestration to build an accounts-payable pipeline: a supervisor delegates invoice extraction, 3-way matching, and durable approvals.
The Ultimate Research Assistant: Processing 100-Page Contracts with Kimi K3
Explore how legal and financial professionals are using Moonshot AI's Kimi K3 model to analyze massive documents, identify loopholes, and extract key insights in seconds.
Mastering Large Codebases: How Kimi K3 Transforms Legacy Code Refactoring
Discover how Moonshot AI's new Kimi K3 model uses its 1-million token context window to help developers refactor massive legacy enterprise applications without losing context.