Results for “Best Practices”
8 matches across blog posts, projects, case studies and series.
Blog posts
Best Practices for Deploying LangChain Apps to Production
Serving, streaming, per-user state, caching, tracing, evals, secrets and timeouts: a checklist for moving a LangChain 1.x agent out of the notebook, checked ag…
Oct 9, 2026Day 15/15 — Build a Complete Headless Salesforce AI Assistant
The capstone: a Next.js assistant that signs in with PKCE, lets Claude call Salesforce hosted MCP servers as the user, and asks before every write.
Oct 9, 2026Day 14/15 — Production Architecture: Governance, Monitoring & Error Handling
Take a Salesforce AI assistant to production: who approves tools, what Salesforce logs, how to classify and retry errors, and which limits and costs to plan fo…
Oct 9, 2026Day 11/15 — Security Architecture: OAuth, Permissions & Least Privilege
A threat model for AI clients on Salesforce, the layers that contain them, where tokens go, why there is no integration user, and a least-privilege permission …
Oct 9, 2026Day 10/15 — Build Your First AI + Salesforce Workflow
Turn a chat into a workflow: a read-only meeting prep brief built with Next.js, the Claude API's MCP connector and Salesforce hosted MCP servers.
Oct 9, 2026Day 9/15 — Create & Update Salesforce Data Safely
Let Claude write to Salesforce without losing control: what still runs on every write, the propose, confirm, execute, verify loop, and a confirm-before-write p…
Oct 9, 2026Day 8/15 — Read Salesforce Data Using Natural Language
Ask Salesforce questions in plain language and trust the answers: how Claude picks soqlQuery, find or getRelatedRecords, prompt patterns, verification and limi…
Oct 9, 2026Day 7/15 — Explore Salesforce MCP Tools & sobject-all
What Claude can actually call in your org: the 11 sobject-all tools, the smaller servers, how to read a tool definition, MCP Inspector, and the beta Headless 3…