AI Careers10 min read
What Is Different About Selling AI
Usage pricing, pilots judged by evals, technical buyers and data questions: what changes for an AE, SDR, SE or CSM when the product is AI.
Published · Updated
Blog
Every post, newest first. Pick a pillar or browse the full archive. Page 4 of 9.
Automation Workflows18 min read
Build an Invoice Pipeline in n8n With a Review Branch
Import a tested n8n workflow that validates extracted invoice fields and routes exceptions to review, then swap in Gmail, Datalab and Sheets.
Published · Updated
Tools & Comparisons14 min read
Codex vs Claude Code vs Cursor: Workflows, Guardrails and Prices
Codex, Claude Code and Cursor compared from their docs: how each would handle one disclosed task, their guardrails, and plan prices checked September 2026.
Published · Updated
Agents & AI Engineering9 min read
Agent Design Patterns: Run Four Control Flows and Their Failures
Run four small agent shapes on fake support tickets and watch what each one does when a step fails, stalls or gets an unclear request.
Published · Updated
Agents & AI Engineering9 min read
Choose an Agent Starter: Inspect Three Repositories and Test One
Compare a Python agent backend, a LangGraph chat UI and a full-stack chatbot, then check one starter at a fixed version without paying for model calls.
Published · Updated
Agents & AI Engineering8 min read
Agent Evaluation Tools: Compare Five Options on One Ticket Task
Run a local Pydantic Evals test, then see how Promptfoo, LangSmith, Braintrust and plain Python handle the same ten tickets and the same scoring rules.
Published · Updated
Agents & AI Engineering8 min read
AI APIs for Beginners: Make a Request and Handle the Response
Make a Claude Messages API request in Python, validate its JSON response, and test authentication, rate limits and bad output with local fixtures.
Published · Updated
Agents & AI Engineering8 min read
Evaluate a Ticket Agent: Dataset, Scoring Code and Failure Report
Run ten support-ticket cases through two simple classifiers, score what they got wrong, and keep every failure in the report.
Published · Updated
Agents & AI Engineering8 min read
Human Approval for Agents: Store and Check the Exact Decision
Build an approval step in SQLite that refuses changed, outdated, expired or revoked requests, and never repeats finished work on retry.
Published · Updated
Agents & AI Engineering7 min read
Plan and Execute: Build a Bounded Ticket Workflow
Run a four-step ticket workflow that checks its plan first, caps how much work it does, can be canceled, and shows what a failed step blocks.
Published · Updated
Agents & AI Engineering7 min read
Build Persistent Agent Memory with Updates, Expiry and Deletion
Build a SQLite memory store that keeps users apart, catches outdated updates, records where each value came from, and handles expiry and deletion.
Published · Updated
Agents & AI Engineering8 min read
Build a Small RAG Pipeline and Measure What It Misses
Build a six-document RAG pipeline, check its citations, filter out private and outdated documents, and measure the synonym question it misses.
Published · Updated