Field notes

Implementation playbooks from the field.

Production AI patterns we ship every week. Stuck pilots, MCP hardening, eval suites, agent orchestration, cost control. Written by Alex Cinovoj, Founder and CTO of TechTide AI. No vendor pitches, no recycled blog posts.

5 of 22 field notes · 2026 archive

All topics Agents Coding agents Cost control Delivery Evals Governance Human in the loop MCP Model choice Observability Orchestration Retrieval ROI Security

June 2026

FIELD NOTE9 min · 2026-06-24

The AI technical debt nobody put on the roadmap.

Six months after the first AI feature ships, the debt shows up as prompt sprawl, untyped tools, no eval baseline, and nobody able to say what changed. How we pay it down.

Read field note →

ANALYSIS10 min · 2026-06-17

The harness matters more than the model now.

Model swaps stopped moving the needle. The gains now come from the harness around the model: durable state, checkpoints, retry policy, budget ceilings, and clean recovery.

Read field note →

April 2026

PLAYBOOK9 min · 2026-04-22

If you cannot replay it, you cannot ship it.

Debugging an agent from a chat transcript is guesswork. Log the full run as a trace, keep cost and latency on the same timeline, and alert on tool-level failures.

Read field note →

March 2026

PLAYBOOK9 min · 2026-03-25

Treat tokens like cloud spend, or the invoice will teach you.

Nobody plans an AI budget overrun. They just never set a ceiling. Per-task budgets, tiered routing, context hygiene, caching, and one dashboard with a named owner.

Read field note →

February 2026

PLAYBOOK10 min · 2026-02-11

Build an agent eval suite in five days.

No eval suite means every change is a vibe. Five days: harvest real tasks, write assertions, set the pass bar, wire CI, then gate deploys on it.

Read field note →

Ship the next version of your AI system

Start with the $1,000 AI Audit