Skip to content
fx-blog
agentic-fx field notes

Build software with AI agents on five pillars.

Intelligence, memory, judgment, verification and value: the bar we hold every AI-built tool to, with the code and the numbers to prove it.

73 posts9 categories5 pillars
afx install --bundle dev✓ gate G1 passed, evidence kept
  • IntelligenceThink before you build
  • MemoryNever repeat a mistake
  • JudgmentAsk, don’t invent
  • VerificationProve it with checks
  • ValueWorth the cost

Several Machines, One p99 You Can Defend

Three storefront agents reported p99 of 43.52, 42.50 and 42.50 ms. Their average is 42.837; the fleet's p99 is 42.496. surge merges the agents' histograms bucket by bucket and evaluates the thresholds once, so several machines produce one verdict.

4 min readAdvanced

Your Load Test Went Green. What Did It Measure?

A load test's number is always true about something — and it may be true about your laptop. surge watches its own CPU, marks a run untrustworthy above 85 % instead of reporting a pass, and keeps 512 bytes of what the server replied to every distinct failure.

4 min readBeginner

A Test That Passed on Retry Is Not Green

CI retries a failing test, the retry passes, and the pipeline goes green with a flaky test inside it. How the playwright template stops that: retries run isolated at the end, and a release gate reads the JSON report and fails on any flaky smoke or critical pass.

4 min readIntermediate

The Retry Button Is Hiding Your Flaky Tests

A test that fails, is retried and passes counts as green. Flaky tests in CI need rules: retry only runner faults, let the gate block a pass on retry, run one commit five times to find the rest, and quarantine each with an owner and a 30-day expiry.

4 min readIntermediate

A Green Pipeline That Ran Zero Tests

A test command that collects nothing exits 0, and the pipeline goes green. A CI quality gate with three outcomes fixes it: test jobs only report, one gate reads every report against quality-gate.yml, and no evidence means NOT EVALUABLE, exit 3.

5 min readIntermediate

When Zero Findings Means Nothing Was Read

A security scan with zero findings looks the same whether the scanner read the code or not. ai-sec, an AI security assessment bundle for Claude Code, grades a module blind when its scanner could not read the target, and lists every gap under Could not evaluate.

4 min readBeginner

Manage the Team: Goals, Trust and Delivery

Eleven goals nobody remembers, and a red result found in week 12, cost a lead the team's focus and the boss's trust. Set a few measurable results with one owner each, send a five-line update weekly, and report red early with a plan.

4 min readIntermediate

One-to-Ones That Matter, and Handling Conflict

Skip one-to-ones and you hear about trouble when someone stops coming to standup. Hold them weekly with their agenda first; when two people clash, talk to each privately, then together, and end on a shared rule, not a winner.

4 min readIntermediate

Hire and Grow Your Crew

Hiring on gut feel picks whoever talks best. Decide what the job needs before you meet anyone, ask every candidate the same questions, score each answer alone before the debrief, then start your hire on a 30-60-90 plan with a buddy.

4 min readIntermediate

From Best Engineer to First-Time Lead

A new lead who keeps the hardest ticket becomes the bottleneck and codes at night to catch up. Your output is now what the team ships: unblock first, review within a day, and hand the work you love to someone who can own it.

4 min readIntermediate
Load more posts20 posts per page, newest first
Newsletter

Get the next post by email

One email per new post, reviewed by hand before it is sent. Pick the whole site or only the categories you follow. Unsubscribe in one click.

+ 6 more